Refactor naming of unary elementwise microkernels

Prefix vector unary elementwise microkernels with V for consistency with other vector microkernels.

PiperOrigin-RevId: 372273672
diff --git a/src/f16-clamp/gen/neonfp16arith-x16.c b/src/f16-vclamp/gen/neonfp16arith-x16.c
similarity index 95%
rename from src/f16-clamp/gen/neonfp16arith-x16.c
rename to src/f16-vclamp/gen/neonfp16arith-x16.c
index a4e7e2f..52998dc 100644
--- a/src/f16-clamp/gen/neonfp16arith-x16.c
+++ b/src/f16-vclamp/gen/neonfp16arith-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f16-clamp/neonfp16arith.c.in
+//   Template: src/f16-vclamp/neonfp16arith.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f16_clamp_ukernel__neonfp16arith_x16(
+void xnn_f16_vclamp_ukernel__neonfp16arith_x16(
     size_t n,
     const void* restrict x_ptr,
     void* restrict y_ptr,
diff --git a/src/f16-clamp/gen/neonfp16arith-x8.c b/src/f16-vclamp/gen/neonfp16arith-x8.c
similarity index 94%
rename from src/f16-clamp/gen/neonfp16arith-x8.c
rename to src/f16-vclamp/gen/neonfp16arith-x8.c
index 6b1bd63..85c4ffb 100644
--- a/src/f16-clamp/gen/neonfp16arith-x8.c
+++ b/src/f16-vclamp/gen/neonfp16arith-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f16-clamp/neonfp16arith.c.in
+//   Template: src/f16-vclamp/neonfp16arith.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f16_clamp_ukernel__neonfp16arith_x8(
+void xnn_f16_vclamp_ukernel__neonfp16arith_x8(
     size_t n,
     const void* restrict x_ptr,
     void* restrict y_ptr,
diff --git a/src/f16-clamp/neonfp16arith.c.in b/src/f16-vclamp/neonfp16arith.c.in
similarity index 97%
rename from src/f16-clamp/neonfp16arith.c.in
rename to src/f16-vclamp/neonfp16arith.c.in
index a909f9b..5a67d12 100644
--- a/src/f16-clamp/neonfp16arith.c.in
+++ b/src/f16-vclamp/neonfp16arith.c.in
@@ -14,7 +14,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f16_clamp_ukernel__neonfp16arith_x${BATCH_TILE}(
+void xnn_f16_vclamp_ukernel__neonfp16arith_x${BATCH_TILE}(
     size_t n,
     const void* restrict x_ptr,
     void* restrict y_ptr,
diff --git a/src/f16-hswish/gen/hswish-neonfp16arith-x16.c b/src/f16-vhswish/gen/vhswish-neonfp16arith-x16.c
similarity index 96%
rename from src/f16-hswish/gen/hswish-neonfp16arith-x16.c
rename to src/f16-vhswish/gen/vhswish-neonfp16arith-x16.c
index 2139609..72dfb6d 100644
--- a/src/f16-hswish/gen/hswish-neonfp16arith-x16.c
+++ b/src/f16-vhswish/gen/vhswish-neonfp16arith-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f16-hswish/neonfp16arith.c.in
+//   Template: src/f16-vhswish/neonfp16arith.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f16_hswish_ukernel__neonfp16arith_x16(
+void xnn_f16_vhswish_ukernel__neonfp16arith_x16(
     size_t n,
     const void* restrict x_ptr,
     void* restrict y_ptr,
diff --git a/src/f16-hswish/gen/hswish-neonfp16arith-x8.c b/src/f16-vhswish/gen/vhswish-neonfp16arith-x8.c
similarity index 95%
rename from src/f16-hswish/gen/hswish-neonfp16arith-x8.c
rename to src/f16-vhswish/gen/vhswish-neonfp16arith-x8.c
index 1c6d001..b34efcc 100644
--- a/src/f16-hswish/gen/hswish-neonfp16arith-x8.c
+++ b/src/f16-vhswish/gen/vhswish-neonfp16arith-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f16-hswish/neonfp16arith.c.in
+//   Template: src/f16-vhswish/neonfp16arith.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f16_hswish_ukernel__neonfp16arith_x8(
+void xnn_f16_vhswish_ukernel__neonfp16arith_x8(
     size_t n,
     const void* restrict x_ptr,
     void* restrict y_ptr,
diff --git a/src/f16-hswish/neonfp16arith.c.in b/src/f16-vhswish/neonfp16arith.c.in
similarity index 97%
rename from src/f16-hswish/neonfp16arith.c.in
rename to src/f16-vhswish/neonfp16arith.c.in
index 1f46606..6d8d161 100644
--- a/src/f16-hswish/neonfp16arith.c.in
+++ b/src/f16-vhswish/neonfp16arith.c.in
@@ -14,7 +14,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f16_hswish_ukernel__neonfp16arith_x${BATCH_TILE}(
+void xnn_f16_vhswish_ukernel__neonfp16arith_x${BATCH_TILE}(
     size_t n,
     const void* restrict x_ptr,
     void* restrict y_ptr,
diff --git a/src/f16-relu/gen/neonfp16arith-x16.c b/src/f16-vrelu/gen/neonfp16arith-x16.c
similarity index 94%
rename from src/f16-relu/gen/neonfp16arith-x16.c
rename to src/f16-vrelu/gen/neonfp16arith-x16.c
index e731bd9..904a267 100644
--- a/src/f16-relu/gen/neonfp16arith-x16.c
+++ b/src/f16-vrelu/gen/neonfp16arith-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f16-relu/neonfp16arith.c.in
+//   Template: src/f16-vrelu/neonfp16arith.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f16_relu_ukernel__neonfp16arith_x16(
+void xnn_f16_vrelu_ukernel__neonfp16arith_x16(
     size_t n,
     const void* restrict x_ptr,
     void* restrict y_ptr,
diff --git a/src/f16-relu/gen/neonfp16arith-x8.c b/src/f16-vrelu/gen/neonfp16arith-x8.c
similarity index 93%
rename from src/f16-relu/gen/neonfp16arith-x8.c
rename to src/f16-vrelu/gen/neonfp16arith-x8.c
index 70435d5..c404cd8 100644
--- a/src/f16-relu/gen/neonfp16arith-x8.c
+++ b/src/f16-vrelu/gen/neonfp16arith-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f16-relu/neonfp16arith.c.in
+//   Template: src/f16-vrelu/neonfp16arith.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f16_relu_ukernel__neonfp16arith_x8(
+void xnn_f16_vrelu_ukernel__neonfp16arith_x8(
     size_t n,
     const void* restrict x_ptr,
     void* restrict y_ptr,
diff --git a/src/f16-relu/neonfp16arith.c.in b/src/f16-vrelu/neonfp16arith.c.in
similarity index 96%
rename from src/f16-relu/neonfp16arith.c.in
rename to src/f16-vrelu/neonfp16arith.c.in
index 2ee136e..fe4cbfb 100644
--- a/src/f16-relu/neonfp16arith.c.in
+++ b/src/f16-vrelu/neonfp16arith.c.in
@@ -14,7 +14,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f16_relu_ukernel__neonfp16arith_x${BATCH_TILE}(
+void xnn_f16_vrelu_ukernel__neonfp16arith_x${BATCH_TILE}(
     size_t n,
     const void* restrict x_ptr,
     void* restrict y_ptr,
diff --git a/src/f32-clamp/avx.c.in b/src/f32-vclamp/avx.c.in
similarity index 97%
rename from src/f32-clamp/avx.c.in
rename to src/f32-vclamp/avx.c.in
index a9725d4..602023c 100644
--- a/src/f32-clamp/avx.c.in
+++ b/src/f32-vclamp/avx.c.in
@@ -16,7 +16,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_clamp_ukernel__avx_x${BATCH_TILE}(
+void xnn_f32_vclamp_ukernel__avx_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/avx512f.c.in b/src/f32-vclamp/avx512f.c.in
similarity index 97%
rename from src/f32-clamp/avx512f.c.in
rename to src/f32-vclamp/avx512f.c.in
index daa742b..091bdc5 100644
--- a/src/f32-clamp/avx512f.c.in
+++ b/src/f32-vclamp/avx512f.c.in
@@ -15,7 +15,7 @@
 #include <xnnpack/intrinsics-polyfill.h>
 
 
-void xnn_f32_clamp_ukernel__avx512f_x${BATCH_TILE}(
+void xnn_f32_vclamp_ukernel__avx512f_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/gen/avx-x16.c b/src/f32-vclamp/gen/avx-x16.c
similarity index 96%
rename from src/f32-clamp/gen/avx-x16.c
rename to src/f32-vclamp/gen/avx-x16.c
index ec75874..e0df409 100644
--- a/src/f32-clamp/gen/avx-x16.c
+++ b/src/f32-vclamp/gen/avx-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-clamp/avx.c.in
+//   Template: src/f32-vclamp/avx.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_clamp_ukernel__avx_x16(
+void xnn_f32_vclamp_ukernel__avx_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/gen/avx-x8.c b/src/f32-vclamp/gen/avx-x8.c
similarity index 95%
rename from src/f32-clamp/gen/avx-x8.c
rename to src/f32-vclamp/gen/avx-x8.c
index 8e6a511..c4e7639 100644
--- a/src/f32-clamp/gen/avx-x8.c
+++ b/src/f32-vclamp/gen/avx-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-clamp/avx.c.in
+//   Template: src/f32-vclamp/avx.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_clamp_ukernel__avx_x8(
+void xnn_f32_vclamp_ukernel__avx_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/gen/avx512f-x16.c b/src/f32-vclamp/gen/avx512f-x16.c
similarity index 94%
rename from src/f32-clamp/gen/avx512f-x16.c
rename to src/f32-vclamp/gen/avx512f-x16.c
index 27f8bdb..f53b3af 100644
--- a/src/f32-clamp/gen/avx512f-x16.c
+++ b/src/f32-vclamp/gen/avx512f-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-clamp/avx512f.c.in
+//   Template: src/f32-vclamp/avx512f.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/intrinsics-polyfill.h>
 
 
-void xnn_f32_clamp_ukernel__avx512f_x16(
+void xnn_f32_vclamp_ukernel__avx512f_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/gen/avx512f-x32.c b/src/f32-vclamp/gen/avx512f-x32.c
similarity index 95%
rename from src/f32-clamp/gen/avx512f-x32.c
rename to src/f32-vclamp/gen/avx512f-x32.c
index 57e386f..6f3338e 100644
--- a/src/f32-clamp/gen/avx512f-x32.c
+++ b/src/f32-vclamp/gen/avx512f-x32.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-clamp/avx512f.c.in
+//   Template: src/f32-vclamp/avx512f.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/intrinsics-polyfill.h>
 
 
-void xnn_f32_clamp_ukernel__avx512f_x32(
+void xnn_f32_vclamp_ukernel__avx512f_x32(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/gen/neon-x4.c b/src/f32-vclamp/gen/neon-x4.c
similarity index 94%
rename from src/f32-clamp/gen/neon-x4.c
rename to src/f32-vclamp/gen/neon-x4.c
index e8375f3..4bc3dbd 100644
--- a/src/f32-clamp/gen/neon-x4.c
+++ b/src/f32-vclamp/gen/neon-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-clamp/neon.c.in
+//   Template: src/f32-vclamp/neon.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_clamp_ukernel__neon_x4(
+void xnn_f32_vclamp_ukernel__neon_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/gen/neon-x8.c b/src/f32-vclamp/gen/neon-x8.c
similarity index 95%
rename from src/f32-clamp/gen/neon-x8.c
rename to src/f32-vclamp/gen/neon-x8.c
index 0c336c5..f533ffa 100644
--- a/src/f32-clamp/gen/neon-x8.c
+++ b/src/f32-vclamp/gen/neon-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-clamp/neon.c.in
+//   Template: src/f32-vclamp/neon.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_clamp_ukernel__neon_x8(
+void xnn_f32_vclamp_ukernel__neon_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/gen/scalar-x1.c b/src/f32-vclamp/gen/scalar-x1.c
similarity index 90%
rename from src/f32-clamp/gen/scalar-x1.c
rename to src/f32-vclamp/gen/scalar-x1.c
index de6fa0f..74948c0 100644
--- a/src/f32-clamp/gen/scalar-x1.c
+++ b/src/f32-vclamp/gen/scalar-x1.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-clamp/scalar.c.in
+//   Template: src/f32-vclamp/scalar.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -14,7 +14,7 @@
 #include <xnnpack/math.h>
 
 
-void xnn_f32_clamp_ukernel__scalar_x1(
+void xnn_f32_vclamp_ukernel__scalar_x1(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/gen/scalar-x2.c b/src/f32-vclamp/gen/scalar-x2.c
similarity index 93%
rename from src/f32-clamp/gen/scalar-x2.c
rename to src/f32-vclamp/gen/scalar-x2.c
index fba553a..ff9f6a2 100644
--- a/src/f32-clamp/gen/scalar-x2.c
+++ b/src/f32-vclamp/gen/scalar-x2.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-clamp/scalar.c.in
+//   Template: src/f32-vclamp/scalar.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -14,7 +14,7 @@
 #include <xnnpack/math.h>
 
 
-void xnn_f32_clamp_ukernel__scalar_x2(
+void xnn_f32_vclamp_ukernel__scalar_x2(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/gen/scalar-x4.c b/src/f32-vclamp/gen/scalar-x4.c
similarity index 94%
rename from src/f32-clamp/gen/scalar-x4.c
rename to src/f32-vclamp/gen/scalar-x4.c
index 8bfa73a..02efbba 100644
--- a/src/f32-clamp/gen/scalar-x4.c
+++ b/src/f32-vclamp/gen/scalar-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-clamp/scalar.c.in
+//   Template: src/f32-vclamp/scalar.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -14,7 +14,7 @@
 #include <xnnpack/math.h>
 
 
-void xnn_f32_clamp_ukernel__scalar_x4(
+void xnn_f32_vclamp_ukernel__scalar_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/gen/sse-x4.c b/src/f32-vclamp/gen/sse-x4.c
similarity index 94%
rename from src/f32-clamp/gen/sse-x4.c
rename to src/f32-vclamp/gen/sse-x4.c
index 50bd0bf..bbda3c8 100644
--- a/src/f32-clamp/gen/sse-x4.c
+++ b/src/f32-vclamp/gen/sse-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-clamp/sse.c.in
+//   Template: src/f32-vclamp/sse.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_clamp_ukernel__sse_x4(
+void xnn_f32_vclamp_ukernel__sse_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/gen/sse-x8.c b/src/f32-vclamp/gen/sse-x8.c
similarity index 95%
rename from src/f32-clamp/gen/sse-x8.c
rename to src/f32-vclamp/gen/sse-x8.c
index 22bd2c5..9371b20 100644
--- a/src/f32-clamp/gen/sse-x8.c
+++ b/src/f32-vclamp/gen/sse-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-clamp/sse.c.in
+//   Template: src/f32-vclamp/sse.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_clamp_ukernel__sse_x8(
+void xnn_f32_vclamp_ukernel__sse_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/gen/wasm-x1.c b/src/f32-vclamp/gen/wasm-x1.c
similarity index 91%
rename from src/f32-clamp/gen/wasm-x1.c
rename to src/f32-vclamp/gen/wasm-x1.c
index 1f23c3e..dbb71ae 100644
--- a/src/f32-clamp/gen/wasm-x1.c
+++ b/src/f32-vclamp/gen/wasm-x1.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-clamp/scalar.c.in
+//   Template: src/f32-vclamp/scalar.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -14,7 +14,7 @@
 #include <xnnpack/math.h>
 
 
-void xnn_f32_clamp_ukernel__wasm_x1(
+void xnn_f32_vclamp_ukernel__wasm_x1(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/gen/wasm-x2.c b/src/f32-vclamp/gen/wasm-x2.c
similarity index 93%
rename from src/f32-clamp/gen/wasm-x2.c
rename to src/f32-vclamp/gen/wasm-x2.c
index 5100b81..9e1092e 100644
--- a/src/f32-clamp/gen/wasm-x2.c
+++ b/src/f32-vclamp/gen/wasm-x2.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-clamp/scalar.c.in
+//   Template: src/f32-vclamp/scalar.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -14,7 +14,7 @@
 #include <xnnpack/math.h>
 
 
-void xnn_f32_clamp_ukernel__wasm_x2(
+void xnn_f32_vclamp_ukernel__wasm_x2(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/gen/wasm-x4.c b/src/f32-vclamp/gen/wasm-x4.c
similarity index 94%
rename from src/f32-clamp/gen/wasm-x4.c
rename to src/f32-vclamp/gen/wasm-x4.c
index 2fbefb6..fa966eb 100644
--- a/src/f32-clamp/gen/wasm-x4.c
+++ b/src/f32-vclamp/gen/wasm-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-clamp/scalar.c.in
+//   Template: src/f32-vclamp/scalar.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -14,7 +14,7 @@
 #include <xnnpack/math.h>
 
 
-void xnn_f32_clamp_ukernel__wasm_x4(
+void xnn_f32_vclamp_ukernel__wasm_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/gen/wasmsimd-arm-x4.c b/src/f32-vclamp/gen/wasmsimd-arm-x4.c
similarity index 93%
rename from src/f32-clamp/gen/wasmsimd-arm-x4.c
rename to src/f32-vclamp/gen/wasmsimd-arm-x4.c
index 35023b9..d0dc160 100644
--- a/src/f32-clamp/gen/wasmsimd-arm-x4.c
+++ b/src/f32-vclamp/gen/wasmsimd-arm-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-clamp/wasmsimd.c.in
+//   Template: src/f32-vclamp/wasmsimd.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_clamp_ukernel__wasmsimd_arm_x4(
+void xnn_f32_vclamp_ukernel__wasmsimd_arm_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/gen/wasmsimd-arm-x8.c b/src/f32-vclamp/gen/wasmsimd-arm-x8.c
similarity index 95%
rename from src/f32-clamp/gen/wasmsimd-arm-x8.c
rename to src/f32-vclamp/gen/wasmsimd-arm-x8.c
index 124b355..5438bd2 100644
--- a/src/f32-clamp/gen/wasmsimd-arm-x8.c
+++ b/src/f32-vclamp/gen/wasmsimd-arm-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-clamp/wasmsimd.c.in
+//   Template: src/f32-vclamp/wasmsimd.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_clamp_ukernel__wasmsimd_arm_x8(
+void xnn_f32_vclamp_ukernel__wasmsimd_arm_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/gen/wasmsimd-x86-x4.c b/src/f32-vclamp/gen/wasmsimd-x86-x4.c
similarity index 94%
rename from src/f32-clamp/gen/wasmsimd-x86-x4.c
rename to src/f32-vclamp/gen/wasmsimd-x86-x4.c
index 5917c8a..8e875bc 100644
--- a/src/f32-clamp/gen/wasmsimd-x86-x4.c
+++ b/src/f32-vclamp/gen/wasmsimd-x86-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-clamp/wasmsimd.c.in
+//   Template: src/f32-vclamp/wasmsimd.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_clamp_ukernel__wasmsimd_x86_x4(
+void xnn_f32_vclamp_ukernel__wasmsimd_x86_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/gen/wasmsimd-x86-x8.c b/src/f32-vclamp/gen/wasmsimd-x86-x8.c
similarity index 96%
rename from src/f32-clamp/gen/wasmsimd-x86-x8.c
rename to src/f32-vclamp/gen/wasmsimd-x86-x8.c
index 9e03cd2..6646103 100644
--- a/src/f32-clamp/gen/wasmsimd-x86-x8.c
+++ b/src/f32-vclamp/gen/wasmsimd-x86-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-clamp/wasmsimd.c.in
+//   Template: src/f32-vclamp/wasmsimd.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_clamp_ukernel__wasmsimd_x86_x8(
+void xnn_f32_vclamp_ukernel__wasmsimd_x86_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/neon.c.in b/src/f32-vclamp/neon.c.in
similarity index 97%
rename from src/f32-clamp/neon.c.in
rename to src/f32-vclamp/neon.c.in
index b8b3f10..49939e1 100644
--- a/src/f32-clamp/neon.c.in
+++ b/src/f32-vclamp/neon.c.in
@@ -14,7 +14,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_clamp_ukernel__neon_x${BATCH_TILE}(
+void xnn_f32_vclamp_ukernel__neon_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/scalar.c.in b/src/f32-vclamp/scalar.c.in
similarity index 95%
rename from src/f32-clamp/scalar.c.in
rename to src/f32-vclamp/scalar.c.in
index 88a5e32..441a444 100644
--- a/src/f32-clamp/scalar.c.in
+++ b/src/f32-vclamp/scalar.c.in
@@ -14,7 +14,7 @@
 
 $MIN_F32 = "__builtin_wasm_min_f32" if WASM else "math_min_f32"
 $MAX_F32 = "__builtin_wasm_max_f32" if WASM else "math_max_f32"
-void xnn_f32_clamp_ukernel__${"wasm" if WASM else "scalar"}_x${BATCH_TILE}(
+void xnn_f32_vclamp_ukernel__${"wasm" if WASM else "scalar"}_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/sse.c.in b/src/f32-vclamp/sse.c.in
similarity index 97%
rename from src/f32-clamp/sse.c.in
rename to src/f32-vclamp/sse.c.in
index 11b88f1..8dc29b4 100644
--- a/src/f32-clamp/sse.c.in
+++ b/src/f32-vclamp/sse.c.in
@@ -14,7 +14,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_clamp_ukernel__sse_x${BATCH_TILE}(
+void xnn_f32_vclamp_ukernel__sse_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-clamp/wasmsimd.c.in b/src/f32-vclamp/wasmsimd.c.in
similarity index 97%
rename from src/f32-clamp/wasmsimd.c.in
rename to src/f32-vclamp/wasmsimd.c.in
index 7e4b860..cf6a885 100644
--- a/src/f32-clamp/wasmsimd.c.in
+++ b/src/f32-vclamp/wasmsimd.c.in
@@ -14,7 +14,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_clamp_ukernel__wasmsimd_${"x86" if X86 else "arm"}_x${BATCH_TILE}(
+void xnn_f32_vclamp_ukernel__wasmsimd_${"x86" if X86 else "arm"}_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/avx.c.in b/src/f32-vhswish/avx.c.in
similarity index 98%
rename from src/f32-hswish/avx.c.in
rename to src/f32-vhswish/avx.c.in
index 884198a..04acbfe 100644
--- a/src/f32-hswish/avx.c.in
+++ b/src/f32-vhswish/avx.c.in
@@ -17,7 +17,7 @@
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
 $ISA = {0: "avx", 3: "fma3"}[FMA]
-void xnn_f32_hswish_ukernel__${ISA}_x${BATCH_TILE}(
+void xnn_f32_vhswish_ukernel__${ISA}_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/avx512f.c.in b/src/f32-vhswish/avx512f.c.in
similarity index 97%
rename from src/f32-hswish/avx512f.c.in
rename to src/f32-vhswish/avx512f.c.in
index 71291cd..bda36c4 100644
--- a/src/f32-hswish/avx512f.c.in
+++ b/src/f32-vhswish/avx512f.c.in
@@ -15,7 +15,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__avx512f_x${BATCH_TILE}(
+void xnn_f32_vhswish_ukernel__avx512f_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-avx-x16.c b/src/f32-vhswish/gen/vhswish-avx-x16.c
similarity index 97%
rename from src/f32-hswish/gen/hswish-avx-x16.c
rename to src/f32-vhswish/gen/vhswish-avx-x16.c
index 978f385..ed263e2 100644
--- a/src/f32-hswish/gen/hswish-avx-x16.c
+++ b/src/f32-vhswish/gen/vhswish-avx-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/avx.c.in
+//   Template: src/f32-vhswish/avx.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_hswish_ukernel__avx_x16(
+void xnn_f32_vhswish_ukernel__avx_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-avx-x8.c b/src/f32-vhswish/gen/vhswish-avx-x8.c
similarity index 96%
rename from src/f32-hswish/gen/hswish-avx-x8.c
rename to src/f32-vhswish/gen/vhswish-avx-x8.c
index 60dd9b9..6b8f4e3 100644
--- a/src/f32-hswish/gen/hswish-avx-x8.c
+++ b/src/f32-vhswish/gen/vhswish-avx-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/avx.c.in
+//   Template: src/f32-vhswish/avx.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_hswish_ukernel__avx_x8(
+void xnn_f32_vhswish_ukernel__avx_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-avx512f-x16.c b/src/f32-vhswish/gen/vhswish-avx512f-x16.c
similarity index 95%
rename from src/f32-hswish/gen/hswish-avx512f-x16.c
rename to src/f32-vhswish/gen/vhswish-avx512f-x16.c
index 5b838ba..43f919a 100644
--- a/src/f32-hswish/gen/hswish-avx512f-x16.c
+++ b/src/f32-vhswish/gen/vhswish-avx512f-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/avx512f.c.in
+//   Template: src/f32-vhswish/avx512f.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__avx512f_x16(
+void xnn_f32_vhswish_ukernel__avx512f_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-avx512f-x32.c b/src/f32-vhswish/gen/vhswish-avx512f-x32.c
similarity index 96%
rename from src/f32-hswish/gen/hswish-avx512f-x32.c
rename to src/f32-vhswish/gen/vhswish-avx512f-x32.c
index fab2af1..477fa12 100644
--- a/src/f32-hswish/gen/hswish-avx512f-x32.c
+++ b/src/f32-vhswish/gen/vhswish-avx512f-x32.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/avx512f.c.in
+//   Template: src/f32-vhswish/avx512f.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__avx512f_x32(
+void xnn_f32_vhswish_ukernel__avx512f_x32(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-fma3-x16.c b/src/f32-vhswish/gen/vhswish-fma3-x16.c
similarity index 97%
rename from src/f32-hswish/gen/hswish-fma3-x16.c
rename to src/f32-vhswish/gen/vhswish-fma3-x16.c
index dfb149d..3c455f0 100644
--- a/src/f32-hswish/gen/hswish-fma3-x16.c
+++ b/src/f32-vhswish/gen/vhswish-fma3-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/avx.c.in
+//   Template: src/f32-vhswish/avx.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_hswish_ukernel__fma3_x16(
+void xnn_f32_vhswish_ukernel__fma3_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-fma3-x8.c b/src/f32-vhswish/gen/vhswish-fma3-x8.c
similarity index 96%
rename from src/f32-hswish/gen/hswish-fma3-x8.c
rename to src/f32-vhswish/gen/vhswish-fma3-x8.c
index f38faf3..ea5d953 100644
--- a/src/f32-hswish/gen/hswish-fma3-x8.c
+++ b/src/f32-vhswish/gen/vhswish-fma3-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/avx.c.in
+//   Template: src/f32-vhswish/avx.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_hswish_ukernel__fma3_x8(
+void xnn_f32_vhswish_ukernel__fma3_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-neon-x16.c b/src/f32-vhswish/gen/vhswish-neon-x16.c
similarity index 97%
rename from src/f32-hswish/gen/hswish-neon-x16.c
rename to src/f32-vhswish/gen/vhswish-neon-x16.c
index 6cf31a6..b667772 100644
--- a/src/f32-hswish/gen/hswish-neon-x16.c
+++ b/src/f32-vhswish/gen/vhswish-neon-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/neon.c.in
+//   Template: src/f32-vhswish/neon.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__neon_x16(
+void xnn_f32_vhswish_ukernel__neon_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-neon-x4.c b/src/f32-vhswish/gen/vhswish-neon-x4.c
similarity index 95%
rename from src/f32-hswish/gen/hswish-neon-x4.c
rename to src/f32-vhswish/gen/vhswish-neon-x4.c
index 818308d..92a4e4f 100644
--- a/src/f32-hswish/gen/hswish-neon-x4.c
+++ b/src/f32-vhswish/gen/vhswish-neon-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/neon.c.in
+//   Template: src/f32-vhswish/neon.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__neon_x4(
+void xnn_f32_vhswish_ukernel__neon_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-neon-x8.c b/src/f32-vhswish/gen/vhswish-neon-x8.c
similarity index 96%
rename from src/f32-hswish/gen/hswish-neon-x8.c
rename to src/f32-vhswish/gen/vhswish-neon-x8.c
index f949f8b..5f888c5 100644
--- a/src/f32-hswish/gen/hswish-neon-x8.c
+++ b/src/f32-vhswish/gen/vhswish-neon-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/neon.c.in
+//   Template: src/f32-vhswish/neon.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__neon_x8(
+void xnn_f32_vhswish_ukernel__neon_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-scalar-x1.c b/src/f32-vhswish/gen/vhswish-scalar-x1.c
similarity index 91%
rename from src/f32-hswish/gen/hswish-scalar-x1.c
rename to src/f32-vhswish/gen/vhswish-scalar-x1.c
index c93e22b..52c161c 100644
--- a/src/f32-hswish/gen/hswish-scalar-x1.c
+++ b/src/f32-vhswish/gen/vhswish-scalar-x1.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/scalar.c.in
+//   Template: src/f32-vhswish/scalar.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -14,7 +14,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__scalar_x1(
+void xnn_f32_vhswish_ukernel__scalar_x1(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-scalar-x2.c b/src/f32-vhswish/gen/vhswish-scalar-x2.c
similarity index 94%
rename from src/f32-hswish/gen/hswish-scalar-x2.c
rename to src/f32-vhswish/gen/vhswish-scalar-x2.c
index d84310e..bd759e4 100644
--- a/src/f32-hswish/gen/hswish-scalar-x2.c
+++ b/src/f32-vhswish/gen/vhswish-scalar-x2.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/scalar.c.in
+//   Template: src/f32-vhswish/scalar.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -14,7 +14,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__scalar_x2(
+void xnn_f32_vhswish_ukernel__scalar_x2(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-scalar-x4.c b/src/f32-vhswish/gen/vhswish-scalar-x4.c
similarity index 95%
rename from src/f32-hswish/gen/hswish-scalar-x4.c
rename to src/f32-vhswish/gen/vhswish-scalar-x4.c
index 6ef7dfc..5a4cd0b 100644
--- a/src/f32-hswish/gen/hswish-scalar-x4.c
+++ b/src/f32-vhswish/gen/vhswish-scalar-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/scalar.c.in
+//   Template: src/f32-vhswish/scalar.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -14,7 +14,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__scalar_x4(
+void xnn_f32_vhswish_ukernel__scalar_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-sse-x4.c b/src/f32-vhswish/gen/vhswish-sse-x4.c
similarity index 95%
rename from src/f32-hswish/gen/hswish-sse-x4.c
rename to src/f32-vhswish/gen/vhswish-sse-x4.c
index da92c93..37fb945 100644
--- a/src/f32-hswish/gen/hswish-sse-x4.c
+++ b/src/f32-vhswish/gen/vhswish-sse-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/sse.c.in
+//   Template: src/f32-vhswish/sse.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__sse_x4(
+void xnn_f32_vhswish_ukernel__sse_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-sse-x8.c b/src/f32-vhswish/gen/vhswish-sse-x8.c
similarity index 96%
rename from src/f32-hswish/gen/hswish-sse-x8.c
rename to src/f32-vhswish/gen/vhswish-sse-x8.c
index 8072ec5..a163771 100644
--- a/src/f32-hswish/gen/hswish-sse-x8.c
+++ b/src/f32-vhswish/gen/vhswish-sse-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/sse.c.in
+//   Template: src/f32-vhswish/sse.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__sse_x8(
+void xnn_f32_vhswish_ukernel__sse_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-wasm-x1.c b/src/f32-vhswish/gen/vhswish-wasm-x1.c
similarity index 92%
rename from src/f32-hswish/gen/hswish-wasm-x1.c
rename to src/f32-vhswish/gen/vhswish-wasm-x1.c
index e3c520c..69a4018 100644
--- a/src/f32-hswish/gen/hswish-wasm-x1.c
+++ b/src/f32-vhswish/gen/vhswish-wasm-x1.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/scalar.c.in
+//   Template: src/f32-vhswish/scalar.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -14,7 +14,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__wasm_x1(
+void xnn_f32_vhswish_ukernel__wasm_x1(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-wasm-x2.c b/src/f32-vhswish/gen/vhswish-wasm-x2.c
similarity index 94%
rename from src/f32-hswish/gen/hswish-wasm-x2.c
rename to src/f32-vhswish/gen/vhswish-wasm-x2.c
index ed8bebb..2ff40e7 100644
--- a/src/f32-hswish/gen/hswish-wasm-x2.c
+++ b/src/f32-vhswish/gen/vhswish-wasm-x2.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/scalar.c.in
+//   Template: src/f32-vhswish/scalar.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -14,7 +14,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__wasm_x2(
+void xnn_f32_vhswish_ukernel__wasm_x2(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-wasm-x4.c b/src/f32-vhswish/gen/vhswish-wasm-x4.c
similarity index 95%
rename from src/f32-hswish/gen/hswish-wasm-x4.c
rename to src/f32-vhswish/gen/vhswish-wasm-x4.c
index 696d055..af429ca 100644
--- a/src/f32-hswish/gen/hswish-wasm-x4.c
+++ b/src/f32-vhswish/gen/vhswish-wasm-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/scalar.c.in
+//   Template: src/f32-vhswish/scalar.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -14,7 +14,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__wasm_x4(
+void xnn_f32_vhswish_ukernel__wasm_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-wasmsimd-x16.c b/src/f32-vhswish/gen/vhswish-wasmsimd-x16.c
similarity index 96%
rename from src/f32-hswish/gen/hswish-wasmsimd-x16.c
rename to src/f32-vhswish/gen/vhswish-wasmsimd-x16.c
index dcbcd77..d6d9e11 100644
--- a/src/f32-hswish/gen/hswish-wasmsimd-x16.c
+++ b/src/f32-vhswish/gen/vhswish-wasmsimd-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/wasmsimd.c.in
+//   Template: src/f32-vhswish/wasmsimd.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__wasmsimd_x16(
+void xnn_f32_vhswish_ukernel__wasmsimd_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-wasmsimd-x4.c b/src/f32-vhswish/gen/vhswish-wasmsimd-x4.c
similarity index 94%
rename from src/f32-hswish/gen/hswish-wasmsimd-x4.c
rename to src/f32-vhswish/gen/vhswish-wasmsimd-x4.c
index 0e63426..d245333 100644
--- a/src/f32-hswish/gen/hswish-wasmsimd-x4.c
+++ b/src/f32-vhswish/gen/vhswish-wasmsimd-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/wasmsimd.c.in
+//   Template: src/f32-vhswish/wasmsimd.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__wasmsimd_x4(
+void xnn_f32_vhswish_ukernel__wasmsimd_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/gen/hswish-wasmsimd-x8.c b/src/f32-vhswish/gen/vhswish-wasmsimd-x8.c
similarity index 96%
rename from src/f32-hswish/gen/hswish-wasmsimd-x8.c
rename to src/f32-vhswish/gen/vhswish-wasmsimd-x8.c
index a078759..8eb6890 100644
--- a/src/f32-hswish/gen/hswish-wasmsimd-x8.c
+++ b/src/f32-vhswish/gen/vhswish-wasmsimd-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-hswish/wasmsimd.c.in
+//   Template: src/f32-vhswish/wasmsimd.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__wasmsimd_x8(
+void xnn_f32_vhswish_ukernel__wasmsimd_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/neon.c.in b/src/f32-vhswish/neon.c.in
similarity index 97%
rename from src/f32-hswish/neon.c.in
rename to src/f32-vhswish/neon.c.in
index 61386b2..54a4184 100644
--- a/src/f32-hswish/neon.c.in
+++ b/src/f32-vhswish/neon.c.in
@@ -14,7 +14,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__neon_x${BATCH_TILE}(
+void xnn_f32_vhswish_ukernel__neon_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/scalar.c.in b/src/f32-vhswish/scalar.c.in
similarity index 96%
rename from src/f32-hswish/scalar.c.in
rename to src/f32-vhswish/scalar.c.in
index fa26801..48e1069 100644
--- a/src/f32-hswish/scalar.c.in
+++ b/src/f32-vhswish/scalar.c.in
@@ -14,7 +14,7 @@
 
 $MIN_F32 = "__builtin_wasm_min_f32" if WASM else "math_min_f32"
 $MAX_F32 = "__builtin_wasm_max_f32" if WASM else "math_max_f32"
-void xnn_f32_hswish_ukernel__${"wasm" if WASM else "scalar"}_x${BATCH_TILE}(
+void xnn_f32_vhswish_ukernel__${"wasm" if WASM else "scalar"}_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/sse.c.in b/src/f32-vhswish/sse.c.in
similarity index 97%
rename from src/f32-hswish/sse.c.in
rename to src/f32-vhswish/sse.c.in
index f3f78e1..518bafa 100644
--- a/src/f32-hswish/sse.c.in
+++ b/src/f32-vhswish/sse.c.in
@@ -14,7 +14,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__sse_x${BATCH_TILE}(
+void xnn_f32_vhswish_ukernel__sse_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-hswish/wasmsimd.c.in b/src/f32-vhswish/wasmsimd.c.in
similarity index 97%
rename from src/f32-hswish/wasmsimd.c.in
rename to src/f32-vhswish/wasmsimd.c.in
index 5854b26..aa31302 100644
--- a/src/f32-hswish/wasmsimd.c.in
+++ b/src/f32-vhswish/wasmsimd.c.in
@@ -14,7 +14,7 @@
 #include <xnnpack/hswish.h>
 
 
-void xnn_f32_hswish_ukernel__wasmsimd_x${BATCH_TILE}(
+void xnn_f32_vhswish_ukernel__wasmsimd_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/avx.c.in b/src/f32-vrelu/avx.c.in
similarity index 97%
rename from src/f32-relu/avx.c.in
rename to src/f32-vrelu/avx.c.in
index 600de42..5b9940e 100644
--- a/src/f32-relu/avx.c.in
+++ b/src/f32-vrelu/avx.c.in
@@ -16,7 +16,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_relu_ukernel__avx_x${BATCH_TILE}(
+void xnn_f32_vrelu_ukernel__avx_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/avx512f.c.in b/src/f32-vrelu/avx512f.c.in
similarity index 97%
rename from src/f32-relu/avx512f.c.in
rename to src/f32-vrelu/avx512f.c.in
index 9f5ccad..9e6e63c 100644
--- a/src/f32-relu/avx512f.c.in
+++ b/src/f32-vrelu/avx512f.c.in
@@ -15,7 +15,7 @@
 #include <xnnpack/intrinsics-polyfill.h>
 
 
-void xnn_f32_relu_ukernel__avx512f_x${BATCH_TILE}(
+void xnn_f32_vrelu_ukernel__avx512f_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/gen/avx-x16.c b/src/f32-vrelu/gen/avx-x16.c
similarity index 96%
rename from src/f32-relu/gen/avx-x16.c
rename to src/f32-vrelu/gen/avx-x16.c
index 8936e67..f35cd8d 100644
--- a/src/f32-relu/gen/avx-x16.c
+++ b/src/f32-vrelu/gen/avx-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/avx.c.in
+//   Template: src/f32-vrelu/avx.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_relu_ukernel__avx_x16(
+void xnn_f32_vrelu_ukernel__avx_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/gen/avx-x8.c b/src/f32-vrelu/gen/avx-x8.c
similarity index 95%
rename from src/f32-relu/gen/avx-x8.c
rename to src/f32-vrelu/gen/avx-x8.c
index c50c049..90ce548 100644
--- a/src/f32-relu/gen/avx-x8.c
+++ b/src/f32-vrelu/gen/avx-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/avx.c.in
+//   Template: src/f32-vrelu/avx.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_relu_ukernel__avx_x8(
+void xnn_f32_vrelu_ukernel__avx_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/gen/avx512f-x16.c b/src/f32-vrelu/gen/avx512f-x16.c
similarity index 93%
rename from src/f32-relu/gen/avx512f-x16.c
rename to src/f32-vrelu/gen/avx512f-x16.c
index 24f6cd4..88fd3df 100644
--- a/src/f32-relu/gen/avx512f-x16.c
+++ b/src/f32-vrelu/gen/avx512f-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/avx512f.c.in
+//   Template: src/f32-vrelu/avx512f.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/intrinsics-polyfill.h>
 
 
-void xnn_f32_relu_ukernel__avx512f_x16(
+void xnn_f32_vrelu_ukernel__avx512f_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/gen/avx512f-x32.c b/src/f32-vrelu/gen/avx512f-x32.c
similarity index 95%
rename from src/f32-relu/gen/avx512f-x32.c
rename to src/f32-vrelu/gen/avx512f-x32.c
index b0ed8d9..a830267 100644
--- a/src/f32-relu/gen/avx512f-x32.c
+++ b/src/f32-vrelu/gen/avx512f-x32.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/avx512f.c.in
+//   Template: src/f32-vrelu/avx512f.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/intrinsics-polyfill.h>
 
 
-void xnn_f32_relu_ukernel__avx512f_x32(
+void xnn_f32_vrelu_ukernel__avx512f_x32(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/gen/neon-x4.c b/src/f32-vrelu/gen/neon-x4.c
similarity index 93%
rename from src/f32-relu/gen/neon-x4.c
rename to src/f32-vrelu/gen/neon-x4.c
index d7d9c7f..422c63f 100644
--- a/src/f32-relu/gen/neon-x4.c
+++ b/src/f32-vrelu/gen/neon-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/neon.c.in
+//   Template: src/f32-vrelu/neon.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_relu_ukernel__neon_x4(
+void xnn_f32_vrelu_ukernel__neon_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/gen/neon-x8.c b/src/f32-vrelu/gen/neon-x8.c
similarity index 94%
rename from src/f32-relu/gen/neon-x8.c
rename to src/f32-vrelu/gen/neon-x8.c
index b164c00..ee06af6 100644
--- a/src/f32-relu/gen/neon-x8.c
+++ b/src/f32-vrelu/gen/neon-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/neon.c.in
+//   Template: src/f32-vrelu/neon.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_relu_ukernel__neon_x8(
+void xnn_f32_vrelu_ukernel__neon_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/gen/scalar-x1.c b/src/f32-vrelu/gen/scalar-x1.c
similarity index 90%
rename from src/f32-relu/gen/scalar-x1.c
rename to src/f32-vrelu/gen/scalar-x1.c
index bc4fa99..b2b13ab 100644
--- a/src/f32-relu/gen/scalar-x1.c
+++ b/src/f32-vrelu/gen/scalar-x1.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/scalar.c.in
+//   Template: src/f32-vrelu/scalar.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -13,7 +13,7 @@
 #include <xnnpack/common.h>
 #include <xnnpack/math.h>
 
-void xnn_f32_relu_ukernel__scalar_x1(
+void xnn_f32_vrelu_ukernel__scalar_x1(
     size_t n,
     const float* x_ptr,
     float* y_ptr,
diff --git a/src/f32-relu/gen/scalar-x2.c b/src/f32-vrelu/gen/scalar-x2.c
similarity index 92%
rename from src/f32-relu/gen/scalar-x2.c
rename to src/f32-vrelu/gen/scalar-x2.c
index 56b8a94..820a5c3 100644
--- a/src/f32-relu/gen/scalar-x2.c
+++ b/src/f32-vrelu/gen/scalar-x2.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/scalar.c.in
+//   Template: src/f32-vrelu/scalar.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -13,7 +13,7 @@
 #include <xnnpack/common.h>
 #include <xnnpack/math.h>
 
-void xnn_f32_relu_ukernel__scalar_x2(
+void xnn_f32_vrelu_ukernel__scalar_x2(
     size_t n,
     const float* x_ptr,
     float* y_ptr,
diff --git a/src/f32-relu/gen/scalar-x4.c b/src/f32-vrelu/gen/scalar-x4.c
similarity index 93%
rename from src/f32-relu/gen/scalar-x4.c
rename to src/f32-vrelu/gen/scalar-x4.c
index 6ce2d22..cb83c5c 100644
--- a/src/f32-relu/gen/scalar-x4.c
+++ b/src/f32-vrelu/gen/scalar-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/scalar.c.in
+//   Template: src/f32-vrelu/scalar.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -13,7 +13,7 @@
 #include <xnnpack/common.h>
 #include <xnnpack/math.h>
 
-void xnn_f32_relu_ukernel__scalar_x4(
+void xnn_f32_vrelu_ukernel__scalar_x4(
     size_t n,
     const float* x_ptr,
     float* y_ptr,
diff --git a/src/f32-relu/gen/scalar-x8.c b/src/f32-vrelu/gen/scalar-x8.c
similarity index 95%
rename from src/f32-relu/gen/scalar-x8.c
rename to src/f32-vrelu/gen/scalar-x8.c
index 8f14b15..e3db133 100644
--- a/src/f32-relu/gen/scalar-x8.c
+++ b/src/f32-vrelu/gen/scalar-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/scalar.c.in
+//   Template: src/f32-vrelu/scalar.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -13,7 +13,7 @@
 #include <xnnpack/common.h>
 #include <xnnpack/math.h>
 
-void xnn_f32_relu_ukernel__scalar_x8(
+void xnn_f32_vrelu_ukernel__scalar_x8(
     size_t n,
     const float* x_ptr,
     float* y_ptr,
diff --git a/src/f32-relu/gen/sse-x4.c b/src/f32-vrelu/gen/sse-x4.c
similarity index 93%
rename from src/f32-relu/gen/sse-x4.c
rename to src/f32-vrelu/gen/sse-x4.c
index d11f929..ff9ae29 100644
--- a/src/f32-relu/gen/sse-x4.c
+++ b/src/f32-vrelu/gen/sse-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/sse.c.in
+//   Template: src/f32-vrelu/sse.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_relu_ukernel__sse_x4(
+void xnn_f32_vrelu_ukernel__sse_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/gen/sse-x8.c b/src/f32-vrelu/gen/sse-x8.c
similarity index 94%
rename from src/f32-relu/gen/sse-x8.c
rename to src/f32-vrelu/gen/sse-x8.c
index 796744c..eec46a4 100644
--- a/src/f32-relu/gen/sse-x8.c
+++ b/src/f32-vrelu/gen/sse-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/sse.c.in
+//   Template: src/f32-vrelu/sse.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_relu_ukernel__sse_x8(
+void xnn_f32_vrelu_ukernel__sse_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/gen/wasm-x1.c b/src/f32-vrelu/gen/wasm-x1.c
similarity index 90%
rename from src/f32-relu/gen/wasm-x1.c
rename to src/f32-vrelu/gen/wasm-x1.c
index 5721bdb..09b098a 100644
--- a/src/f32-relu/gen/wasm-x1.c
+++ b/src/f32-vrelu/gen/wasm-x1.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/wasm.c.in
+//   Template: src/f32-vrelu/wasm.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -14,7 +14,7 @@
 #include <xnnpack/math.h>
 
 
-void xnn_f32_relu_ukernel__wasm_x1(
+void xnn_f32_vrelu_ukernel__wasm_x1(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/gen/wasm-x2.c b/src/f32-vrelu/gen/wasm-x2.c
similarity index 92%
rename from src/f32-relu/gen/wasm-x2.c
rename to src/f32-vrelu/gen/wasm-x2.c
index e0c3b54..586f6a3 100644
--- a/src/f32-relu/gen/wasm-x2.c
+++ b/src/f32-vrelu/gen/wasm-x2.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/wasm.c.in
+//   Template: src/f32-vrelu/wasm.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -14,7 +14,7 @@
 #include <xnnpack/math.h>
 
 
-void xnn_f32_relu_ukernel__wasm_x2(
+void xnn_f32_vrelu_ukernel__wasm_x2(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/gen/wasm-x4.c b/src/f32-vrelu/gen/wasm-x4.c
similarity index 93%
rename from src/f32-relu/gen/wasm-x4.c
rename to src/f32-vrelu/gen/wasm-x4.c
index 27508de..36fd228 100644
--- a/src/f32-relu/gen/wasm-x4.c
+++ b/src/f32-vrelu/gen/wasm-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/wasm.c.in
+//   Template: src/f32-vrelu/wasm.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -14,7 +14,7 @@
 #include <xnnpack/math.h>
 
 
-void xnn_f32_relu_ukernel__wasm_x4(
+void xnn_f32_vrelu_ukernel__wasm_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/gen/wasm-x8.c b/src/f32-vrelu/gen/wasm-x8.c
similarity index 95%
rename from src/f32-relu/gen/wasm-x8.c
rename to src/f32-vrelu/gen/wasm-x8.c
index c1e68f3..8477cfb 100644
--- a/src/f32-relu/gen/wasm-x8.c
+++ b/src/f32-vrelu/gen/wasm-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/wasm.c.in
+//   Template: src/f32-vrelu/wasm.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -14,7 +14,7 @@
 #include <xnnpack/math.h>
 
 
-void xnn_f32_relu_ukernel__wasm_x8(
+void xnn_f32_vrelu_ukernel__wasm_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/gen/wasmsimd-x16.c b/src/f32-vrelu/gen/wasmsimd-x16.c
similarity index 95%
rename from src/f32-relu/gen/wasmsimd-x16.c
rename to src/f32-vrelu/gen/wasmsimd-x16.c
index 32ad2e9..62fc992 100644
--- a/src/f32-relu/gen/wasmsimd-x16.c
+++ b/src/f32-vrelu/gen/wasmsimd-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/wasmsimd.c.in
+//   Template: src/f32-vrelu/wasmsimd.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_relu_ukernel__wasmsimd_x16(
+void xnn_f32_vrelu_ukernel__wasmsimd_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/gen/wasmsimd-x4.c b/src/f32-vrelu/gen/wasmsimd-x4.c
similarity index 93%
rename from src/f32-relu/gen/wasmsimd-x4.c
rename to src/f32-vrelu/gen/wasmsimd-x4.c
index c5b48d7..c15bb5e 100644
--- a/src/f32-relu/gen/wasmsimd-x4.c
+++ b/src/f32-vrelu/gen/wasmsimd-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/wasmsimd.c.in
+//   Template: src/f32-vrelu/wasmsimd.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_relu_ukernel__wasmsimd_x4(
+void xnn_f32_vrelu_ukernel__wasmsimd_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/gen/wasmsimd-x8.c b/src/f32-vrelu/gen/wasmsimd-x8.c
similarity index 94%
rename from src/f32-relu/gen/wasmsimd-x8.c
rename to src/f32-vrelu/gen/wasmsimd-x8.c
index 911de0a..1a733ab 100644
--- a/src/f32-relu/gen/wasmsimd-x8.c
+++ b/src/f32-vrelu/gen/wasmsimd-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-relu/wasmsimd.c.in
+//   Template: src/f32-vrelu/wasmsimd.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_relu_ukernel__wasmsimd_x8(
+void xnn_f32_vrelu_ukernel__wasmsimd_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/neon.c.in b/src/f32-vrelu/neon.c.in
similarity index 96%
rename from src/f32-relu/neon.c.in
rename to src/f32-vrelu/neon.c.in
index 1839085..4fe3812 100644
--- a/src/f32-relu/neon.c.in
+++ b/src/f32-vrelu/neon.c.in
@@ -14,7 +14,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_relu_ukernel__neon_x${BATCH_TILE}(
+void xnn_f32_vrelu_ukernel__neon_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/scalar.c.in b/src/f32-vrelu/scalar.c.in
similarity index 96%
rename from src/f32-relu/scalar.c.in
rename to src/f32-vrelu/scalar.c.in
index 0a247e9..8d7fd83 100644
--- a/src/f32-relu/scalar.c.in
+++ b/src/f32-vrelu/scalar.c.in
@@ -11,7 +11,7 @@
 #include <xnnpack/common.h>
 #include <xnnpack/math.h>
 
-void xnn_f32_relu_ukernel__scalar_x${BATCH_TILE}(
+void xnn_f32_vrelu_ukernel__scalar_x${BATCH_TILE}(
     size_t n,
     const float* x_ptr,
     float* y_ptr,
diff --git a/src/f32-relu/sse.c.in b/src/f32-vrelu/sse.c.in
similarity index 96%
rename from src/f32-relu/sse.c.in
rename to src/f32-vrelu/sse.c.in
index 42e1c88..6d616f1 100644
--- a/src/f32-relu/sse.c.in
+++ b/src/f32-vrelu/sse.c.in
@@ -14,7 +14,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_relu_ukernel__sse_x${BATCH_TILE}(
+void xnn_f32_vrelu_ukernel__sse_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/wasm.c.in b/src/f32-vrelu/wasm.c.in
similarity index 96%
rename from src/f32-relu/wasm.c.in
rename to src/f32-vrelu/wasm.c.in
index b9e10a5..68e8b22 100644
--- a/src/f32-relu/wasm.c.in
+++ b/src/f32-vrelu/wasm.c.in
@@ -12,7 +12,7 @@
 #include <xnnpack/math.h>
 
 
-void xnn_f32_relu_ukernel__wasm_x${BATCH_TILE}(
+void xnn_f32_vrelu_ukernel__wasm_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-relu/wasm_shr_x1.S b/src/f32-vrelu/wasm_shr_x1.S
similarity index 85%
rename from src/f32-relu/wasm_shr_x1.S
rename to src/f32-vrelu/wasm_shr_x1.S
index 57348aa..3c09ca6 100644
--- a/src/f32-relu/wasm_shr_x1.S
+++ b/src/f32-vrelu/wasm_shr_x1.S
@@ -5,7 +5,7 @@
 
 #include <xnnpack/assembly.h>
 
-# void xnn_f32_relu_ukernel__wasm32_shr_x1(
+# void xnn_f32_vrelu_ukernel__wasm32_shr_x1(
 #     size_t n,             0
 #     const float* x,       1
 #     float* y,             2
@@ -15,8 +15,8 @@
 #     float v               4
 #     float mask            5
 
-BEGIN_FUNCTION  xnn_f32_relu_ukernel__wasm32_shr_x1
-    .functype   xnn_f32_relu_ukernel__wasm32_shr_x1 (i32, i32, i32, i32) -> ()
+BEGIN_FUNCTION  xnn_f32_vrelu_ukernel__wasm32_shr_x1
+    .functype   xnn_f32_vrelu_ukernel__wasm32_shr_x1 (i32, i32, i32, i32) -> ()
     .local      i32, i32  # 4 - value, 5 - mask
 
     loop
@@ -63,4 +63,4 @@
       i32.gt_s
       br_if        0       # loop
     end_loop
-END_FUNCTION xnn_f32_relu_ukernel__wasm32_shr_x1
\ No newline at end of file
+END_FUNCTION xnn_f32_vrelu_ukernel__wasm32_shr_x1
\ No newline at end of file
diff --git a/src/f32-relu/wasm_shr_x2.S b/src/f32-vrelu/wasm_shr_x2.S
similarity index 91%
rename from src/f32-relu/wasm_shr_x2.S
rename to src/f32-vrelu/wasm_shr_x2.S
index 307c1f4..462bd26 100644
--- a/src/f32-relu/wasm_shr_x2.S
+++ b/src/f32-vrelu/wasm_shr_x2.S
@@ -5,7 +5,7 @@
 
 #include <xnnpack/assembly.h>
 
-# void xnn_f32_relu_ukernel__wasm32_shr_x2(
+# void xnn_f32_vrelu_ukernel__wasm32_shr_x2(
 #     size_t n,             0
 #     const float* x,       1
 #     float* y,             2
@@ -18,8 +18,8 @@
 #     float mask1           7
 
 
-BEGIN_FUNCTION  xnn_f32_relu_ukernel__wasm32_shr_x2
-    .functype   xnn_f32_relu_ukernel__wasm32_shr_x2 (i32, i32, i32, i32) -> ()
+BEGIN_FUNCTION  xnn_f32_vrelu_ukernel__wasm32_shr_x2
+    .functype   xnn_f32_vrelu_ukernel__wasm32_shr_x2 (i32, i32, i32, i32) -> ()
     .local      i32, i32, i32, i32
 
     local.get    0
@@ -117,4 +117,4 @@
       local.get    4
       i32.store    0        # store float
     end_if
-END_FUNCTION xnn_f32_relu_ukernel__wasm32_shr_x2
+END_FUNCTION xnn_f32_vrelu_ukernel__wasm32_shr_x2
diff --git a/src/f32-relu/wasm_shr_x4.S b/src/f32-vrelu/wasm_shr_x4.S
similarity index 94%
rename from src/f32-relu/wasm_shr_x4.S
rename to src/f32-vrelu/wasm_shr_x4.S
index cd16e57..4093e01 100644
--- a/src/f32-relu/wasm_shr_x4.S
+++ b/src/f32-vrelu/wasm_shr_x4.S
@@ -5,7 +5,7 @@
 
 #include <xnnpack/assembly.h>
 
-# void xnn_f32_relu_ukernel__wasm32_shr_x4(
+# void xnn_f32_vrelu_ukernel__wasm32_shr_x4(
 #     size_t n,             0
 #     const float* x,       1
 #     float* y,             2
@@ -21,8 +21,8 @@
 #     float mask2           10
 #     float mask3           11
 
-BEGIN_FUNCTION  xnn_f32_relu_ukernel__wasm32_shr_x4
-    .functype   xnn_f32_relu_ukernel__wasm32_shr_x4 (i32, i32, i32, i32) -> ()
+BEGIN_FUNCTION  xnn_f32_vrelu_ukernel__wasm32_shr_x4
+    .functype   xnn_f32_vrelu_ukernel__wasm32_shr_x4 (i32, i32, i32, i32) -> ()
     .local      i32, i32, i32, i32, i32, i32, i32, i32
 
     local.get    0
@@ -178,4 +178,4 @@
         br_if        0       # loop
       end_loop
     end_if
-END_FUNCTION xnn_f32_relu_ukernel__wasm32_shr_x4
+END_FUNCTION xnn_f32_vrelu_ukernel__wasm32_shr_x4
diff --git a/src/f32-relu/wasmsimd.c.in b/src/f32-vrelu/wasmsimd.c.in
similarity index 96%
rename from src/f32-relu/wasmsimd.c.in
rename to src/f32-vrelu/wasmsimd.c.in
index 6834b00..e59014e 100644
--- a/src/f32-relu/wasmsimd.c.in
+++ b/src/f32-vrelu/wasmsimd.c.in
@@ -14,7 +14,7 @@
 #include <xnnpack/common.h>
 
 
-void xnn_f32_relu_ukernel__wasmsimd_x${BATCH_TILE}(
+void xnn_f32_vrelu_ukernel__wasmsimd_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/avx-p5.c.in b/src/f32-vsigmoid/avx-p5.c.in
similarity index 98%
rename from src/f32-sigmoid/avx-p5.c.in
rename to src/f32-vsigmoid/avx-p5.c.in
index cd214e4..1daf871 100644
--- a/src/f32-sigmoid/avx-p5.c.in
+++ b/src/f32-vsigmoid/avx-p5.c.in
@@ -19,7 +19,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr${RR_STEPS}_p5_${DIV_ALGO}_x${BATCH_TILE}(
+void xnn_f32_vsigmoid_ukernel__avx_rr${RR_STEPS}_p5_${DIV_ALGO}_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/avx2-p5.c.in b/src/f32-vsigmoid/avx2-p5.c.in
similarity index 98%
rename from src/f32-sigmoid/avx2-p5.c.in
rename to src/f32-vsigmoid/avx2-p5.c.in
index cefab32..1f0e7d4 100644
--- a/src/f32-sigmoid/avx2-p5.c.in
+++ b/src/f32-vsigmoid/avx2-p5.c.in
@@ -19,7 +19,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr${RR_STEPS}_p5_${DIV_ALGO}_x${BATCH_TILE}(
+void xnn_f32_vsigmoid_ukernel__avx2_rr${RR_STEPS}_p5_${DIV_ALGO}_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in b/src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
similarity index 98%
rename from src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in
rename to src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
index ef16884..8439d5f 100644
--- a/src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in
+++ b/src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
@@ -18,7 +18,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr${RR_STEPS}_lut16_p3_perm_scalef_${DIV_ALGO}_x${BATCH_TILE}(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr${RR_STEPS}_lut16_p3_perm_scalef_${DIV_ALGO}_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in b/src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
similarity index 98%
rename from src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in
rename to src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
index 863af89..5879147 100644
--- a/src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in
+++ b/src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
@@ -18,7 +18,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr${RR_STEPS}_lut32_p2_perm2_scalef_${DIV_ALGO}_x${BATCH_TILE}(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr${RR_STEPS}_lut32_p2_perm2_scalef_${DIV_ALGO}_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/avx512f-p5-scalef.c.in b/src/f32-vsigmoid/avx512f-p5-scalef.c.in
similarity index 98%
rename from src/f32-sigmoid/avx512f-p5-scalef.c.in
rename to src/f32-vsigmoid/avx512f-p5-scalef.c.in
index aee4e4e..1cb740d 100644
--- a/src/f32-sigmoid/avx512f-p5-scalef.c.in
+++ b/src/f32-vsigmoid/avx512f-p5-scalef.c.in
@@ -18,7 +18,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr${RR_STEPS}_p5_scalef_${DIV_ALGO}_x${BATCH_TILE}(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr${RR_STEPS}_p5_scalef_${DIV_ALGO}_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-div-x16.c b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx-rr2-p5-div-x16.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-div-x16.c
index 9fe5a64..b97a8ad 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-div-x16.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x16(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-div-x24.c b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx-rr2-p5-div-x24.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-div-x24.c
index 3e103ec..fa89e92 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-div-x24.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x24(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-div-x32.c b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x32.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx-rr2-p5-div-x32.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-div-x32.c
index 59cfeb2..a9398ac 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-div-x32.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x32.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x32(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x32(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-div-x40.c b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x40.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx-rr2-p5-div-x40.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-div-x40.c
index 34ed9eb..aa35eaa 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-div-x40.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x40.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x40(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x40(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-div-x48.c b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x48.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx-rr2-p5-div-x48.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-div-x48.c
index 29cf94d..1128abe 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-div-x48.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x48.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x48(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x48(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-div-x56.c b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x56.c
similarity index 99%
rename from src/f32-sigmoid/gen/avx-rr2-p5-div-x56.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-div-x56.c
index 3708b3e..5d5036d 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-div-x56.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x56.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x56(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x56(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-div-x64.c b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x64.c
similarity index 99%
rename from src/f32-sigmoid/gen/avx-rr2-p5-div-x64.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-div-x64.c
index 787e743..f010dd4 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-div-x64.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x64.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x64(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x64(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-div-x72.c b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x72.c
similarity index 99%
rename from src/f32-sigmoid/gen/avx-rr2-p5-div-x72.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-div-x72.c
index fc4749e..98f60ad 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-div-x72.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x72.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x72(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x72(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-div-x8.c b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x8.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx-rr2-p5-div-x8.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-div-x8.c
index cc8b2b6..8a4954b 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-div-x8.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x8(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-div-x80.c b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x80.c
similarity index 99%
rename from src/f32-sigmoid/gen/avx-rr2-p5-div-x80.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-div-x80.c
index bc9f87e..1bbb25d 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-div-x80.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-div-x80.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x80(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x80(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x16.c b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx-rr2-p5-nr2-x16.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x16.c
index 0a68c4c..2cc9b6c 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x16.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x16(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x24.c b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx-rr2-p5-nr2-x24.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x24.c
index 3befedd..4aff9e3 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x24.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x24(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x32.c b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x32.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx-rr2-p5-nr2-x32.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x32.c
index f3f8aab..76e92bd 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x32.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x32.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x32(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x32(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x40.c b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x40.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx-rr2-p5-nr2-x40.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x40.c
index 690df21..2b61a00 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x40.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x40.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x40(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x40(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x48.c b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x48.c
similarity index 99%
rename from src/f32-sigmoid/gen/avx-rr2-p5-nr2-x48.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x48.c
index 1b0e8f8..38c2488 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x48.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x48.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x48(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x48(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x56.c b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x56.c
similarity index 99%
rename from src/f32-sigmoid/gen/avx-rr2-p5-nr2-x56.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x56.c
index 0098f3c..f7c7f6a 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x56.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x56.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x56(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x56(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x64.c b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x64.c
similarity index 99%
rename from src/f32-sigmoid/gen/avx-rr2-p5-nr2-x64.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x64.c
index eebda7d..f4e12d2 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x64.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x64.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x64(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x64(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x72.c b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x72.c
similarity index 99%
rename from src/f32-sigmoid/gen/avx-rr2-p5-nr2-x72.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x72.c
index 8d19388..e06166b 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x72.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x72.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x72(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x72(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x8.c b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x8.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx-rr2-p5-nr2-x8.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x8.c
index 88cdafc..b95b77b 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x8.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x8(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x80.c b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x80.c
similarity index 99%
rename from src/f32-sigmoid/gen/avx-rr2-p5-nr2-x80.c
rename to src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x80.c
index 5f0121e..f883d6a 100644
--- a/src/f32-sigmoid/gen/avx-rr2-p5-nr2-x80.c
+++ b/src/f32-vsigmoid/gen/avx-rr2-p5-nr2-x80.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx-p5.c.in
+//   Template: src/f32-vsigmoid/avx-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x80(
+void xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x80(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x16.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x16.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-div-x16.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-div-x16.c
index 52287a8..19c9d9e 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x16.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x16(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x24.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-div-x24.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-div-x24.c
index cbb5eba..5af9e9a 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x24.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x24(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x32.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x32.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-div-x32.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-div-x32.c
index 572f554..ed8b949 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x32.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x32.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x32(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x32(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x40.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x40.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-div-x40.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-div-x40.c
index dae8ae5..e80bbe9 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x40.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x40.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x40(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x40(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x48.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x48.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-div-x48.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-div-x48.c
index d6df1bc..e2d860e 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x48.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x48.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x48(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x48(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x56.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x56.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-div-x56.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-div-x56.c
index 7c36b17..e0453eb 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x56.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x56.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x56(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x56(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x64.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x64.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-div-x64.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-div-x64.c
index c01b78c..0339c6f 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x64.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x64.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x64(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x64(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x72.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x72.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-div-x72.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-div-x72.c
index d2ef43e..bdb25c1 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x72.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x72.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x72(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x72(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x8.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x8.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-div-x8.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-div-x8.c
index 76ab68f..4c27d32 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x8.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x8(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x80.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x80.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-div-x80.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-div-x80.c
index c934ab9..4b1b154 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-div-x80.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-div-x80.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x80(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x80(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x16.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x16.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x16.c
index 2202cad..e72833e 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x16.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x16(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x24.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x24.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x24.c
index 07fcda9..f20230b 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x24.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x24(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x32.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x32.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x32.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x32.c
index 9449d0e..68398a4 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x32.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x32.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x32(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x32(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x40.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x40.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x40.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x40.c
index 365622c..4b9c70b 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x40.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x40.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x40(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x40(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x48.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x48.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x48.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x48.c
index 6fa18a8..c13cbeb 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x48.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x48.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x48(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x48(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x56.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x56.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x56.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x56.c
index b29465c..a019654 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x56.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x56.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x56(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x56(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x64.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x64.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x64.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x64.c
index 59ca184..4fd5ce0 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x64.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x64.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x64(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x64(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x72.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x72.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x72.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x72.c
index 3a09a42..cbaf256 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x72.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x72.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x72(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x72(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x8.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x8.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x8.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x8.c
index 09beb82..4fb1ec7 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x8.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x8(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x80.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x80.c
similarity index 99%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x80.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x80.c
index 6ea62aa..a4c6975 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr1fma-x80.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr1fma-x80.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x80(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x80(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x16.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x16.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x16.c
index d141fe1..86f0b61 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x16.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x16(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x24.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x24.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x24.c
index 7756395..7443c0f 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x24.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x24(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x32.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x32.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x32.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x32.c
index 7b970da..4c785e8 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x32.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x32.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x32(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x32(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x40.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x40.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x40.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x40.c
index 42bbd71..6ed6f77 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x40.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x40.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x40(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x40(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x48.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x48.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x48.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x48.c
index f78064d..6eba645 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x48.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x48.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x48(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x48(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x56.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x56.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x56.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x56.c
index 10245a5..b33284c 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x56.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x56.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x56(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x56(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x64.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x64.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x64.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x64.c
index 9acdd13..624b590 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x64.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x64.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x64(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x64(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x72.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x72.c
similarity index 99%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x72.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x72.c
index 43ec8d5..976b2c6 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x72.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x72.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x72(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x72(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x8.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x8.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x8.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x8.c
index 53bfe60..ba3eb42 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x8.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x8(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x80.c b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x80.c
similarity index 99%
rename from src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x80.c
rename to src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x80.c
index 1abc569..58fa463 100644
--- a/src/f32-sigmoid/gen/avx2-rr1-p5-nr2fma-x80.c
+++ b/src/f32-vsigmoid/gen/avx2-rr1-p5-nr2fma-x80.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx2-p5.c.in
+//   Template: src/f32-vsigmoid/avx2-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 static const int32_t mask_table[14] = {-1, -1, -1, -1, -1, -1, -1, 0, 0, 0, 0, 0, 0, 0};
 
-void xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x80(
+void xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x80(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x112.c b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x112.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x112.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x112.c
index f9cda94..bb4b2c0 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x112.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x112.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x112(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x112(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x128.c b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x128.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x128.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x128.c
index c62892f..94deece 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x128.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x128.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x128(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x128(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x16.c b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x16.c
similarity index 95%
rename from src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x16.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x16.c
index a23d2cd..04e37e3 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x16.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x16(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x32.c b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x32.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x32.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x32.c
index 1d5a33f..33c9065 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x32.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x32.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x32(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x32(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x48.c b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x48.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x48.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x48.c
index bc73931..d024491 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x48.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x48.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x48(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x48(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x64.c b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x64.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x64.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x64.c
index dc83403..fd49fd4 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x64.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x64.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x64(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x64(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x80.c b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x80.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x80.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x80.c
index fcb8d4a..80dbde0 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x80.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x80.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x80(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x80(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x96.c b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x96.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x96.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x96.c
index 4ed1be2..a96baa0 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x96.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-div-x96.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x96(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x96(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x112.c b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x112.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x112.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x112.c
index f814c8a..41e64c4 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x112.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x112.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x112(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x112(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x128.c b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x128.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x128.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x128.c
index caeb669..c2cc940 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x128.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x128.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x128(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x128(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x16.c b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x16.c
similarity index 95%
rename from src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x16.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x16.c
index 49f147c..26a81b8 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x16.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x16(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x32.c b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x32.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x32.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x32.c
index 657e1ee..081e271 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x32.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x32.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x32(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x32(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x48.c b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x48.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x48.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x48.c
index eed8df3..c7d86d9 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x48.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x48.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x48(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x48(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x64.c b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x64.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x64.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x64.c
index a4866cb..c665cd1 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x64.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x64.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x64(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x64(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x80.c b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x80.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x80.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x80.c
index 76626fe..9e9fa8d 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x80.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x80.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x80(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x80(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x96.c b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x96.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x96.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x96.c
index e5a0fdb..9b8ccc8 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x96.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-lut16-p3-perm-scalef-nr1fma-x96.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut16-p3-perm-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut16-p3-perm-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x96(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x96(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x112.c b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x112.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x112.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x112.c
index 6151067..75d98b8 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x112.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x112.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-p5-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-p5-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_div_x112(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_div_x112(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x128.c b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x128.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x128.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x128.c
index 911684b..f49d3f9 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x128.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x128.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-p5-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-p5-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_div_x128(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_div_x128(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x16.c b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x16.c
similarity index 95%
rename from src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x16.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x16.c
index f6c3ef5..6b007b9 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x16.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-p5-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-p5-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_div_x16(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_div_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x32.c b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x32.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x32.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x32.c
index 17ed567..a40e8d6 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x32.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x32.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-p5-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-p5-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_div_x32(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_div_x32(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x48.c b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x48.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x48.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x48.c
index 3ec9553..8eb3df0 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x48.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x48.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-p5-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-p5-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_div_x48(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_div_x48(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x64.c b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x64.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x64.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x64.c
index 4ca356b..f6dcaab 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x64.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x64.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-p5-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-p5-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_div_x64(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_div_x64(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x80.c b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x80.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x80.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x80.c
index 0c5bbb3..397fb74 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x80.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x80.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-p5-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-p5-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_div_x80(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_div_x80(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x96.c b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x96.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x96.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x96.c
index 20c7faf..20fb0f3 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-div-x96.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-div-x96.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-p5-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-p5-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_div_x96(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_div_x96(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x112.c b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x112.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x112.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x112.c
index c3e854f..0b41fbd 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x112.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x112.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-p5-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-p5-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x112(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x112(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x128.c b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x128.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x128.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x128.c
index 0a6afa7..5ba204c 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x128.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x128.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-p5-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-p5-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x128(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x128(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x16.c b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x16.c
similarity index 96%
rename from src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x16.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x16.c
index a6e2e24..4605aea 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x16.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-p5-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-p5-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x16(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x32.c b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x32.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x32.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x32.c
index 7e0758a..ca825ef 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x32.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x32.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-p5-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-p5-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x32(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x32(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x48.c b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x48.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x48.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x48.c
index ae8e23b..31f0023 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x48.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x48.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-p5-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-p5-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x48(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x48(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x64.c b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x64.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x64.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x64.c
index ef24507..cfe1984 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x64.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x64.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-p5-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-p5-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x64(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x64(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x80.c b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x80.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x80.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x80.c
index 30cd9e9..1bc7b98 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x80.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x80.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-p5-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-p5-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x80(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x80(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x96.c b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x96.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x96.c
rename to src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x96.c
index 3a68123..3e03700 100644
--- a/src/f32-sigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x96.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr1-p5-scalef-nr1fma-x96.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-p5-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-p5-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x96(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x96(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x112.c b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x112.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x112.c
rename to src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x112.c
index 2b42eb7..f66b675 100644
--- a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x112.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x112.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x112(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x112(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x128.c b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x128.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x128.c
rename to src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x128.c
index b44b21c..67fa386 100644
--- a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x128.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x128.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x128(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x128(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x16.c b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x16.c
similarity index 96%
rename from src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x16.c
rename to src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x16.c
index 293ca17..80661f3 100644
--- a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x16.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x16(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x32.c b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x32.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x32.c
rename to src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x32.c
index ac7adb3..eef3dbf 100644
--- a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x32.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x32.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x32(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x32(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x48.c b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x48.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x48.c
rename to src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x48.c
index 829c28f..0cc852f 100644
--- a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x48.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x48.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x48(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x48(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x64.c b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x64.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x64.c
rename to src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x64.c
index 9b67898..bb3d85c 100644
--- a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x64.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x64.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x64(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x64(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x80.c b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x80.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x80.c
rename to src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x80.c
index 4a6f630..b8fecfb 100644
--- a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x80.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x80.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x80(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x80(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x96.c b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x96.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x96.c
rename to src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x96.c
index 1e774e6..0d897e9 100644
--- a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x96.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-div-x96.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x96(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x96(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x112.c b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x112.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x112.c
rename to src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x112.c
index 1c625e6..e60588a 100644
--- a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x112.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x112.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x112(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x112(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x128.c b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x128.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x128.c
rename to src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x128.c
index 04dcfda..36ce3e3 100644
--- a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x128.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x128.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x128(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x128(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x16.c b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x16.c
similarity index 96%
rename from src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x16.c
rename to src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x16.c
index d585746..475dcb2 100644
--- a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x16.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x16(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x32.c b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x32.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x32.c
rename to src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x32.c
index 571732d..da38386 100644
--- a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x32.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x32.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x32(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x32(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x48.c b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x48.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x48.c
rename to src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x48.c
index 21e9029..fc9ff2d 100644
--- a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x48.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x48.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x48(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x48(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x64.c b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x64.c
similarity index 97%
rename from src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x64.c
rename to src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x64.c
index 2328cad..85a3702 100644
--- a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x64.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x64.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x64(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x64(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x80.c b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x80.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x80.c
rename to src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x80.c
index d7db6e2..a43611f 100644
--- a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x80.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x80.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x80(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x80(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x96.c b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x96.c
similarity index 98%
rename from src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x96.c
rename to src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x96.c
index 08b9367..559757c 100644
--- a/src/f32-sigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x96.c
+++ b/src/f32-vsigmoid/gen/avx512f-rr2-lut32-p2-perm2-scalef-nr1fma-x96.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/avx512f-lut32-p2-perm2-scalef.c.in
+//   Template: src/f32-vsigmoid/avx512f-lut32-p2-perm2-scalef.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -16,7 +16,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x96(
+void xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x96(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x12.c b/src/f32-vsigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x12.c
rename to src/f32-vsigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x12.c
index 75ccd47..07cd8d1 100644
--- a/src/f32-sigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x12.c
+++ b/src/f32-vsigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x12(
+void xnn_f32_vsigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x16.c b/src/f32-vsigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x16.c
rename to src/f32-vsigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x16.c
index 2feed48..c7b03ce 100644
--- a/src/f32-sigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x16.c
+++ b/src/f32-vsigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x16(
+void xnn_f32_vsigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x20.c b/src/f32-vsigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x20.c
rename to src/f32-vsigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x20.c
index daf7647..91851dd 100644
--- a/src/f32-sigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x20.c
+++ b/src/f32-vsigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x20(
+void xnn_f32_vsigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x24.c b/src/f32-vsigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x24.c
rename to src/f32-vsigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x24.c
index c3ff2c6..e3c865c 100644
--- a/src/f32-sigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x24.c
+++ b/src/f32-vsigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x24(
+void xnn_f32_vsigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x4.c b/src/f32-vsigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x4.c
similarity index 97%
rename from src/f32-sigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x4.c
rename to src/f32-vsigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x4.c
index a612834..e7e58dc 100644
--- a/src/f32-sigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x4.c
+++ b/src/f32-vsigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x4(
+void xnn_f32_vsigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x8.c b/src/f32-vsigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x8.c
similarity index 98%
rename from src/f32-sigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x8.c
rename to src/f32-vsigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x8.c
index 39921d0..c1b6baa 100644
--- a/src/f32-sigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x8.c
+++ b/src/f32-vsigmoid/gen/neon-rr2-lut2048-p1-nr2recps-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x8(
+void xnn_f32_vsigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neon-rr2-lut64-p2-nr2recps-x12.c b/src/f32-vsigmoid/gen/neon-rr2-lut64-p2-nr2recps-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/neon-rr2-lut64-p2-nr2recps-x12.c
rename to src/f32-vsigmoid/gen/neon-rr2-lut64-p2-nr2recps-x12.c
index c4e8a61..9138938 100644
--- a/src/f32-sigmoid/gen/neon-rr2-lut64-p2-nr2recps-x12.c
+++ b/src/f32-vsigmoid/gen/neon-rr2-lut64-p2-nr2recps-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x12(
+void xnn_f32_vsigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neon-rr2-lut64-p2-nr2recps-x16.c b/src/f32-vsigmoid/gen/neon-rr2-lut64-p2-nr2recps-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/neon-rr2-lut64-p2-nr2recps-x16.c
rename to src/f32-vsigmoid/gen/neon-rr2-lut64-p2-nr2recps-x16.c
index 759748a..a5bd7c4 100644
--- a/src/f32-sigmoid/gen/neon-rr2-lut64-p2-nr2recps-x16.c
+++ b/src/f32-vsigmoid/gen/neon-rr2-lut64-p2-nr2recps-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x16(
+void xnn_f32_vsigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neon-rr2-lut64-p2-nr2recps-x20.c b/src/f32-vsigmoid/gen/neon-rr2-lut64-p2-nr2recps-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/neon-rr2-lut64-p2-nr2recps-x20.c
rename to src/f32-vsigmoid/gen/neon-rr2-lut64-p2-nr2recps-x20.c
index e84df01..356d494 100644
--- a/src/f32-sigmoid/gen/neon-rr2-lut64-p2-nr2recps-x20.c
+++ b/src/f32-vsigmoid/gen/neon-rr2-lut64-p2-nr2recps-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x20(
+void xnn_f32_vsigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neon-rr2-lut64-p2-nr2recps-x24.c b/src/f32-vsigmoid/gen/neon-rr2-lut64-p2-nr2recps-x24.c
similarity index 99%
rename from src/f32-sigmoid/gen/neon-rr2-lut64-p2-nr2recps-x24.c
rename to src/f32-vsigmoid/gen/neon-rr2-lut64-p2-nr2recps-x24.c
index 99a5708..a396b79 100644
--- a/src/f32-sigmoid/gen/neon-rr2-lut64-p2-nr2recps-x24.c
+++ b/src/f32-vsigmoid/gen/neon-rr2-lut64-p2-nr2recps-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x24(
+void xnn_f32_vsigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neon-rr2-lut64-p2-nr2recps-x4.c b/src/f32-vsigmoid/gen/neon-rr2-lut64-p2-nr2recps-x4.c
similarity index 97%
rename from src/f32-sigmoid/gen/neon-rr2-lut64-p2-nr2recps-x4.c
rename to src/f32-vsigmoid/gen/neon-rr2-lut64-p2-nr2recps-x4.c
index 30f4b5d..35e62c3 100644
--- a/src/f32-sigmoid/gen/neon-rr2-lut64-p2-nr2recps-x4.c
+++ b/src/f32-vsigmoid/gen/neon-rr2-lut64-p2-nr2recps-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x4(
+void xnn_f32_vsigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neon-rr2-lut64-p2-nr2recps-x8.c b/src/f32-vsigmoid/gen/neon-rr2-lut64-p2-nr2recps-x8.c
similarity index 98%
rename from src/f32-sigmoid/gen/neon-rr2-lut64-p2-nr2recps-x8.c
rename to src/f32-vsigmoid/gen/neon-rr2-lut64-p2-nr2recps-x8.c
index 50bda3e..ac79aa8 100644
--- a/src/f32-sigmoid/gen/neon-rr2-lut64-p2-nr2recps-x8.c
+++ b/src/f32-vsigmoid/gen/neon-rr2-lut64-p2-nr2recps-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x8(
+void xnn_f32_vsigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neon-rr2-p5-nr2recps-x12.c b/src/f32-vsigmoid/gen/neon-rr2-p5-nr2recps-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/neon-rr2-p5-nr2recps-x12.c
rename to src/f32-vsigmoid/gen/neon-rr2-p5-nr2recps-x12.c
index 2392d91..bf2a506 100644
--- a/src/f32-sigmoid/gen/neon-rr2-p5-nr2recps-x12.c
+++ b/src/f32-vsigmoid/gen/neon-rr2-p5-nr2recps-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neon_rr2_p5_nr2recps_x12(
+void xnn_f32_vsigmoid_ukernel__neon_rr2_p5_nr2recps_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neon-rr2-p5-nr2recps-x16.c b/src/f32-vsigmoid/gen/neon-rr2-p5-nr2recps-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/neon-rr2-p5-nr2recps-x16.c
rename to src/f32-vsigmoid/gen/neon-rr2-p5-nr2recps-x16.c
index 2c5a242..d7fbf76 100644
--- a/src/f32-sigmoid/gen/neon-rr2-p5-nr2recps-x16.c
+++ b/src/f32-vsigmoid/gen/neon-rr2-p5-nr2recps-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neon_rr2_p5_nr2recps_x16(
+void xnn_f32_vsigmoid_ukernel__neon_rr2_p5_nr2recps_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neon-rr2-p5-nr2recps-x20.c b/src/f32-vsigmoid/gen/neon-rr2-p5-nr2recps-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/neon-rr2-p5-nr2recps-x20.c
rename to src/f32-vsigmoid/gen/neon-rr2-p5-nr2recps-x20.c
index b180839..1ac696d 100644
--- a/src/f32-sigmoid/gen/neon-rr2-p5-nr2recps-x20.c
+++ b/src/f32-vsigmoid/gen/neon-rr2-p5-nr2recps-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neon_rr2_p5_nr2recps_x20(
+void xnn_f32_vsigmoid_ukernel__neon_rr2_p5_nr2recps_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neon-rr2-p5-nr2recps-x24.c b/src/f32-vsigmoid/gen/neon-rr2-p5-nr2recps-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/neon-rr2-p5-nr2recps-x24.c
rename to src/f32-vsigmoid/gen/neon-rr2-p5-nr2recps-x24.c
index db5cd17..1fc82e2 100644
--- a/src/f32-sigmoid/gen/neon-rr2-p5-nr2recps-x24.c
+++ b/src/f32-vsigmoid/gen/neon-rr2-p5-nr2recps-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neon_rr2_p5_nr2recps_x24(
+void xnn_f32_vsigmoid_ukernel__neon_rr2_p5_nr2recps_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neon-rr2-p5-nr2recps-x4.c b/src/f32-vsigmoid/gen/neon-rr2-p5-nr2recps-x4.c
similarity index 96%
rename from src/f32-sigmoid/gen/neon-rr2-p5-nr2recps-x4.c
rename to src/f32-vsigmoid/gen/neon-rr2-p5-nr2recps-x4.c
index c02d734..5083dc1 100644
--- a/src/f32-sigmoid/gen/neon-rr2-p5-nr2recps-x4.c
+++ b/src/f32-vsigmoid/gen/neon-rr2-p5-nr2recps-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neon_rr2_p5_nr2recps_x4(
+void xnn_f32_vsigmoid_ukernel__neon_rr2_p5_nr2recps_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neon-rr2-p5-nr2recps-x8.c b/src/f32-vsigmoid/gen/neon-rr2-p5-nr2recps-x8.c
similarity index 98%
rename from src/f32-sigmoid/gen/neon-rr2-p5-nr2recps-x8.c
rename to src/f32-vsigmoid/gen/neon-rr2-p5-nr2recps-x8.c
index 58380f3..f464888 100644
--- a/src/f32-sigmoid/gen/neon-rr2-p5-nr2recps-x8.c
+++ b/src/f32-vsigmoid/gen/neon-rr2-p5-nr2recps-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neon_rr2_p5_nr2recps_x8(
+void xnn_f32_vsigmoid_ukernel__neon_rr2_p5_nr2recps_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-div-x12.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-div-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-div-x12.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-div-x12.c
index c256be1..2cc5083 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-div-x12.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-div-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x12(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-div-x16.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-div-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-div-x16.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-div-x16.c
index 67aeabf..89d0155 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-div-x16.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-div-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x16(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-div-x20.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-div-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-div-x20.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-div-x20.c
index 0177768..ca1a5b2 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-div-x20.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-div-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x20(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-div-x24.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-div-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-div-x24.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-div-x24.c
index 678d34c..42b3efd 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-div-x24.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-div-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x24(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-div-x4.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-div-x4.c
similarity index 97%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-div-x4.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-div-x4.c
index 6587ae1..41fcb77 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-div-x4.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-div-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x4(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-div-x8.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-div-x8.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-div-x8.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-div-x8.c
index f726535..3c53640 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-div-x8.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-div-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x8(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x12.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x12.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x12.c
index 0146342..a6c4b80 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x12.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x12(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x16.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x16.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x16.c
index a2ca1a5..1d3f05d 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x16.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x16(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x20.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x20.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x20.c
index cb56435..e8a4bea 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x20.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x20(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x24.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x24.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x24.c
index 1c79d2d..56795f2 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x24.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x24(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x4.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x4.c
similarity index 97%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x4.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x4.c
index c468999..10005c0 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x4.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x4(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x8.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x8.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x8.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x8.c
index 520ffec..e134e02 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x8.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr1recps1fma-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x8(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x12.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x12.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x12.c
index b468b77..aaf5840 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x12.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x12(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x16.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x16.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x16.c
index 8be742a..a709352 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x16.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x16(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x20.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x20.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x20.c
index 459d224..8dbaef0 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x20.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x20(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x24.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x24.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x24.c
index debe975..d8d32b0 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x24.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x24(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x4.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x4.c
similarity index 97%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x4.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x4.c
index 0f9a687..0f554ca 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x4.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x4(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x8.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x8.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x8.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x8.c
index 850f9c1..e5e74e1 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x8.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2fma-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x8(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x12.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x12.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x12.c
index 9f90592..86eed58 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x12.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x12(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x16.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x16.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x16.c
index 977bfe7..ed047c0 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x16.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x16(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x20.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x20.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x20.c
index 32484e7..b3c63c1 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x20.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x20(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x24.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x24.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x24.c
index f2f81b9..33c3636 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x24.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x24(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x4.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x4.c
similarity index 97%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x4.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x4.c
index 0c94aa3..c5b4b34 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x4.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x4(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x8.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x8.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x8.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x8.c
index 676b94c..feab875 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x8.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut2048-p1-nr2recps-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut2048-p1.c.in
+//   Template: src/f32-vsigmoid/neon-lut2048-p1.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x8(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-div-x12.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-div-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-div-x12.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-div-x12.c
index b5133fc..b4299d3 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-div-x12.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-div-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_div_x12(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_div_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-div-x16.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-div-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-div-x16.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-div-x16.c
index 2855b96..c922aee 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-div-x16.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-div-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_div_x16(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_div_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-div-x20.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-div-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-div-x20.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-div-x20.c
index b3b69cb..00f4605 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-div-x20.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-div-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_div_x20(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_div_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-div-x24.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-div-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-div-x24.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-div-x24.c
index 0d29d99..15912ca 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-div-x24.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-div-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_div_x24(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_div_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-div-x4.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-div-x4.c
similarity index 97%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-div-x4.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-div-x4.c
index e2ba5d6..3716a24 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-div-x4.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-div-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_div_x4(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_div_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-div-x8.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-div-x8.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-div-x8.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-div-x8.c
index 4be3444..c1ecd06 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-div-x8.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-div-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_div_x8(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_div_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x12.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x12.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x12.c
index 76d1793..6e24147 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x12.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x12(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x16.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x16.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x16.c
index dadab58..64757c6 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x16.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x16(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x20.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x20.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x20.c
index 0b56f4a..d6b8119 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x20.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x20(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x24.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x24.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x24.c
index df0ef41..16d4de8 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x24.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x24(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x4.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x4.c
similarity index 97%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x4.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x4.c
index b5094b3..7cba965 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x4.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x4(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x8.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x8.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x8.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x8.c
index f7892fc..0add020 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x8.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr1recps1fma-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x8(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x12.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x12.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x12.c
index 9bf1eee..af40419 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x12.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x12(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x16.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x16.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x16.c
index 706fe4d..4df0ffb 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x16.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x16(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x20.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x20.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x20.c
index 5401467..fcf9362 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x20.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x20(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x24.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x24.c
similarity index 99%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x24.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x24.c
index 537b361..d6f96c3 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x24.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x24(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x4.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x4.c
similarity index 97%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x4.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x4.c
index 30f2c8e..f4308b8 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x4.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x4(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x8.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x8.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x8.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x8.c
index b39788a..54b2f68 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x8.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2fma-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x8(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x12.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x12.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x12.c
index bb8dbd1..58ba076 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x12.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x12(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x16.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x16.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x16.c
index c32b2eb..635fac1 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x16.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x16(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x20.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x20.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x20.c
index 90a6dcf..20f966c 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x20.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x20(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x24.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x24.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x24.c
index 8555fb0..09a8fff 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x24.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x24(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x4.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x4.c
similarity index 97%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x4.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x4.c
index ca1b7a4..8720e17 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x4.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x4(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x8.c b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x8.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x8.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x8.c
index 73122e9..ca1fda5 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x8.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-lut64-p2-nr2recps-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-lut64-p2.c.in
+//   Template: src/f32-vsigmoid/neon-lut64-p2.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x8(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-div-x12.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-div-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-div-x12.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-div-x12.c
index 32ef290..453d663 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-div-x12.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-div-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_div_x12(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_div_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-div-x16.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-div-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-div-x16.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-div-x16.c
index 8658e4a..8d32e45 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-div-x16.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-div-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_div_x16(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_div_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-div-x20.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-div-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-div-x20.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-div-x20.c
index c379e71..b972c83 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-div-x20.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-div-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_div_x20(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_div_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-div-x24.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-div-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-div-x24.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-div-x24.c
index fa6e699..95c04c6 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-div-x24.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-div-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_div_x24(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_div_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-div-x4.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-div-x4.c
similarity index 96%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-div-x4.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-div-x4.c
index c196e41..9ca641c 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-div-x4.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-div-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_div_x4(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_div_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-div-x8.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-div-x8.c
similarity index 97%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-div-x8.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-div-x8.c
index 47f8612..51b7cb7 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-div-x8.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-div-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_div_x8(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_div_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x12.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x12.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x12.c
index e8923c3..3563bb7 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x12.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x12(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x16.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x16.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x16.c
index ea055ef..140e855 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x16.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x16(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x20.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x20.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x20.c
index 1012bb3..a201263 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x20.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x20(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x24.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x24.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x24.c
index ca5b02c..1001fbc 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x24.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x24(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x4.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x4.c
similarity index 96%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x4.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x4.c
index 9ae18f3..e09c5d7 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x4.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x4(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x8.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x8.c
similarity index 97%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x8.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x8.c
index 2fbcbae..2dc9e44 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x8.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr1recps1fma-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x8(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2fma-x12.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2fma-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-nr2fma-x12.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2fma-x12.c
index 34899ca..2eb7804 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2fma-x12.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2fma-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2fma_x12(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2fma_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2fma-x16.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2fma-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-nr2fma-x16.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2fma-x16.c
index 8557aa2..30aa3da 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2fma-x16.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2fma-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2fma_x16(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2fma_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2fma-x20.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2fma-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-nr2fma-x20.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2fma-x20.c
index 5e397f2..0ab75d9 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2fma-x20.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2fma-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2fma_x20(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2fma_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2fma-x24.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2fma-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-nr2fma-x24.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2fma-x24.c
index fdd6657..438e9f3 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2fma-x24.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2fma-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2fma_x24(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2fma_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2fma-x4.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2fma-x4.c
similarity index 96%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-nr2fma-x4.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2fma-x4.c
index 3d47995..f9c6741 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2fma-x4.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2fma-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2fma_x4(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2fma_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2fma-x8.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2fma-x8.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-nr2fma-x8.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2fma-x8.c
index 66721c2..8ffee74 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2fma-x8.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2fma-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2fma_x8(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2fma_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2recps-x12.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2recps-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-nr2recps-x12.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2recps-x12.c
index ca76976..345e5d0 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2recps-x12.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2recps-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2recps_x12(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2recps_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2recps-x16.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2recps-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-nr2recps-x16.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2recps-x16.c
index c2dbf5b..33ee118 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2recps-x16.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2recps-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2recps_x16(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2recps_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2recps-x20.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2recps-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-nr2recps-x20.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2recps-x20.c
index f2e55cd..4a240d6 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2recps-x20.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2recps-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2recps_x20(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2recps_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2recps-x24.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2recps-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-nr2recps-x24.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2recps-x24.c
index 3fdeb5e..6a36dc9 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2recps-x24.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2recps-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2recps_x24(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2recps_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2recps-x4.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2recps-x4.c
similarity index 96%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-nr2recps-x4.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2recps-x4.c
index e0af562..a2c308c 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2recps-x4.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2recps-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2recps_x4(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2recps_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2recps-x8.c b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2recps-x8.c
similarity index 98%
rename from src/f32-sigmoid/gen/neonfma-rr1-p5-nr2recps-x8.c
rename to src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2recps-x8.c
index 123f011..ec9204e 100644
--- a/src/f32-sigmoid/gen/neonfma-rr1-p5-nr2recps-x8.c
+++ b/src/f32-vsigmoid/gen/neonfma-rr1-p5-nr2recps-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/neon-p5.c.in
+//   Template: src/f32-vsigmoid/neon-p5.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2recps_x8(
+void xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2recps_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/scalar-lut2048-p1-div-x1.c b/src/f32-vsigmoid/gen/scalar-lut2048-p1-div-x1.c
similarity index 93%
rename from src/f32-sigmoid/gen/scalar-lut2048-p1-div-x1.c
rename to src/f32-vsigmoid/gen/scalar-lut2048-p1-div-x1.c
index 84c3a7b..7de27f9 100644
--- a/src/f32-sigmoid/gen/scalar-lut2048-p1-div-x1.c
+++ b/src/f32-vsigmoid/gen/scalar-lut2048-p1-div-x1.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/scalar-lut2048-p1-div.c.in
+//   Template: src/f32-vsigmoid/scalar-lut2048-p1-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -19,7 +19,7 @@
 // Note redefine as uint32[] to avoid redundant bitcasts.
 extern XNN_INTERNAL const uint32_t xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__scalar_lut2048_p1_div_x1(
+void xnn_f32_vsigmoid_ukernel__scalar_lut2048_p1_div_x1(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/scalar-lut2048-p1-div-x2.c b/src/f32-vsigmoid/gen/scalar-lut2048-p1-div-x2.c
similarity index 96%
rename from src/f32-sigmoid/gen/scalar-lut2048-p1-div-x2.c
rename to src/f32-vsigmoid/gen/scalar-lut2048-p1-div-x2.c
index b78195a..9232515 100644
--- a/src/f32-sigmoid/gen/scalar-lut2048-p1-div-x2.c
+++ b/src/f32-vsigmoid/gen/scalar-lut2048-p1-div-x2.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/scalar-lut2048-p1-div.c.in
+//   Template: src/f32-vsigmoid/scalar-lut2048-p1-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -19,7 +19,7 @@
 // Note redefine as uint32[] to avoid redundant bitcasts.
 extern XNN_INTERNAL const uint32_t xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__scalar_lut2048_p1_div_x2(
+void xnn_f32_vsigmoid_ukernel__scalar_lut2048_p1_div_x2(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/scalar-lut2048-p1-div-x4.c b/src/f32-vsigmoid/gen/scalar-lut2048-p1-div-x4.c
similarity index 97%
rename from src/f32-sigmoid/gen/scalar-lut2048-p1-div-x4.c
rename to src/f32-vsigmoid/gen/scalar-lut2048-p1-div-x4.c
index 249d1c0..ded50ff 100644
--- a/src/f32-sigmoid/gen/scalar-lut2048-p1-div-x4.c
+++ b/src/f32-vsigmoid/gen/scalar-lut2048-p1-div-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/scalar-lut2048-p1-div.c.in
+//   Template: src/f32-vsigmoid/scalar-lut2048-p1-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -19,7 +19,7 @@
 // Note redefine as uint32[] to avoid redundant bitcasts.
 extern XNN_INTERNAL const uint32_t xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__scalar_lut2048_p1_div_x4(
+void xnn_f32_vsigmoid_ukernel__scalar_lut2048_p1_div_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/scalar-lut64-p2-div-x1.c b/src/f32-vsigmoid/gen/scalar-lut64-p2-div-x1.c
similarity index 93%
rename from src/f32-sigmoid/gen/scalar-lut64-p2-div-x1.c
rename to src/f32-vsigmoid/gen/scalar-lut64-p2-div-x1.c
index cb4a559..b29a87e 100644
--- a/src/f32-sigmoid/gen/scalar-lut64-p2-div-x1.c
+++ b/src/f32-vsigmoid/gen/scalar-lut64-p2-div-x1.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/scalar-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/scalar-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -19,7 +19,7 @@
 // Note redefine as uint32[] to avoid redundant bitcasts.
 extern XNN_INTERNAL const uint32_t xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__scalar_lut64_p2_div_x1(
+void xnn_f32_vsigmoid_ukernel__scalar_lut64_p2_div_x1(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/scalar-lut64-p2-div-x2.c b/src/f32-vsigmoid/gen/scalar-lut64-p2-div-x2.c
similarity index 96%
rename from src/f32-sigmoid/gen/scalar-lut64-p2-div-x2.c
rename to src/f32-vsigmoid/gen/scalar-lut64-p2-div-x2.c
index edc47a5..a2735f8 100644
--- a/src/f32-sigmoid/gen/scalar-lut64-p2-div-x2.c
+++ b/src/f32-vsigmoid/gen/scalar-lut64-p2-div-x2.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/scalar-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/scalar-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -19,7 +19,7 @@
 // Note redefine as uint32[] to avoid redundant bitcasts.
 extern XNN_INTERNAL const uint32_t xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__scalar_lut64_p2_div_x2(
+void xnn_f32_vsigmoid_ukernel__scalar_lut64_p2_div_x2(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/scalar-lut64-p2-div-x4.c b/src/f32-vsigmoid/gen/scalar-lut64-p2-div-x4.c
similarity index 97%
rename from src/f32-sigmoid/gen/scalar-lut64-p2-div-x4.c
rename to src/f32-vsigmoid/gen/scalar-lut64-p2-div-x4.c
index bcc95e5..e320119 100644
--- a/src/f32-sigmoid/gen/scalar-lut64-p2-div-x4.c
+++ b/src/f32-vsigmoid/gen/scalar-lut64-p2-div-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/scalar-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/scalar-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -19,7 +19,7 @@
 // Note redefine as uint32[] to avoid redundant bitcasts.
 extern XNN_INTERNAL const uint32_t xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__scalar_lut64_p2_div_x4(
+void xnn_f32_vsigmoid_ukernel__scalar_lut64_p2_div_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/scalar-p5-div-x1.c b/src/f32-vsigmoid/gen/scalar-p5-div-x1.c
similarity index 93%
rename from src/f32-sigmoid/gen/scalar-p5-div-x1.c
rename to src/f32-vsigmoid/gen/scalar-p5-div-x1.c
index d4c0057..5941c9e 100644
--- a/src/f32-sigmoid/gen/scalar-p5-div-x1.c
+++ b/src/f32-vsigmoid/gen/scalar-p5-div-x1.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/scalar-p5-div.c.in
+//   Template: src/f32-vsigmoid/scalar-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -16,7 +16,7 @@
 #include <fp16/bitcasts.h>
 
 
-void xnn_f32_sigmoid_ukernel__scalar_p5_div_x1(
+void xnn_f32_vsigmoid_ukernel__scalar_p5_div_x1(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/scalar-p5-div-x2.c b/src/f32-vsigmoid/gen/scalar-p5-div-x2.c
similarity index 96%
rename from src/f32-sigmoid/gen/scalar-p5-div-x2.c
rename to src/f32-vsigmoid/gen/scalar-p5-div-x2.c
index fa7f1b0..b237f7e 100644
--- a/src/f32-sigmoid/gen/scalar-p5-div-x2.c
+++ b/src/f32-vsigmoid/gen/scalar-p5-div-x2.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/scalar-p5-div.c.in
+//   Template: src/f32-vsigmoid/scalar-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -16,7 +16,7 @@
 #include <fp16/bitcasts.h>
 
 
-void xnn_f32_sigmoid_ukernel__scalar_p5_div_x2(
+void xnn_f32_vsigmoid_ukernel__scalar_p5_div_x2(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/scalar-p5-div-x4.c b/src/f32-vsigmoid/gen/scalar-p5-div-x4.c
similarity index 97%
rename from src/f32-sigmoid/gen/scalar-p5-div-x4.c
rename to src/f32-vsigmoid/gen/scalar-p5-div-x4.c
index fd78fb0..efedf81 100644
--- a/src/f32-sigmoid/gen/scalar-p5-div-x4.c
+++ b/src/f32-vsigmoid/gen/scalar-p5-div-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/scalar-p5-div.c.in
+//   Template: src/f32-vsigmoid/scalar-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -16,7 +16,7 @@
 #include <fp16/bitcasts.h>
 
 
-void xnn_f32_sigmoid_ukernel__scalar_p5_div_x4(
+void xnn_f32_vsigmoid_ukernel__scalar_p5_div_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse2-lut64-p2-div-x12.c b/src/f32-vsigmoid/gen/sse2-lut64-p2-div-x12.c
similarity index 99%
rename from src/f32-sigmoid/gen/sse2-lut64-p2-div-x12.c
rename to src/f32-vsigmoid/gen/sse2-lut64-p2-div-x12.c
index 816db20..c26d899 100644
--- a/src/f32-sigmoid/gen/sse2-lut64-p2-div-x12.c
+++ b/src/f32-vsigmoid/gen/sse2-lut64-p2-div-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/sse-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__sse2_lut64_p2_div_x12(
+void xnn_f32_vsigmoid_ukernel__sse2_lut64_p2_div_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse2-lut64-p2-div-x16.c b/src/f32-vsigmoid/gen/sse2-lut64-p2-div-x16.c
similarity index 99%
rename from src/f32-sigmoid/gen/sse2-lut64-p2-div-x16.c
rename to src/f32-vsigmoid/gen/sse2-lut64-p2-div-x16.c
index d6b2b67..6c757ee 100644
--- a/src/f32-sigmoid/gen/sse2-lut64-p2-div-x16.c
+++ b/src/f32-vsigmoid/gen/sse2-lut64-p2-div-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/sse-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__sse2_lut64_p2_div_x16(
+void xnn_f32_vsigmoid_ukernel__sse2_lut64_p2_div_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse2-lut64-p2-div-x20.c b/src/f32-vsigmoid/gen/sse2-lut64-p2-div-x20.c
similarity index 99%
rename from src/f32-sigmoid/gen/sse2-lut64-p2-div-x20.c
rename to src/f32-vsigmoid/gen/sse2-lut64-p2-div-x20.c
index 0c8d7d3..5f4878c 100644
--- a/src/f32-sigmoid/gen/sse2-lut64-p2-div-x20.c
+++ b/src/f32-vsigmoid/gen/sse2-lut64-p2-div-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/sse-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__sse2_lut64_p2_div_x20(
+void xnn_f32_vsigmoid_ukernel__sse2_lut64_p2_div_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse2-lut64-p2-div-x24.c b/src/f32-vsigmoid/gen/sse2-lut64-p2-div-x24.c
similarity index 99%
rename from src/f32-sigmoid/gen/sse2-lut64-p2-div-x24.c
rename to src/f32-vsigmoid/gen/sse2-lut64-p2-div-x24.c
index 5dafb94..374a9ef 100644
--- a/src/f32-sigmoid/gen/sse2-lut64-p2-div-x24.c
+++ b/src/f32-vsigmoid/gen/sse2-lut64-p2-div-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/sse-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__sse2_lut64_p2_div_x24(
+void xnn_f32_vsigmoid_ukernel__sse2_lut64_p2_div_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse2-lut64-p2-div-x4.c b/src/f32-vsigmoid/gen/sse2-lut64-p2-div-x4.c
similarity index 98%
rename from src/f32-sigmoid/gen/sse2-lut64-p2-div-x4.c
rename to src/f32-vsigmoid/gen/sse2-lut64-p2-div-x4.c
index ab2abb6..acda587 100644
--- a/src/f32-sigmoid/gen/sse2-lut64-p2-div-x4.c
+++ b/src/f32-vsigmoid/gen/sse2-lut64-p2-div-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/sse-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__sse2_lut64_p2_div_x4(
+void xnn_f32_vsigmoid_ukernel__sse2_lut64_p2_div_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse2-lut64-p2-div-x8.c b/src/f32-vsigmoid/gen/sse2-lut64-p2-div-x8.c
similarity index 98%
rename from src/f32-sigmoid/gen/sse2-lut64-p2-div-x8.c
rename to src/f32-vsigmoid/gen/sse2-lut64-p2-div-x8.c
index 8861427..c3f6663 100644
--- a/src/f32-sigmoid/gen/sse2-lut64-p2-div-x8.c
+++ b/src/f32-vsigmoid/gen/sse2-lut64-p2-div-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/sse-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__sse2_lut64_p2_div_x8(
+void xnn_f32_vsigmoid_ukernel__sse2_lut64_p2_div_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse2-p5-div-x12.c b/src/f32-vsigmoid/gen/sse2-p5-div-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/sse2-p5-div-x12.c
rename to src/f32-vsigmoid/gen/sse2-p5-div-x12.c
index 19fc316..24d428f 100644
--- a/src/f32-sigmoid/gen/sse2-p5-div-x12.c
+++ b/src/f32-vsigmoid/gen/sse2-p5-div-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-p5-div.c.in
+//   Template: src/f32-vsigmoid/sse-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__sse2_p5_div_x12(
+void xnn_f32_vsigmoid_ukernel__sse2_p5_div_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse2-p5-div-x16.c b/src/f32-vsigmoid/gen/sse2-p5-div-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/sse2-p5-div-x16.c
rename to src/f32-vsigmoid/gen/sse2-p5-div-x16.c
index b928e44..f5867fa 100644
--- a/src/f32-sigmoid/gen/sse2-p5-div-x16.c
+++ b/src/f32-vsigmoid/gen/sse2-p5-div-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-p5-div.c.in
+//   Template: src/f32-vsigmoid/sse-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__sse2_p5_div_x16(
+void xnn_f32_vsigmoid_ukernel__sse2_p5_div_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse2-p5-div-x20.c b/src/f32-vsigmoid/gen/sse2-p5-div-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/sse2-p5-div-x20.c
rename to src/f32-vsigmoid/gen/sse2-p5-div-x20.c
index a594dda..a6be804 100644
--- a/src/f32-sigmoid/gen/sse2-p5-div-x20.c
+++ b/src/f32-vsigmoid/gen/sse2-p5-div-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-p5-div.c.in
+//   Template: src/f32-vsigmoid/sse-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__sse2_p5_div_x20(
+void xnn_f32_vsigmoid_ukernel__sse2_p5_div_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse2-p5-div-x24.c b/src/f32-vsigmoid/gen/sse2-p5-div-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/sse2-p5-div-x24.c
rename to src/f32-vsigmoid/gen/sse2-p5-div-x24.c
index 8f5f10c..77ccf27 100644
--- a/src/f32-sigmoid/gen/sse2-p5-div-x24.c
+++ b/src/f32-vsigmoid/gen/sse2-p5-div-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-p5-div.c.in
+//   Template: src/f32-vsigmoid/sse-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__sse2_p5_div_x24(
+void xnn_f32_vsigmoid_ukernel__sse2_p5_div_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse2-p5-div-x4.c b/src/f32-vsigmoid/gen/sse2-p5-div-x4.c
similarity index 97%
rename from src/f32-sigmoid/gen/sse2-p5-div-x4.c
rename to src/f32-vsigmoid/gen/sse2-p5-div-x4.c
index 79a77c4..5f8bf06 100644
--- a/src/f32-sigmoid/gen/sse2-p5-div-x4.c
+++ b/src/f32-vsigmoid/gen/sse2-p5-div-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-p5-div.c.in
+//   Template: src/f32-vsigmoid/sse-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__sse2_p5_div_x4(
+void xnn_f32_vsigmoid_ukernel__sse2_p5_div_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse2-p5-div-x8.c b/src/f32-vsigmoid/gen/sse2-p5-div-x8.c
similarity index 98%
rename from src/f32-sigmoid/gen/sse2-p5-div-x8.c
rename to src/f32-vsigmoid/gen/sse2-p5-div-x8.c
index 968daaa..47e8f78 100644
--- a/src/f32-sigmoid/gen/sse2-p5-div-x8.c
+++ b/src/f32-vsigmoid/gen/sse2-p5-div-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-p5-div.c.in
+//   Template: src/f32-vsigmoid/sse-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__sse2_p5_div_x8(
+void xnn_f32_vsigmoid_ukernel__sse2_p5_div_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse41-lut64-p2-div-x12.c b/src/f32-vsigmoid/gen/sse41-lut64-p2-div-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/sse41-lut64-p2-div-x12.c
rename to src/f32-vsigmoid/gen/sse41-lut64-p2-div-x12.c
index 5825550..9cf7419 100644
--- a/src/f32-sigmoid/gen/sse41-lut64-p2-div-x12.c
+++ b/src/f32-vsigmoid/gen/sse41-lut64-p2-div-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/sse-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__sse41_lut64_p2_div_x12(
+void xnn_f32_vsigmoid_ukernel__sse41_lut64_p2_div_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse41-lut64-p2-div-x16.c b/src/f32-vsigmoid/gen/sse41-lut64-p2-div-x16.c
similarity index 99%
rename from src/f32-sigmoid/gen/sse41-lut64-p2-div-x16.c
rename to src/f32-vsigmoid/gen/sse41-lut64-p2-div-x16.c
index c71eb09..c5c41d4 100644
--- a/src/f32-sigmoid/gen/sse41-lut64-p2-div-x16.c
+++ b/src/f32-vsigmoid/gen/sse41-lut64-p2-div-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/sse-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__sse41_lut64_p2_div_x16(
+void xnn_f32_vsigmoid_ukernel__sse41_lut64_p2_div_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse41-lut64-p2-div-x20.c b/src/f32-vsigmoid/gen/sse41-lut64-p2-div-x20.c
similarity index 99%
rename from src/f32-sigmoid/gen/sse41-lut64-p2-div-x20.c
rename to src/f32-vsigmoid/gen/sse41-lut64-p2-div-x20.c
index 4bea693..e87b49e 100644
--- a/src/f32-sigmoid/gen/sse41-lut64-p2-div-x20.c
+++ b/src/f32-vsigmoid/gen/sse41-lut64-p2-div-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/sse-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__sse41_lut64_p2_div_x20(
+void xnn_f32_vsigmoid_ukernel__sse41_lut64_p2_div_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse41-lut64-p2-div-x24.c b/src/f32-vsigmoid/gen/sse41-lut64-p2-div-x24.c
similarity index 99%
rename from src/f32-sigmoid/gen/sse41-lut64-p2-div-x24.c
rename to src/f32-vsigmoid/gen/sse41-lut64-p2-div-x24.c
index de75420..a302fa4 100644
--- a/src/f32-sigmoid/gen/sse41-lut64-p2-div-x24.c
+++ b/src/f32-vsigmoid/gen/sse41-lut64-p2-div-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/sse-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__sse41_lut64_p2_div_x24(
+void xnn_f32_vsigmoid_ukernel__sse41_lut64_p2_div_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse41-lut64-p2-div-x4.c b/src/f32-vsigmoid/gen/sse41-lut64-p2-div-x4.c
similarity index 97%
rename from src/f32-sigmoid/gen/sse41-lut64-p2-div-x4.c
rename to src/f32-vsigmoid/gen/sse41-lut64-p2-div-x4.c
index 4ce64e6..3fee506 100644
--- a/src/f32-sigmoid/gen/sse41-lut64-p2-div-x4.c
+++ b/src/f32-vsigmoid/gen/sse41-lut64-p2-div-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/sse-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__sse41_lut64_p2_div_x4(
+void xnn_f32_vsigmoid_ukernel__sse41_lut64_p2_div_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse41-lut64-p2-div-x8.c b/src/f32-vsigmoid/gen/sse41-lut64-p2-div-x8.c
similarity index 98%
rename from src/f32-sigmoid/gen/sse41-lut64-p2-div-x8.c
rename to src/f32-vsigmoid/gen/sse41-lut64-p2-div-x8.c
index 2aa61db..75fafed 100644
--- a/src/f32-sigmoid/gen/sse41-lut64-p2-div-x8.c
+++ b/src/f32-vsigmoid/gen/sse41-lut64-p2-div-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/sse-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__sse41_lut64_p2_div_x8(
+void xnn_f32_vsigmoid_ukernel__sse41_lut64_p2_div_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse41-p5-div-x12.c b/src/f32-vsigmoid/gen/sse41-p5-div-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/sse41-p5-div-x12.c
rename to src/f32-vsigmoid/gen/sse41-p5-div-x12.c
index 4f665a7..af492f7 100644
--- a/src/f32-sigmoid/gen/sse41-p5-div-x12.c
+++ b/src/f32-vsigmoid/gen/sse41-p5-div-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-p5-div.c.in
+//   Template: src/f32-vsigmoid/sse-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__sse41_p5_div_x12(
+void xnn_f32_vsigmoid_ukernel__sse41_p5_div_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse41-p5-div-x16.c b/src/f32-vsigmoid/gen/sse41-p5-div-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/sse41-p5-div-x16.c
rename to src/f32-vsigmoid/gen/sse41-p5-div-x16.c
index 0f0fc7c..081e2ca 100644
--- a/src/f32-sigmoid/gen/sse41-p5-div-x16.c
+++ b/src/f32-vsigmoid/gen/sse41-p5-div-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-p5-div.c.in
+//   Template: src/f32-vsigmoid/sse-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__sse41_p5_div_x16(
+void xnn_f32_vsigmoid_ukernel__sse41_p5_div_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse41-p5-div-x20.c b/src/f32-vsigmoid/gen/sse41-p5-div-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/sse41-p5-div-x20.c
rename to src/f32-vsigmoid/gen/sse41-p5-div-x20.c
index 8315531..99ec379 100644
--- a/src/f32-sigmoid/gen/sse41-p5-div-x20.c
+++ b/src/f32-vsigmoid/gen/sse41-p5-div-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-p5-div.c.in
+//   Template: src/f32-vsigmoid/sse-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__sse41_p5_div_x20(
+void xnn_f32_vsigmoid_ukernel__sse41_p5_div_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse41-p5-div-x24.c b/src/f32-vsigmoid/gen/sse41-p5-div-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/sse41-p5-div-x24.c
rename to src/f32-vsigmoid/gen/sse41-p5-div-x24.c
index ee5a83a..fa95451 100644
--- a/src/f32-sigmoid/gen/sse41-p5-div-x24.c
+++ b/src/f32-vsigmoid/gen/sse41-p5-div-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-p5-div.c.in
+//   Template: src/f32-vsigmoid/sse-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__sse41_p5_div_x24(
+void xnn_f32_vsigmoid_ukernel__sse41_p5_div_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse41-p5-div-x4.c b/src/f32-vsigmoid/gen/sse41-p5-div-x4.c
similarity index 96%
rename from src/f32-sigmoid/gen/sse41-p5-div-x4.c
rename to src/f32-vsigmoid/gen/sse41-p5-div-x4.c
index 0af0f6a..8f032d8 100644
--- a/src/f32-sigmoid/gen/sse41-p5-div-x4.c
+++ b/src/f32-vsigmoid/gen/sse41-p5-div-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-p5-div.c.in
+//   Template: src/f32-vsigmoid/sse-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__sse41_p5_div_x4(
+void xnn_f32_vsigmoid_ukernel__sse41_p5_div_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/sse41-p5-div-x8.c b/src/f32-vsigmoid/gen/sse41-p5-div-x8.c
similarity index 97%
rename from src/f32-sigmoid/gen/sse41-p5-div-x8.c
rename to src/f32-vsigmoid/gen/sse41-p5-div-x8.c
index b34d722..3348a48 100644
--- a/src/f32-sigmoid/gen/sse41-p5-div-x8.c
+++ b/src/f32-vsigmoid/gen/sse41-p5-div-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/sse-p5-div.c.in
+//   Template: src/f32-vsigmoid/sse-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2019 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__sse41_p5_div_x8(
+void xnn_f32_vsigmoid_ukernel__sse41_p5_div_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/wasmsimd-lut64-p2-div-x12.c b/src/f32-vsigmoid/gen/wasmsimd-lut64-p2-div-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/wasmsimd-lut64-p2-div-x12.c
rename to src/f32-vsigmoid/gen/wasmsimd-lut64-p2-div-x12.c
index 24ebde0..4d63fe4 100644
--- a/src/f32-sigmoid/gen/wasmsimd-lut64-p2-div-x12.c
+++ b/src/f32-vsigmoid/gen/wasmsimd-lut64-p2-div-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/wasmsimd-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/wasmsimd-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__wasmsimd_lut64_p2_div_x12(
+void xnn_f32_vsigmoid_ukernel__wasmsimd_lut64_p2_div_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/wasmsimd-lut64-p2-div-x16.c b/src/f32-vsigmoid/gen/wasmsimd-lut64-p2-div-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/wasmsimd-lut64-p2-div-x16.c
rename to src/f32-vsigmoid/gen/wasmsimd-lut64-p2-div-x16.c
index 0560ddc..7c2d482 100644
--- a/src/f32-sigmoid/gen/wasmsimd-lut64-p2-div-x16.c
+++ b/src/f32-vsigmoid/gen/wasmsimd-lut64-p2-div-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/wasmsimd-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/wasmsimd-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__wasmsimd_lut64_p2_div_x16(
+void xnn_f32_vsigmoid_ukernel__wasmsimd_lut64_p2_div_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/wasmsimd-lut64-p2-div-x20.c b/src/f32-vsigmoid/gen/wasmsimd-lut64-p2-div-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/wasmsimd-lut64-p2-div-x20.c
rename to src/f32-vsigmoid/gen/wasmsimd-lut64-p2-div-x20.c
index 5002b95..23196da 100644
--- a/src/f32-sigmoid/gen/wasmsimd-lut64-p2-div-x20.c
+++ b/src/f32-vsigmoid/gen/wasmsimd-lut64-p2-div-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/wasmsimd-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/wasmsimd-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__wasmsimd_lut64_p2_div_x20(
+void xnn_f32_vsigmoid_ukernel__wasmsimd_lut64_p2_div_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/wasmsimd-lut64-p2-div-x24.c b/src/f32-vsigmoid/gen/wasmsimd-lut64-p2-div-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/wasmsimd-lut64-p2-div-x24.c
rename to src/f32-vsigmoid/gen/wasmsimd-lut64-p2-div-x24.c
index f6f0bc1..249ebcb 100644
--- a/src/f32-sigmoid/gen/wasmsimd-lut64-p2-div-x24.c
+++ b/src/f32-vsigmoid/gen/wasmsimd-lut64-p2-div-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/wasmsimd-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/wasmsimd-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__wasmsimd_lut64_p2_div_x24(
+void xnn_f32_vsigmoid_ukernel__wasmsimd_lut64_p2_div_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/wasmsimd-lut64-p2-div-x4.c b/src/f32-vsigmoid/gen/wasmsimd-lut64-p2-div-x4.c
similarity index 97%
rename from src/f32-sigmoid/gen/wasmsimd-lut64-p2-div-x4.c
rename to src/f32-vsigmoid/gen/wasmsimd-lut64-p2-div-x4.c
index 3651e84..1fb8c55 100644
--- a/src/f32-sigmoid/gen/wasmsimd-lut64-p2-div-x4.c
+++ b/src/f32-vsigmoid/gen/wasmsimd-lut64-p2-div-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/wasmsimd-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/wasmsimd-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__wasmsimd_lut64_p2_div_x4(
+void xnn_f32_vsigmoid_ukernel__wasmsimd_lut64_p2_div_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/wasmsimd-lut64-p2-div-x8.c b/src/f32-vsigmoid/gen/wasmsimd-lut64-p2-div-x8.c
similarity index 98%
rename from src/f32-sigmoid/gen/wasmsimd-lut64-p2-div-x8.c
rename to src/f32-vsigmoid/gen/wasmsimd-lut64-p2-div-x8.c
index 912d249..89ddd1d 100644
--- a/src/f32-sigmoid/gen/wasmsimd-lut64-p2-div-x8.c
+++ b/src/f32-vsigmoid/gen/wasmsimd-lut64-p2-div-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/wasmsimd-lut64-p2-div.c.in
+//   Template: src/f32-vsigmoid/wasmsimd-lut64-p2-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -17,7 +17,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__wasmsimd_lut64_p2_div_x8(
+void xnn_f32_vsigmoid_ukernel__wasmsimd_lut64_p2_div_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/wasmsimd-p5-div-x12.c b/src/f32-vsigmoid/gen/wasmsimd-p5-div-x12.c
similarity index 98%
rename from src/f32-sigmoid/gen/wasmsimd-p5-div-x12.c
rename to src/f32-vsigmoid/gen/wasmsimd-p5-div-x12.c
index 1a9e2de..34e87fe 100644
--- a/src/f32-sigmoid/gen/wasmsimd-p5-div-x12.c
+++ b/src/f32-vsigmoid/gen/wasmsimd-p5-div-x12.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/wasmsimd-p5-div.c.in
+//   Template: src/f32-vsigmoid/wasmsimd-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__wasmsimd_p5_div_x12(
+void xnn_f32_vsigmoid_ukernel__wasmsimd_p5_div_x12(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/wasmsimd-p5-div-x16.c b/src/f32-vsigmoid/gen/wasmsimd-p5-div-x16.c
similarity index 98%
rename from src/f32-sigmoid/gen/wasmsimd-p5-div-x16.c
rename to src/f32-vsigmoid/gen/wasmsimd-p5-div-x16.c
index ad22b68..8f48e49 100644
--- a/src/f32-sigmoid/gen/wasmsimd-p5-div-x16.c
+++ b/src/f32-vsigmoid/gen/wasmsimd-p5-div-x16.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/wasmsimd-p5-div.c.in
+//   Template: src/f32-vsigmoid/wasmsimd-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__wasmsimd_p5_div_x16(
+void xnn_f32_vsigmoid_ukernel__wasmsimd_p5_div_x16(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/wasmsimd-p5-div-x20.c b/src/f32-vsigmoid/gen/wasmsimd-p5-div-x20.c
similarity index 98%
rename from src/f32-sigmoid/gen/wasmsimd-p5-div-x20.c
rename to src/f32-vsigmoid/gen/wasmsimd-p5-div-x20.c
index f8f0333..0d1c1c1 100644
--- a/src/f32-sigmoid/gen/wasmsimd-p5-div-x20.c
+++ b/src/f32-vsigmoid/gen/wasmsimd-p5-div-x20.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/wasmsimd-p5-div.c.in
+//   Template: src/f32-vsigmoid/wasmsimd-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__wasmsimd_p5_div_x20(
+void xnn_f32_vsigmoid_ukernel__wasmsimd_p5_div_x20(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/wasmsimd-p5-div-x24.c b/src/f32-vsigmoid/gen/wasmsimd-p5-div-x24.c
similarity index 98%
rename from src/f32-sigmoid/gen/wasmsimd-p5-div-x24.c
rename to src/f32-vsigmoid/gen/wasmsimd-p5-div-x24.c
index 94ee6b8..490f0c8 100644
--- a/src/f32-sigmoid/gen/wasmsimd-p5-div-x24.c
+++ b/src/f32-vsigmoid/gen/wasmsimd-p5-div-x24.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/wasmsimd-p5-div.c.in
+//   Template: src/f32-vsigmoid/wasmsimd-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__wasmsimd_p5_div_x24(
+void xnn_f32_vsigmoid_ukernel__wasmsimd_p5_div_x24(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/wasmsimd-p5-div-x4.c b/src/f32-vsigmoid/gen/wasmsimd-p5-div-x4.c
similarity index 96%
rename from src/f32-sigmoid/gen/wasmsimd-p5-div-x4.c
rename to src/f32-vsigmoid/gen/wasmsimd-p5-div-x4.c
index 253a75e..1822e8b 100644
--- a/src/f32-sigmoid/gen/wasmsimd-p5-div-x4.c
+++ b/src/f32-vsigmoid/gen/wasmsimd-p5-div-x4.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/wasmsimd-p5-div.c.in
+//   Template: src/f32-vsigmoid/wasmsimd-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__wasmsimd_p5_div_x4(
+void xnn_f32_vsigmoid_ukernel__wasmsimd_p5_div_x4(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/gen/wasmsimd-p5-div-x8.c b/src/f32-vsigmoid/gen/wasmsimd-p5-div-x8.c
similarity index 97%
rename from src/f32-sigmoid/gen/wasmsimd-p5-div-x8.c
rename to src/f32-vsigmoid/gen/wasmsimd-p5-div-x8.c
index f93e351..a423a89 100644
--- a/src/f32-sigmoid/gen/wasmsimd-p5-div-x8.c
+++ b/src/f32-vsigmoid/gen/wasmsimd-p5-div-x8.c
@@ -1,5 +1,5 @@
 // Auto-generated file. Do not edit!
-//   Template: src/f32-sigmoid/wasmsimd-p5-div.c.in
+//   Template: src/f32-vsigmoid/wasmsimd-p5-div.c.in
 //   Generator: tools/xngen
 //
 // Copyright 2020 Google LLC
@@ -15,7 +15,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__wasmsimd_p5_div_x8(
+void xnn_f32_vsigmoid_ukernel__wasmsimd_p5_div_x8(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/neon-lut2048-p1.c.in b/src/f32-vsigmoid/neon-lut2048-p1.c.in
similarity index 98%
rename from src/f32-sigmoid/neon-lut2048-p1.c.in
rename to src/f32-vsigmoid/neon-lut2048-p1.c.in
index 14f14ef..8e69dea 100644
--- a/src/f32-sigmoid/neon-lut2048-p1.c.in
+++ b/src/f32-vsigmoid/neon-lut2048-p1.c.in
@@ -19,7 +19,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__${"neonfma" if FMA else "neon"}_rr${RR_STEPS}_lut2048_p1_${DIV_ALGO}_x${BATCH_TILE}(
+void xnn_f32_vsigmoid_ukernel__${"neonfma" if FMA else "neon"}_rr${RR_STEPS}_lut2048_p1_${DIV_ALGO}_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/neon-lut64-p2.c.in b/src/f32-vsigmoid/neon-lut64-p2.c.in
similarity index 98%
rename from src/f32-sigmoid/neon-lut64-p2.c.in
rename to src/f32-vsigmoid/neon-lut64-p2.c.in
index 29fbe99..1bd2736 100644
--- a/src/f32-sigmoid/neon-lut64-p2.c.in
+++ b/src/f32-vsigmoid/neon-lut64-p2.c.in
@@ -20,7 +20,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__${"neonfma" if FMA else "neon"}_rr${RR_STEPS}_lut64_p2_${DIV_ALGO}_x${BATCH_TILE}(
+void xnn_f32_vsigmoid_ukernel__${"neonfma" if FMA else "neon"}_rr${RR_STEPS}_lut64_p2_${DIV_ALGO}_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/neon-p5.c.in b/src/f32-vsigmoid/neon-p5.c.in
similarity index 98%
rename from src/f32-sigmoid/neon-p5.c.in
rename to src/f32-vsigmoid/neon-p5.c.in
index 9e9dc39..c267d73 100644
--- a/src/f32-sigmoid/neon-p5.c.in
+++ b/src/f32-vsigmoid/neon-p5.c.in
@@ -17,7 +17,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__${"neonfma" if FMA else "neon"}_rr${RR_STEPS}_p5_${DIV_ALGO}_x${BATCH_TILE}(
+void xnn_f32_vsigmoid_ukernel__${"neonfma" if FMA else "neon"}_rr${RR_STEPS}_p5_${DIV_ALGO}_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/scalar-lut2048-p1-div.c.in b/src/f32-vsigmoid/scalar-lut2048-p1-div.c.in
similarity index 98%
rename from src/f32-sigmoid/scalar-lut2048-p1-div.c.in
rename to src/f32-vsigmoid/scalar-lut2048-p1-div.c.in
index fb6fdea..62163bd 100644
--- a/src/f32-sigmoid/scalar-lut2048-p1-div.c.in
+++ b/src/f32-vsigmoid/scalar-lut2048-p1-div.c.in
@@ -17,7 +17,7 @@
 // Note redefine as uint32[] to avoid redundant bitcasts.
 extern XNN_INTERNAL const uint32_t xnn_table_exp2minus_k_over_2048[2048];
 
-void xnn_f32_sigmoid_ukernel__scalar_lut2048_p1_div_x${BATCH_TILE}(
+void xnn_f32_vsigmoid_ukernel__scalar_lut2048_p1_div_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/scalar-lut64-p2-div.c.in b/src/f32-vsigmoid/scalar-lut64-p2-div.c.in
similarity index 98%
rename from src/f32-sigmoid/scalar-lut64-p2-div.c.in
rename to src/f32-vsigmoid/scalar-lut64-p2-div.c.in
index 7cc5a40..395817b 100644
--- a/src/f32-sigmoid/scalar-lut64-p2-div.c.in
+++ b/src/f32-vsigmoid/scalar-lut64-p2-div.c.in
@@ -17,7 +17,7 @@
 // Note redefine as uint32[] to avoid redundant bitcasts.
 extern XNN_INTERNAL const uint32_t xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__scalar_lut64_p2_div_x${BATCH_TILE}(
+void xnn_f32_vsigmoid_ukernel__scalar_lut64_p2_div_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/scalar-p5-div.c.in b/src/f32-vsigmoid/scalar-p5-div.c.in
similarity index 98%
rename from src/f32-sigmoid/scalar-p5-div.c.in
rename to src/f32-vsigmoid/scalar-p5-div.c.in
index c0b455c..7b18f7a 100644
--- a/src/f32-sigmoid/scalar-p5-div.c.in
+++ b/src/f32-vsigmoid/scalar-p5-div.c.in
@@ -14,7 +14,7 @@
 #include <fp16/bitcasts.h>
 
 
-void xnn_f32_sigmoid_ukernel__scalar_p5_div_x${BATCH_TILE}(
+void xnn_f32_vsigmoid_ukernel__scalar_p5_div_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/sse-lut64-p2-div.c.in b/src/f32-vsigmoid/sse-lut64-p2-div.c.in
similarity index 99%
rename from src/f32-sigmoid/sse-lut64-p2-div.c.in
rename to src/f32-vsigmoid/sse-lut64-p2-div.c.in
index 3a04ce8..6454428 100644
--- a/src/f32-sigmoid/sse-lut64-p2-div.c.in
+++ b/src/f32-vsigmoid/sse-lut64-p2-div.c.in
@@ -18,7 +18,7 @@
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
 $ISA = {2: "sse2", 4: "sse41"}[SSE]
-void xnn_f32_sigmoid_ukernel__${ISA}_lut64_p2_div_x${BATCH_TILE}(
+void xnn_f32_vsigmoid_ukernel__${ISA}_lut64_p2_div_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/sse-p5-div.c.in b/src/f32-vsigmoid/sse-p5-div.c.in
similarity index 98%
rename from src/f32-sigmoid/sse-p5-div.c.in
rename to src/f32-vsigmoid/sse-p5-div.c.in
index e98f097..22881fd 100644
--- a/src/f32-sigmoid/sse-p5-div.c.in
+++ b/src/f32-vsigmoid/sse-p5-div.c.in
@@ -16,7 +16,7 @@
 
 
 $ISA = {2: "sse2", 4: "sse41"}[SSE]
-void xnn_f32_sigmoid_ukernel__${ISA}_p5_div_x${BATCH_TILE}(
+void xnn_f32_vsigmoid_ukernel__${ISA}_p5_div_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/wasmsimd-lut64-p2-div.c.in b/src/f32-vsigmoid/wasmsimd-lut64-p2-div.c.in
similarity index 98%
rename from src/f32-sigmoid/wasmsimd-lut64-p2-div.c.in
rename to src/f32-vsigmoid/wasmsimd-lut64-p2-div.c.in
index cf6db17..c9112d4 100644
--- a/src/f32-sigmoid/wasmsimd-lut64-p2-div.c.in
+++ b/src/f32-vsigmoid/wasmsimd-lut64-p2-div.c.in
@@ -16,7 +16,7 @@
 
 extern XNN_INTERNAL const float xnn_table_exp2minus_k_over_64[64];
 
-void xnn_f32_sigmoid_ukernel__wasmsimd_lut64_p2_div_x${BATCH_TILE}(
+void xnn_f32_vsigmoid_ukernel__wasmsimd_lut64_p2_div_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/f32-sigmoid/wasmsimd-p5-div.c.in b/src/f32-vsigmoid/wasmsimd-p5-div.c.in
similarity index 98%
rename from src/f32-sigmoid/wasmsimd-p5-div.c.in
rename to src/f32-vsigmoid/wasmsimd-p5-div.c.in
index 6d75673..88e1cd9 100644
--- a/src/f32-sigmoid/wasmsimd-p5-div.c.in
+++ b/src/f32-vsigmoid/wasmsimd-p5-div.c.in
@@ -14,7 +14,7 @@
 #include <xnnpack/vunary.h>
 
 
-void xnn_f32_sigmoid_ukernel__wasmsimd_p5_div_x${BATCH_TILE}(
+void xnn_f32_vsigmoid_ukernel__wasmsimd_p5_div_x${BATCH_TILE}(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/init.c b/src/init.c
index 2b8b15c..f899a71 100644
--- a/src/init.c
+++ b/src/init.c
@@ -181,7 +181,7 @@
         .mr = 9,
         .qr = 8,
       };
-      xnn_params.u8.clamp = (xnn_univector_ukernel_function) xnn_u8_clamp_ukernel__neon_x64;
+      xnn_params.u8.clamp = (xnn_univector_ukernel_function) xnn_u8_vclamp_ukernel__neon_x64;
       xnn_params.u8.rmax = xnn_u8_rmax_ukernel__neon;
       xnn_params.u8.lut32norm = xnn_u8_lut32norm_ukernel__scalar;
     #endif  // XNN_NO_U8_OPERATORS
@@ -358,13 +358,13 @@
         .channel_tile = 8,
       };
       xnn_params.f32.abs = (xnn_univector_ukernel_function) xnn_f32_vabs_ukernel__neon_x8;
-      xnn_params.f32.clamp = (xnn_univector_ukernel_function) xnn_f32_clamp_ukernel__neon_x8;
+      xnn_params.f32.clamp = (xnn_univector_ukernel_function) xnn_f32_vclamp_ukernel__neon_x8;
       if (cpuinfo_has_arm_neon_fma()) {
         xnn_params.f32.elu = (xnn_univector_ukernel_function) xnn_f32_velu_ukernel__neonfma_rr1_p6_x8;
       } else {
         xnn_params.f32.elu = (xnn_univector_ukernel_function) xnn_f32_velu_ukernel__neon_rr2_lut16_p3_x8;
       }
-      xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_hswish_ukernel__neon_x16;
+      xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_vhswish_ukernel__neon_x16;
       xnn_params.f32.lrelu = (xnn_univector_ukernel_function) xnn_f32_vlrelu_ukernel__neon_x8;
       xnn_params.f32.neg = (xnn_univector_ukernel_function) xnn_f32_vneg_ukernel__neon_x8;
       if (cpuinfo_has_arm_neon_v8()) {
@@ -378,7 +378,7 @@
         xnn_params.f32.rndu  = (xnn_univector_ukernel_function) xnn_f32_vrndu_ukernel__neon_x8;
         xnn_params.f32.rndd  = (xnn_univector_ukernel_function) xnn_f32_vrndd_ukernel__neon_x8;
       }
-      xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_sigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x8;
+      xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_vsigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x8;
       xnn_params.f32.sqr = (xnn_univector_ukernel_function) xnn_f32_vsqr_ukernel__neon_x8;
       xnn_params.f32.sqrt = (xnn_univector_ukernel_function) xnn_f32_vsqrt_ukernel__scalar_sqrt_x1;
       xnn_params.f32.prelu = (struct prelu_parameters) {
@@ -546,7 +546,7 @@
         .mr = 9,
         .qr = 8,
       };
-      xnn_params.u8.clamp = (xnn_univector_ukernel_function) xnn_u8_clamp_ukernel__scalar_x4;
+      xnn_params.u8.clamp = (xnn_univector_ukernel_function) xnn_u8_vclamp_ukernel__scalar_x4;
       xnn_params.u8.lut32norm = xnn_u8_lut32norm_ukernel__scalar;
       xnn_params.u8.rmax = xnn_u8_rmax_ukernel__scalar;
     #endif  // XNN_NO_U8_OPERATORS
@@ -646,16 +646,16 @@
         .channel_tile = 2,
       };
       xnn_params.f32.abs = (xnn_univector_ukernel_function) xnn_f32_vabs_ukernel__scalar_x4;
-      xnn_params.f32.clamp = (xnn_univector_ukernel_function) xnn_f32_clamp_ukernel__scalar_x4;
+      xnn_params.f32.clamp = (xnn_univector_ukernel_function) xnn_f32_vclamp_ukernel__scalar_x4;
       xnn_params.f32.elu = (xnn_univector_ukernel_function) xnn_f32_velu_ukernel__scalar_rr2_lut16_p3_x4;
-      xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_hswish_ukernel__scalar_x4;
+      xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_vhswish_ukernel__scalar_x4;
       xnn_params.f32.lrelu = (xnn_univector_ukernel_function) xnn_f32_vlrelu_ukernel__scalar_x4;
       xnn_params.f32.neg = (xnn_univector_ukernel_function) xnn_f32_vneg_ukernel__scalar_x4;
       xnn_params.f32.rndne = (xnn_univector_ukernel_function) xnn_f32_vrndne_ukernel__scalar_libm_x1;
       xnn_params.f32.rndz  = (xnn_univector_ukernel_function) xnn_f32_vrndz_ukernel__scalar_libm_x1;
       xnn_params.f32.rndu  = (xnn_univector_ukernel_function) xnn_f32_vrndu_ukernel__scalar_libm_x1;
       xnn_params.f32.rndd  = (xnn_univector_ukernel_function) xnn_f32_vrndd_ukernel__scalar_libm_x1;
-      xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_sigmoid_ukernel__scalar_lut64_p2_div_x2;
+      xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_vsigmoid_ukernel__scalar_lut64_p2_div_x2;
       xnn_params.f32.sqr = (xnn_univector_ukernel_function) xnn_f32_vsqr_ukernel__scalar_x4;
       xnn_params.f32.sqrt = (xnn_univector_ukernel_function) xnn_f32_vsqrt_ukernel__scalar_sqrt_x1;
       xnn_params.f32.prelu = (struct prelu_parameters) {
@@ -1016,7 +1016,7 @@
       .mr = 9,
       .qr = 8,
     };
-    xnn_params.u8.clamp = (xnn_univector_ukernel_function) xnn_u8_clamp_ukernel__neon_x64;
+    xnn_params.u8.clamp = (xnn_univector_ukernel_function) xnn_u8_vclamp_ukernel__neon_x64;
     xnn_params.u8.lut32norm = xnn_u8_lut32norm_ukernel__scalar;
     xnn_params.u8.rmax = xnn_u8_rmax_ukernel__neon;
   #endif  // XNN_NO_U8_OPERATORS
@@ -1085,7 +1085,7 @@
         .channel_tile = 8,
         .row_tile = 2,
       };
-      xnn_params.f16.hswish = (xnn_univector_ukernel_function) xnn_f16_hswish_ukernel__neonfp16arith_x16;
+      xnn_params.f16.hswish = (xnn_univector_ukernel_function) xnn_f16_vhswish_ukernel__neonfp16arith_x16;
     }
   #endif  // XNN_NO_F16_OPERATORS
 
@@ -1324,16 +1324,16 @@
       .channel_tile = 8,
     };
     xnn_params.f32.abs = (xnn_univector_ukernel_function) xnn_f32_vabs_ukernel__neon_x8;
-    xnn_params.f32.clamp = (xnn_univector_ukernel_function) xnn_f32_clamp_ukernel__neon_x8;
+    xnn_params.f32.clamp = (xnn_univector_ukernel_function) xnn_f32_vclamp_ukernel__neon_x8;
     xnn_params.f32.elu = (xnn_univector_ukernel_function) xnn_f32_velu_ukernel__neonfma_rr1_lut16_p3_x16;
-    xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_hswish_ukernel__neon_x16;
+    xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_vhswish_ukernel__neon_x16;
     xnn_params.f32.lrelu = (xnn_univector_ukernel_function) xnn_f32_vlrelu_ukernel__neon_x8;
     xnn_params.f32.neg = (xnn_univector_ukernel_function) xnn_f32_vneg_ukernel__neon_x8;
     xnn_params.f32.rndne = (xnn_univector_ukernel_function) xnn_f32_vrndne_ukernel__neonv8_x8;
     xnn_params.f32.rndz = (xnn_univector_ukernel_function) xnn_f32_vrndz_ukernel__neonv8_x8;
     xnn_params.f32.rndu = (xnn_univector_ukernel_function) xnn_f32_vrndu_ukernel__neonv8_x8;
     xnn_params.f32.rndd = (xnn_univector_ukernel_function) xnn_f32_vrndd_ukernel__neonv8_x8;
-    xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x16;
+    xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x16;
     xnn_params.f32.sqr = (xnn_univector_ukernel_function) xnn_f32_vsqr_ukernel__neon_x8;
     xnn_params.f32.sqrt = (xnn_univector_ukernel_function) xnn_f32_vsqrt_ukernel__neon_sqrt_x4;
     xnn_params.f32.prelu = (struct prelu_parameters) {
@@ -1664,7 +1664,7 @@
       .mr = 9,
       .qr = 8,
     };
-    xnn_params.u8.clamp = (xnn_univector_ukernel_function) xnn_u8_clamp_ukernel__sse2_x64;
+    xnn_params.u8.clamp = (xnn_univector_ukernel_function) xnn_u8_vclamp_ukernel__sse2_x64;
     xnn_params.u8.lut32norm = xnn_u8_lut32norm_ukernel__scalar;
     xnn_params.u8.rmax = xnn_u8_rmax_ukernel__sse2;
   #endif  // XNN_NO_U8_OPERATORS
@@ -1832,11 +1832,11 @@
       xnn_params.f32.abs = (xnn_univector_ukernel_function) xnn_f32_vabs_ukernel__sse_x8;
     }
     if (!XNN_PLATFORM_MOBILE && cpuinfo_has_x86_avx512f()) {
-      xnn_params.f32.clamp = (xnn_univector_ukernel_function) xnn_f32_clamp_ukernel__avx512f_x16;
+      xnn_params.f32.clamp = (xnn_univector_ukernel_function) xnn_f32_vclamp_ukernel__avx512f_x16;
     } else if (!XNN_PLATFORM_MOBILE && cpuinfo_has_x86_avx()) {
-      xnn_params.f32.clamp = (xnn_univector_ukernel_function) xnn_f32_clamp_ukernel__avx_x16;
+      xnn_params.f32.clamp = (xnn_univector_ukernel_function) xnn_f32_vclamp_ukernel__avx_x16;
     } else {
-      xnn_params.f32.clamp = (xnn_univector_ukernel_function) xnn_f32_clamp_ukernel__sse_x8;
+      xnn_params.f32.clamp = (xnn_univector_ukernel_function) xnn_f32_vclamp_ukernel__sse_x8;
     }
     if (!XNN_PLATFORM_MOBILE && cpuinfo_has_x86_avx512f()) {
       xnn_params.f32.elu = (xnn_univector_ukernel_function) xnn_f32_velu_ukernel__avx512f_rr1_lut16_p3_perm_x64;
@@ -1848,13 +1848,13 @@
       xnn_params.f32.elu = (xnn_univector_ukernel_function) xnn_f32_velu_ukernel__sse2_rr2_lut16_p3_x12;
     }
     if (!XNN_PLATFORM_MOBILE && cpuinfo_has_x86_avx512f()) {
-      xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_hswish_ukernel__avx512f_x16;
+      xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_vhswish_ukernel__avx512f_x16;
     } else if (!XNN_PLATFORM_MOBILE && cpuinfo_has_x86_fma3()) {
-      xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_hswish_ukernel__fma3_x16;
+      xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_vhswish_ukernel__fma3_x16;
     } else if (!XNN_PLATFORM_MOBILE && cpuinfo_has_x86_avx()) {
-      xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_hswish_ukernel__avx_x16;
+      xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_vhswish_ukernel__avx_x16;
     } else {
-      xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_hswish_ukernel__sse_x8;
+      xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_vhswish_ukernel__sse_x8;
     }
     if (!XNN_PLATFORM_MOBILE && cpuinfo_has_x86_avx512f()) {
       xnn_params.f32.lrelu = (xnn_univector_ukernel_function) xnn_f32_vlrelu_ukernel__avx512f_x16;
@@ -1894,15 +1894,15 @@
       xnn_params.f32.rndd  = (xnn_univector_ukernel_function) xnn_f32_vrndd_ukernel__sse2_x8;
     }
     if (!XNN_PLATFORM_MOBILE && cpuinfo_has_x86_avx512f()) {
-      xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x64;
+      xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x64;
     } else if (!XNN_PLATFORM_MOBILE && cpuinfo_has_x86_avx2()) {
-      xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x40;
+      xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x40;
     } else if (!XNN_PLATFORM_MOBILE && cpuinfo_has_x86_avx()) {
-      xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x40;
+      xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x40;
     } else if (cpuinfo_has_x86_sse4_1()) {
-      xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_sigmoid_ukernel__sse41_lut64_p2_div_x8;
+      xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_vsigmoid_ukernel__sse41_lut64_p2_div_x8;
     } else {
-      xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_sigmoid_ukernel__sse2_lut64_p2_div_x8;
+      xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_vsigmoid_ukernel__sse2_lut64_p2_div_x8;
     }
     if (!XNN_PLATFORM_MOBILE && cpuinfo_has_x86_avx512f()) {
       xnn_params.f32.sqr = (xnn_univector_ukernel_function) xnn_f32_vsqr_ukernel__avx512f_x16;
@@ -2240,7 +2240,7 @@
       .mr = 9,
       .qr = 8,
     };
-    xnn_params.u8.clamp = (xnn_univector_ukernel_function) xnn_u8_clamp_ukernel__scalar_x4;
+    xnn_params.u8.clamp = (xnn_univector_ukernel_function) xnn_u8_vclamp_ukernel__scalar_x4;
     xnn_params.u8.lut32norm = xnn_u8_lut32norm_ukernel__scalar;
     xnn_params.u8.rmax = xnn_u8_rmax_ukernel__scalar;
   #endif  // XNN_NO_U8_OPERATORS
@@ -2407,23 +2407,23 @@
     };
     xnn_params.f32.abs = (xnn_univector_ukernel_function) xnn_f32_vabs_ukernel__wasmsimd_x8;
     if (is_wasm_x86) {
-      xnn_params.f32.clamp = (xnn_univector_ukernel_function) xnn_f32_clamp_ukernel__wasmsimd_x86_x8;
+      xnn_params.f32.clamp = (xnn_univector_ukernel_function) xnn_f32_vclamp_ukernel__wasmsimd_x86_x8;
     } else {
-      xnn_params.f32.clamp = (xnn_univector_ukernel_function) xnn_f32_clamp_ukernel__wasmsimd_arm_x8;
+      xnn_params.f32.clamp = (xnn_univector_ukernel_function) xnn_f32_vclamp_ukernel__wasmsimd_arm_x8;
     }
     if (is_wasm_x86) {
       xnn_params.f32.elu = (xnn_univector_ukernel_function) xnn_f32_velu_ukernel__wasmsimd_x86_rr2_p6_x20;
     } else {
       xnn_params.f32.elu = (xnn_univector_ukernel_function) xnn_f32_velu_ukernel__wasmsimd_arm_rr2_p6_x20;
     }
-    xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_hswish_ukernel__wasmsimd_x16;
+    xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_vhswish_ukernel__wasmsimd_x16;
     if (is_wasm_x86) {
       xnn_params.f32.lrelu = (xnn_univector_ukernel_function) xnn_f32_vlrelu_ukernel__wasmsimd_minmax_x8;
     } else {
       xnn_params.f32.lrelu = (xnn_univector_ukernel_function) xnn_f32_vlrelu_ukernel__wasmsimd_bitselect_x8;
     }
     xnn_params.f32.neg = (xnn_univector_ukernel_function) xnn_f32_vneg_ukernel__wasmsimd_x8;
-    xnn_params.f32.relu = (xnn_univector_ukernel_function) xnn_f32_relu_ukernel__wasmsimd_x16;
+    xnn_params.f32.relu = (xnn_univector_ukernel_function) xnn_f32_vrelu_ukernel__wasmsimd_x16;
     xnn_params.f32.rndne = (xnn_univector_ukernel_function) xnn_f32_vrndne_ukernel__wasmsimd_addsub_x8;
     if (is_wasm_x86) {
       xnn_params.f32.rndz = (xnn_univector_ukernel_function) xnn_f32_vrndz_ukernel__wasmsimd_addsub_x8;
@@ -2432,7 +2432,7 @@
     }
     xnn_params.f32.rndu = (xnn_univector_ukernel_function) xnn_f32_vrndu_ukernel__wasmsimd_addsub_x8;
     xnn_params.f32.rndd = (xnn_univector_ukernel_function) xnn_f32_vrndd_ukernel__wasmsimd_addsub_x8;
-    xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_sigmoid_ukernel__wasmsimd_p5_div_x16;
+    xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_vsigmoid_ukernel__wasmsimd_p5_div_x16;
     xnn_params.f32.sqr = (xnn_univector_ukernel_function) xnn_f32_vsqr_ukernel__wasmsimd_x8;
     xnn_params.f32.sqrt = (xnn_univector_ukernel_function) xnn_f32_vsqrt_ukernel__wasmsimd_sqrt_x8;
     if (is_wasm_x86) {
@@ -2727,7 +2727,7 @@
       .mr = 9,
       .qr = 8,
     };
-    xnn_params.u8.clamp = (xnn_univector_ukernel_function) xnn_u8_clamp_ukernel__scalar_x4;
+    xnn_params.u8.clamp = (xnn_univector_ukernel_function) xnn_u8_vclamp_ukernel__scalar_x4;
     xnn_params.u8.lut32norm = xnn_u8_lut32norm_ukernel__scalar;
     xnn_params.u8.rmax = xnn_u8_rmax_ukernel__scalar;
   #endif  // XNN_NO_U8_OPERATORS
@@ -2843,11 +2843,11 @@
       .channel_tile = 2,
     };
     xnn_params.f32.abs = (xnn_univector_ukernel_function) xnn_f32_vabs_ukernel__scalar_x4;
-    xnn_params.f32.clamp = (xnn_univector_ukernel_function) xnn_f32_clamp_ukernel__wasm_x4;
+    xnn_params.f32.clamp = (xnn_univector_ukernel_function) xnn_f32_vclamp_ukernel__wasm_x4;
     if (is_wasm_x86) {
-      xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_hswish_ukernel__scalar_x4;
+      xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_vhswish_ukernel__scalar_x4;
     } else {
-      xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_hswish_ukernel__wasm_x4;
+      xnn_params.f32.hswish = (xnn_univector_ukernel_function) xnn_f32_vhswish_ukernel__wasm_x4;
     }
     if (is_wasm_x86) {
       xnn_params.f32.elu = (xnn_univector_ukernel_function) xnn_f32_velu_ukernel__scalar_rr2_lut16_p3_x2;
@@ -2857,15 +2857,15 @@
     xnn_params.f32.lrelu = (xnn_univector_ukernel_function) xnn_f32_vlrelu_ukernel__scalar_x4;
     xnn_params.f32.neg = (xnn_univector_ukernel_function) xnn_f32_vneg_ukernel__scalar_x4;
     if (is_wasm_x86) {
-      xnn_params.f32.relu = (xnn_univector_ukernel_function) xnn_f32_relu_ukernel__scalar_x8;
+      xnn_params.f32.relu = (xnn_univector_ukernel_function) xnn_f32_vrelu_ukernel__scalar_x8;
     } else {
-      xnn_params.f32.relu = (xnn_univector_ukernel_function) xnn_f32_relu_ukernel__wasm_x8;
+      xnn_params.f32.relu = (xnn_univector_ukernel_function) xnn_f32_vrelu_ukernel__wasm_x8;
     }
     xnn_params.f32.rndne = (xnn_univector_ukernel_function) xnn_f32_vrndne_ukernel__scalar_libm_x4;
     xnn_params.f32.rndz  = (xnn_univector_ukernel_function) xnn_f32_vrndz_ukernel__scalar_libm_x4;
     xnn_params.f32.rndu  = (xnn_univector_ukernel_function) xnn_f32_vrndu_ukernel__scalar_libm_x4;
     xnn_params.f32.rndd  = (xnn_univector_ukernel_function) xnn_f32_vrndd_ukernel__scalar_libm_x4;
-    xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_sigmoid_ukernel__scalar_lut64_p2_div_x2;
+    xnn_params.f32.sigmoid = (xnn_univector_ukernel_function) xnn_f32_vsigmoid_ukernel__scalar_lut64_p2_div_x2;
     xnn_params.f32.sqr = (xnn_univector_ukernel_function) xnn_f32_vsqr_ukernel__scalar_x4;
     xnn_params.f32.sqrt = (xnn_univector_ukernel_function) xnn_f32_vsqrt_ukernel__scalar_sqrt_x1;
     if (is_wasm_x86) {
diff --git a/src/u8-clamp/neon-x64.c b/src/u8-vclamp/neon-x64.c
similarity index 97%
rename from src/u8-clamp/neon-x64.c
rename to src/u8-vclamp/neon-x64.c
index 1322b4a..62fab99 100644
--- a/src/u8-clamp/neon-x64.c
+++ b/src/u8-vclamp/neon-x64.c
@@ -13,7 +13,7 @@
 #include <xnnpack/clamp.h>
 
 
-void xnn_u8_clamp_ukernel__neon_x64(
+void xnn_u8_vclamp_ukernel__neon_x64(
     size_t n,
     const uint8_t* x,
     uint8_t* y,
diff --git a/src/u8-clamp/scalar-x4.c b/src/u8-vclamp/scalar-x4.c
similarity index 97%
rename from src/u8-clamp/scalar-x4.c
rename to src/u8-vclamp/scalar-x4.c
index b193a5b..99d0179 100644
--- a/src/u8-clamp/scalar-x4.c
+++ b/src/u8-vclamp/scalar-x4.c
@@ -8,7 +8,7 @@
 #include <xnnpack/clamp.h>
 
 
-void xnn_u8_clamp_ukernel__scalar_x4(
+void xnn_u8_vclamp_ukernel__scalar_x4(
     size_t n,
     const uint8_t* x,
     uint8_t* y,
diff --git a/src/u8-clamp/sse2-x64.c b/src/u8-vclamp/sse2-x64.c
similarity index 98%
rename from src/u8-clamp/sse2-x64.c
rename to src/u8-vclamp/sse2-x64.c
index a46ee0c..148f4f3 100644
--- a/src/u8-clamp/sse2-x64.c
+++ b/src/u8-vclamp/sse2-x64.c
@@ -13,7 +13,7 @@
 #include <xnnpack/clamp.h>
 
 
-void xnn_u8_clamp_ukernel__sse2_x64(
+void xnn_u8_vclamp_ukernel__sse2_x64(
     size_t n,
     const uint8_t* x,
     uint8_t* y,
diff --git a/src/xnnpack/clamp.h b/src/xnnpack/clamp.h
index b01bcf7..32ffd4c 100644
--- a/src/xnnpack/clamp.h
+++ b/src/xnnpack/clamp.h
@@ -19,53 +19,53 @@
 #endif
 
 
-#define DECLARE_F16_CLAMP_UKERNEL_FUNCTION(fn_name)   \
-  XNN_INTERNAL void fn_name(                          \
-      size_t n,                                       \
-      const void* x,                                  \
-      void* y,                                        \
+#define DECLARE_F16_VCLAMP_UKERNEL_FUNCTION(fn_name) \
+  XNN_INTERNAL void fn_name(                         \
+      size_t n,                                      \
+      const void* x,                                 \
+      void* y,                                       \
       const struct xnn_f16_minmax_params* params);
 
-DECLARE_F16_CLAMP_UKERNEL_FUNCTION(xnn_f16_clamp_ukernel__neonfp16arith_x8)
-DECLARE_F16_CLAMP_UKERNEL_FUNCTION(xnn_f16_clamp_ukernel__neonfp16arith_x16)
+DECLARE_F16_VCLAMP_UKERNEL_FUNCTION(xnn_f16_vclamp_ukernel__neonfp16arith_x8)
+DECLARE_F16_VCLAMP_UKERNEL_FUNCTION(xnn_f16_vclamp_ukernel__neonfp16arith_x16)
 
-#define DECLARE_F32_CLAMP_UKERNEL_FUNCTION(fn_name)   \
-  XNN_INTERNAL void fn_name(                          \
-      size_t n,                                       \
-      const float* x,                                 \
-      float* y,                                       \
+#define DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(fn_name) \
+  XNN_INTERNAL void fn_name(                         \
+      size_t n,                                      \
+      const float* x,                                \
+      float* y,                                      \
       const union xnn_f32_minmax_params* params);
 
-DECLARE_F32_CLAMP_UKERNEL_FUNCTION(xnn_f32_clamp_ukernel__neon_x4)
-DECLARE_F32_CLAMP_UKERNEL_FUNCTION(xnn_f32_clamp_ukernel__neon_x8)
-DECLARE_F32_CLAMP_UKERNEL_FUNCTION(xnn_f32_clamp_ukernel__sse_x4)
-DECLARE_F32_CLAMP_UKERNEL_FUNCTION(xnn_f32_clamp_ukernel__sse_x8)
-DECLARE_F32_CLAMP_UKERNEL_FUNCTION(xnn_f32_clamp_ukernel__avx_x8)
-DECLARE_F32_CLAMP_UKERNEL_FUNCTION(xnn_f32_clamp_ukernel__avx_x16)
-DECLARE_F32_CLAMP_UKERNEL_FUNCTION(xnn_f32_clamp_ukernel__avx512f_x16)
-DECLARE_F32_CLAMP_UKERNEL_FUNCTION(xnn_f32_clamp_ukernel__avx512f_x32)
-DECLARE_F32_CLAMP_UKERNEL_FUNCTION(xnn_f32_clamp_ukernel__wasmsimd_arm_x4)
-DECLARE_F32_CLAMP_UKERNEL_FUNCTION(xnn_f32_clamp_ukernel__wasmsimd_arm_x8)
-DECLARE_F32_CLAMP_UKERNEL_FUNCTION(xnn_f32_clamp_ukernel__wasmsimd_x86_x4)
-DECLARE_F32_CLAMP_UKERNEL_FUNCTION(xnn_f32_clamp_ukernel__wasmsimd_x86_x8)
-DECLARE_F32_CLAMP_UKERNEL_FUNCTION(xnn_f32_clamp_ukernel__wasm_x1)
-DECLARE_F32_CLAMP_UKERNEL_FUNCTION(xnn_f32_clamp_ukernel__wasm_x2)
-DECLARE_F32_CLAMP_UKERNEL_FUNCTION(xnn_f32_clamp_ukernel__wasm_x4)
-DECLARE_F32_CLAMP_UKERNEL_FUNCTION(xnn_f32_clamp_ukernel__scalar_x1)
-DECLARE_F32_CLAMP_UKERNEL_FUNCTION(xnn_f32_clamp_ukernel__scalar_x2)
-DECLARE_F32_CLAMP_UKERNEL_FUNCTION(xnn_f32_clamp_ukernel__scalar_x4)
+DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(xnn_f32_vclamp_ukernel__neon_x4)
+DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(xnn_f32_vclamp_ukernel__neon_x8)
+DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(xnn_f32_vclamp_ukernel__sse_x4)
+DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(xnn_f32_vclamp_ukernel__sse_x8)
+DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(xnn_f32_vclamp_ukernel__avx_x8)
+DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(xnn_f32_vclamp_ukernel__avx_x16)
+DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(xnn_f32_vclamp_ukernel__avx512f_x16)
+DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(xnn_f32_vclamp_ukernel__avx512f_x32)
+DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(xnn_f32_vclamp_ukernel__wasmsimd_arm_x4)
+DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(xnn_f32_vclamp_ukernel__wasmsimd_arm_x8)
+DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(xnn_f32_vclamp_ukernel__wasmsimd_x86_x4)
+DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(xnn_f32_vclamp_ukernel__wasmsimd_x86_x8)
+DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(xnn_f32_vclamp_ukernel__wasm_x1)
+DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(xnn_f32_vclamp_ukernel__wasm_x2)
+DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(xnn_f32_vclamp_ukernel__wasm_x4)
+DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(xnn_f32_vclamp_ukernel__scalar_x1)
+DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(xnn_f32_vclamp_ukernel__scalar_x2)
+DECLARE_F32_VCLAMP_UKERNEL_FUNCTION(xnn_f32_vclamp_ukernel__scalar_x4)
 
 
-#define DECLARE_U8_CLAMP_UKERNEL_FUNCTION(fn_name) \
-  XNN_INTERNAL void fn_name(                       \
-      size_t n,                                    \
-      const uint8_t* x,                            \
-      uint8_t* y,                                  \
+#define DECLARE_U8_VCLAMP_UKERNEL_FUNCTION(fn_name) \
+  XNN_INTERNAL void fn_name(                        \
+      size_t n,                                     \
+      const uint8_t* x,                             \
+      uint8_t* y,                                   \
       const union xnn_u8_minmax_params* params);
 
-DECLARE_U8_CLAMP_UKERNEL_FUNCTION(xnn_u8_clamp_ukernel__neon_x64)
-DECLARE_U8_CLAMP_UKERNEL_FUNCTION(xnn_u8_clamp_ukernel__sse2_x64)
-DECLARE_U8_CLAMP_UKERNEL_FUNCTION(xnn_u8_clamp_ukernel__scalar_x4)
+DECLARE_U8_VCLAMP_UKERNEL_FUNCTION(xnn_u8_vclamp_ukernel__neon_x64)
+DECLARE_U8_VCLAMP_UKERNEL_FUNCTION(xnn_u8_vclamp_ukernel__sse2_x64)
+DECLARE_U8_VCLAMP_UKERNEL_FUNCTION(xnn_u8_vclamp_ukernel__scalar_x4)
 
 
 #ifdef __cplusplus
diff --git a/src/xnnpack/hswish.h b/src/xnnpack/hswish.h
index d5ac3ca..f980a5b 100644
--- a/src/xnnpack/hswish.h
+++ b/src/xnnpack/hswish.h
@@ -16,50 +16,50 @@
 #endif
 
 
-#define DECLARE_F16_HSWISH_UKERNEL_FUNCTION(fn_name) \
-  XNN_INTERNAL void fn_name(                         \
-      size_t n,                                      \
-      const void* x,                                 \
-      void* y,                                       \
+#define DECLARE_F16_VHSWISH_UKERNEL_FUNCTION(fn_name) \
+  XNN_INTERNAL void fn_name(                          \
+      size_t n,                                       \
+      const void* x,                                  \
+      void* y,                                        \
       const struct xnn_f16_hswish_params* params);
 
-DECLARE_F16_HSWISH_UKERNEL_FUNCTION(xnn_f16_hswish_ukernel__neonfp16arith_x8)
-DECLARE_F16_HSWISH_UKERNEL_FUNCTION(xnn_f16_hswish_ukernel__neonfp16arith_x16)
+DECLARE_F16_VHSWISH_UKERNEL_FUNCTION(xnn_f16_vhswish_ukernel__neonfp16arith_x8)
+DECLARE_F16_VHSWISH_UKERNEL_FUNCTION(xnn_f16_vhswish_ukernel__neonfp16arith_x16)
 
-#define DECLARE_F32_HSWISH_UKERNEL_FUNCTION(fn_name) \
-  XNN_INTERNAL void fn_name(                         \
-      size_t n,                                      \
-      const float* x,                                \
-      float* y,                                      \
+#define DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(fn_name) \
+  XNN_INTERNAL void fn_name(                          \
+      size_t n,                                       \
+      const float* x,                                 \
+      float* y,                                       \
       const union xnn_f32_hswish_params* params);
 
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__neon_x4)
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__neon_x8)
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__neon_x16)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__neon_x4)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__neon_x8)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__neon_x16)
 
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__sse_x4)
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__sse_x8)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__sse_x4)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__sse_x8)
 
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__avx_x8)
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__avx_x16)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__avx_x8)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__avx_x16)
 
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__fma3_x8)
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__fma3_x16)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__fma3_x8)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__fma3_x16)
 
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__avx512f_x16)
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__avx512f_x32)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__avx512f_x16)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__avx512f_x32)
 
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__wasmsimd_x4)
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__wasmsimd_x8)
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__wasmsimd_x16)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__wasmsimd_x4)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__wasmsimd_x8)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__wasmsimd_x16)
 
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__wasm_x1)
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__wasm_x2)
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__wasm_x4)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__wasm_x1)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__wasm_x2)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__wasm_x4)
 
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__scalar_x1)
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__scalar_x2)
-DECLARE_F32_HSWISH_UKERNEL_FUNCTION(xnn_f32_hswish_ukernel__scalar_x4)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__scalar_x1)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__scalar_x2)
+DECLARE_F32_VHSWISH_UKERNEL_FUNCTION(xnn_f32_vhswish_ukernel__scalar_x4)
 
 
 #ifdef __cplusplus
diff --git a/src/xnnpack/params.h b/src/xnnpack/params.h
index 18fdf53..948e673 100644
--- a/src/xnnpack/params.h
+++ b/src/xnnpack/params.h
@@ -1507,25 +1507,25 @@
     uint8_t* y,
     const union xnn_u8_minmax_params* params);
 
-typedef void (*xnn_f16_relu_ukernel_function)(
+typedef void (*xnn_f16_vrelu_ukernel_function)(
     size_t n,
     const void* x,
     void* y,
     const struct xnn_f16_relu_params* params);
 
-typedef void (*xnn_f32_relu_ukernel_function)(
+typedef void (*xnn_f32_vrelu_ukernel_function)(
     size_t n,
     const float* x,
     float* y,
     const union xnn_f32_relu_params* params);
 
-typedef void (*xnn_f16_hswish_ukernel_function)(
+typedef void (*xnn_f16_vhswish_ukernel_function)(
     size_t n,
     const void* x,
     void* y,
     const struct xnn_f16_hswish_params* params);
 
-typedef void (*xnn_f32_hswish_ukernel_function)(
+typedef void (*xnn_f32_vhswish_ukernel_function)(
     size_t n,
     const float* x,
     float* y,
diff --git a/src/xnnpack/vunary.h b/src/xnnpack/vunary.h
index 2daf409..489fa41 100644
--- a/src/xnnpack/vunary.h
+++ b/src/xnnpack/vunary.h
@@ -23,275 +23,275 @@
       float* y,                                      \
       const void* params);
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_div_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_div_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_div_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_div_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_div_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_div_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_div_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_div_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_div_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_div_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_div_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_div_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2fma_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2fma_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2fma_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2fma_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2fma_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2fma_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2fma_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2fma_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2fma_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2fma_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2fma_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2fma_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr1recps1fma_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2recps_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2recps_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2recps_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2recps_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2recps_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_p5_nr2recps_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2recps_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2recps_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2recps_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2recps_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2recps_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_p5_nr2recps_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_rr2_p5_nr2recps_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_rr2_p5_nr2recps_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_rr2_p5_nr2recps_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_rr2_p5_nr2recps_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_rr2_p5_nr2recps_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_rr2_p5_nr2recps_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_rr2_p5_nr2recps_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_rr2_p5_nr2recps_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_rr2_p5_nr2recps_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_rr2_p5_nr2recps_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_rr2_p5_nr2recps_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_rr2_p5_nr2recps_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_div_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_div_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_div_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_div_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_div_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_div_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_div_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_div_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_div_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_div_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_div_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_div_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2fma_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr1recps1fma_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut64_p2_nr2recps_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_rr2_lut64_p2_nr2recps_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_div_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2fma_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr1recps1fma_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neonfma_rr1_lut2048_p1_nr2recps_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_rr2_lut2048_p1_nr2recps_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__neon_frac_p9_p10_nr1recps_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__neon_frac_p9_p10_nr1recps_x16)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse2_p5_div_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse2_p5_div_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse2_p5_div_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse2_p5_div_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse2_p5_div_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse2_p5_div_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse2_p5_div_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse2_p5_div_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse2_p5_div_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse2_p5_div_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse2_p5_div_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse2_p5_div_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse41_p5_div_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse41_p5_div_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse41_p5_div_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse41_p5_div_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse41_p5_div_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse41_p5_div_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse41_p5_div_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse41_p5_div_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse41_p5_div_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse41_p5_div_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse41_p5_div_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse41_p5_div_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse2_lut64_p2_div_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse2_lut64_p2_div_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse2_lut64_p2_div_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse2_lut64_p2_div_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse2_lut64_p2_div_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse2_lut64_p2_div_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse2_lut64_p2_div_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse2_lut64_p2_div_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse2_lut64_p2_div_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse2_lut64_p2_div_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse2_lut64_p2_div_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse2_lut64_p2_div_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse41_lut64_p2_div_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse41_lut64_p2_div_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse41_lut64_p2_div_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse41_lut64_p2_div_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse41_lut64_p2_div_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__sse41_lut64_p2_div_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse41_lut64_p2_div_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse41_lut64_p2_div_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse41_lut64_p2_div_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse41_lut64_p2_div_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse41_lut64_p2_div_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__sse41_lut64_p2_div_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x24)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x32)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x40)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x48)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x56)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x64)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x72)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_div_x80)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x32)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x40)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x48)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x56)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x64)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x72)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_div_x80)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x24)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x32)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x40)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x48)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x56)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x64)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x72)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx_rr2_p5_nr2_x80)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x32)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x40)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x48)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x56)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x64)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x72)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx_rr2_p5_nr2_x80)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x24)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x32)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x40)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x48)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x56)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x64)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x72)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_div_x80)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x32)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x40)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x48)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x56)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x64)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x72)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_div_x80)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x24)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x32)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x40)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x48)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x56)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x64)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x72)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr1fma_x80)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x32)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x40)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x48)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x56)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x64)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x72)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr1fma_x80)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x24)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x32)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x40)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x48)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x56)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x64)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x72)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx2_rr1_p5_nr2fma_x80)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x32)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x40)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x48)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x56)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x64)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x72)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx2_rr1_p5_nr2fma_x80)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_div_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_div_x32)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_div_x48)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_div_x64)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_div_x80)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_div_x96)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_div_x112)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_div_x128)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_div_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_div_x32)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_div_x48)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_div_x64)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_div_x80)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_div_x96)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_div_x112)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_div_x128)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x32)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x48)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x64)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x80)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x96)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x112)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x128)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x32)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x48)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x64)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x80)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x96)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x112)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_p5_scalef_nr1fma_x128)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x32)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x48)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x64)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x80)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x96)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x112)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x128)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x32)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x48)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x64)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x80)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x96)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x112)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_div_x128)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x32)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x48)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x64)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x80)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x96)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x112)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x128)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x32)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x48)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x64)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x80)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x96)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x112)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr1_lut16_p3_perm_scalef_nr1fma_x128)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x32)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x48)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x64)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x80)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x96)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x112)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x128)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x32)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x48)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x64)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x80)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x96)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x112)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_div_x128)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x32)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x48)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x64)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x80)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x96)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x112)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x128)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x32)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x48)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x64)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x80)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x96)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x112)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__avx512f_rr2_lut32_p2_perm2_scalef_nr1fma_x128)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__wasmsimd_p5_div_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__wasmsimd_p5_div_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__wasmsimd_p5_div_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__wasmsimd_p5_div_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__wasmsimd_p5_div_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__wasmsimd_p5_div_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__wasmsimd_p5_div_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__wasmsimd_p5_div_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__wasmsimd_p5_div_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__wasmsimd_p5_div_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__wasmsimd_p5_div_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__wasmsimd_p5_div_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__wasmsimd_lut64_p2_div_x4)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__wasmsimd_lut64_p2_div_x8)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__wasmsimd_lut64_p2_div_x12)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__wasmsimd_lut64_p2_div_x16)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__wasmsimd_lut64_p2_div_x20)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__wasmsimd_lut64_p2_div_x24)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__wasmsimd_lut64_p2_div_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__wasmsimd_lut64_p2_div_x8)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__wasmsimd_lut64_p2_div_x12)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__wasmsimd_lut64_p2_div_x16)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__wasmsimd_lut64_p2_div_x20)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__wasmsimd_lut64_p2_div_x24)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__scalar_lut2048_p1_div_x1)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__scalar_lut2048_p1_div_x2)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__scalar_lut2048_p1_div_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__scalar_lut2048_p1_div_x1)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__scalar_lut2048_p1_div_x2)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__scalar_lut2048_p1_div_x4)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__scalar_lut64_p2_div_x1)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__scalar_lut64_p2_div_x2)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__scalar_lut64_p2_div_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__scalar_lut64_p2_div_x1)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__scalar_lut64_p2_div_x2)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__scalar_lut64_p2_div_x4)
 
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__scalar_p5_div_x1)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__scalar_p5_div_x2)
-DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_sigmoid_ukernel__scalar_p5_div_x4)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__scalar_p5_div_x1)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__scalar_p5_div_x2)
+DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsigmoid_ukernel__scalar_p5_div_x4)
 
 DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsqr_ukernel__neon_x4)
 DECLARE_F32_VUNARY_UKERNEL_FUNCTION(xnn_f32_vsqr_ukernel__neon_x8)
@@ -762,45 +762,45 @@
 DECLARE_F32_VRND_UKERNEL_FUNCTION(xnn_f32_vrndd_ukernel__scalar_libm_x2)
 DECLARE_F32_VRND_UKERNEL_FUNCTION(xnn_f32_vrndd_ukernel__scalar_libm_x4)
 
-#define DECLARE_F16_RELU_UKERNEL_FUNCTION(fn_name) \
-  XNN_INTERNAL void fn_name(                       \
-      size_t n,                                    \
-      const void* x,                               \
-      void* y,                                     \
+#define DECLARE_F16_VRELU_UKERNEL_FUNCTION(fn_name) \
+  XNN_INTERNAL void fn_name(                        \
+      size_t n,                                     \
+      const void* x,                                \
+      void* y,                                      \
       const struct xnn_f16_relu_params* params);
 
-DECLARE_F16_RELU_UKERNEL_FUNCTION(xnn_f16_relu_ukernel__neonfp16arith_x8)
-DECLARE_F16_RELU_UKERNEL_FUNCTION(xnn_f16_relu_ukernel__neonfp16arith_x16)
+DECLARE_F16_VRELU_UKERNEL_FUNCTION(xnn_f16_vrelu_ukernel__neonfp16arith_x8)
+DECLARE_F16_VRELU_UKERNEL_FUNCTION(xnn_f16_vrelu_ukernel__neonfp16arith_x16)
 
-#define DECLARE_F32_RELU_UKERNEL_FUNCTION(fn_name) \
-  XNN_INTERNAL void fn_name(                       \
-      size_t n,                                    \
-      const float* x,                              \
-      float* y,                                    \
+#define DECLARE_F32_VRELU_UKERNEL_FUNCTION(fn_name) \
+  XNN_INTERNAL void fn_name(                        \
+      size_t n,                                     \
+      const float* x,                               \
+      float* y,                                     \
       const union xnn_f32_relu_params* params);
 
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__neon_x4)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__neon_x8)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__sse_x4)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__sse_x8)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__avx_x8)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__avx_x16)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__avx512f_x16)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__avx512f_x32)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__scalar_x1)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__scalar_x2)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__scalar_x4)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__scalar_x8)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__wasmsimd_x4)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__wasmsimd_x8)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__wasmsimd_x16)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__wasm_x1)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__wasm_x2)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__wasm_x4)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__wasm_x8)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__wasm32_shr_x1)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__wasm32_shr_x2)
-DECLARE_F32_RELU_UKERNEL_FUNCTION(xnn_f32_relu_ukernel__wasm32_shr_x4)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__neon_x4)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__neon_x8)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__sse_x4)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__sse_x8)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__avx_x8)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__avx_x16)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__avx512f_x16)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__avx512f_x32)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__scalar_x1)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__scalar_x2)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__scalar_x4)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__scalar_x8)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__wasmsimd_x4)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__wasmsimd_x8)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__wasmsimd_x16)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__wasm_x1)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__wasm_x2)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__wasm_x4)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__wasm_x8)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__wasm32_shr_x1)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__wasm32_shr_x2)
+DECLARE_F32_VRELU_UKERNEL_FUNCTION(xnn_f32_vrelu_ukernel__wasm32_shr_x4)
 
 #define DECLARE_XX_VUNARY_UKERNEL_FUNCTION(fn_name) \
   XNN_INTERNAL void fn_name(                        \