QS8 NEONDOT GEMM/IGEMM microkernels with FP32 requantization
PiperOrigin-RevId: 377216784
diff --git a/BUILD.bazel b/BUILD.bazel
index 3c9d7b0..747e8d3 100644
--- a/BUILD.bazel
+++ b/BUILD.bazel
@@ -2335,22 +2335,38 @@
]
NEONDOT_UKERNELS = [
- "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/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",
]
SSE_UKERNELS = [