commit 18630de490a8b6840080e9bd621e556be096a51c
author Marat Dukhan <maratek@google.com> Wed Jun 02 22:20:01 2021 -0700
committer XNNPACK Team <xnnpack-github-robot@google.com> Wed Jun 02 22:20:47 2021 -0700
tree e498f8db4bd26c18b712a7e9586d93a0b6d90355
parent 801d2c2d7e3576b368d2f841b357adebc8ac1527

QS8 NEONDOT GEMM/IGEMM microkernels with FP32 requantization

PiperOrigin-RevId: 377216784

CMakeLists.txt

diff --git a/CMakeLists.txt b/CMakeLists.txt
index 03b56c8..f1c0b80 100755
--- a/CMakeLists.txt
+++ b/CMakeLists.txt
@@ -1577,22 +1577,38 @@
   src/f16-vrelu/gen/vrelu-neonfp16arith-x16.c)
 
 SET(XNNPACK_NEONDOT_MICROKERNEL_SRCS
-  src/qs8-gemm/gen/1x8c4-minmax-gemmlowp-neondot.c
+  src/qs8-gemm/gen/1x16c4-minmax-fp32-neondot.c
   src/qs8-gemm/gen/1x16c4-minmax-gemmlowp-neondot.c
-  src/qs8-gemm/gen/4x8c4-minmax-gemmlowp-neondot.c
+  src/qs8-gemm/gen/1x8c4-minmax-fp32-neondot.c
+  src/qs8-gemm/gen/1x8c4-minmax-gemmlowp-neondot.c
+  src/qs8-gemm/gen/4x16c4-minmax-fp32-neondot.c
   src/qs8-gemm/gen/4x16c4-minmax-gemmlowp-neondot.c
-  src/qs8-gemm/gen/6x8c4-minmax-gemmlowp-neondot.c
+  src/qs8-gemm/gen/4x8c4-minmax-fp32-neondot.c
+  src/qs8-gemm/gen/4x8c4-minmax-gemmlowp-neondot.c
+  src/qs8-gemm/gen/6x16c4-minmax-fp32-neondot.c
   src/qs8-gemm/gen/6x16c4-minmax-gemmlowp-neondot.c
-  src/qs8-gemm/gen/8x8c4-minmax-gemmlowp-neondot.c
+  src/qs8-gemm/gen/6x8c4-minmax-fp32-neondot.c
+  src/qs8-gemm/gen/6x8c4-minmax-gemmlowp-neondot.c
+  src/qs8-gemm/gen/8x16c4-minmax-fp32-neondot.c
   src/qs8-gemm/gen/8x16c4-minmax-gemmlowp-neondot.c
-  src/qs8-igemm/gen/1x8c4-minmax-gemmlowp-neondot.c
+  src/qs8-gemm/gen/8x8c4-minmax-fp32-neondot.c
+  src/qs8-gemm/gen/8x8c4-minmax-gemmlowp-neondot.c
+  src/qs8-igemm/gen/1x16c4-minmax-fp32-neondot.c
   src/qs8-igemm/gen/1x16c4-minmax-gemmlowp-neondot.c
-  src/qs8-igemm/gen/4x8c4-minmax-gemmlowp-neondot.c
+  src/qs8-igemm/gen/1x8c4-minmax-fp32-neondot.c
+  src/qs8-igemm/gen/1x8c4-minmax-gemmlowp-neondot.c
+  src/qs8-igemm/gen/4x16c4-minmax-fp32-neondot.c
   src/qs8-igemm/gen/4x16c4-minmax-gemmlowp-neondot.c
-  src/qs8-igemm/gen/6x8c4-minmax-gemmlowp-neondot.c
+  src/qs8-igemm/gen/4x8c4-minmax-fp32-neondot.c
+  src/qs8-igemm/gen/4x8c4-minmax-gemmlowp-neondot.c
+  src/qs8-igemm/gen/6x16c4-minmax-fp32-neondot.c
   src/qs8-igemm/gen/6x16c4-minmax-gemmlowp-neondot.c
-  src/qs8-igemm/gen/8x8c4-minmax-gemmlowp-neondot.c
-  src/qs8-igemm/gen/8x16c4-minmax-gemmlowp-neondot.c)
+  src/qs8-igemm/gen/6x8c4-minmax-fp32-neondot.c
+  src/qs8-igemm/gen/6x8c4-minmax-gemmlowp-neondot.c
+  src/qs8-igemm/gen/8x16c4-minmax-fp32-neondot.c
+  src/qs8-igemm/gen/8x16c4-minmax-gemmlowp-neondot.c
+  src/qs8-igemm/gen/8x8c4-minmax-fp32-neondot.c
+  src/qs8-igemm/gen/8x8c4-minmax-gemmlowp-neondot.c)
 
 SET(XNNPACK_SSE_MICROKERNEL_SRCS
   src/f32-avgpool/9p8x-minmax-sse-c4.c