F32-RELU unrolled more for improved performance on Web Assembly

PiperOrigin-RevId: 328788618
diff --git a/BUILD.bazel b/BUILD.bazel
index 4380a88..29b14d7 100644
--- a/BUILD.bazel
+++ b/BUILD.bazel
@@ -216,6 +216,7 @@
     "src/f32-relu/gen/scalar-x1.c",
     "src/f32-relu/gen/scalar-x2.c",
     "src/f32-relu/gen/scalar-x4.c",
+    "src/f32-relu/gen/scalar-x8.c",
     "src/f32-sigmoid/gen/scalar-lut2048-p1-div-x1.c",
     "src/f32-sigmoid/gen/scalar-lut2048-p1-div-x2.c",
     "src/f32-sigmoid/gen/scalar-lut2048-p1-div-x4.c",
@@ -505,6 +506,7 @@
     "src/f32-relu/gen/wasm-x1.c",
     "src/f32-relu/gen/wasm-x2.c",
     "src/f32-relu/gen/wasm-x4.c",
+    "src/f32-relu/gen/wasm-x8.c",
     "src/f32-vbinary/gen/vadd-minmax-wasm-x1.c",
     "src/f32-vbinary/gen/vadd-minmax-wasm-x2.c",
     "src/f32-vbinary/gen/vadd-minmax-wasm-x4.c",
@@ -788,6 +790,7 @@
     "src/f32-raddstoreexpminusmax/gen/wasmsimd-p5-x20-acc5.c",
     "src/f32-relu/gen/wasmsimd-x4.c",
     "src/f32-relu/gen/wasmsimd-x8.c",
+    "src/f32-relu/gen/wasmsimd-x16.c",
     "src/f32-rmax/wasmsimd-arm.c",
     "src/f32-rmax/wasmsimd-x86.c",
     "src/f32-sigmoid/gen/wasmsimd-p5-div-x4.c",