diff options
author | Georgios Pinitas <georgios.pinitas@arm.com> | 2020-03-06 18:12:09 +0000 |
---|---|---|
committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2020-03-12 12:12:30 +0000 |
commit | c7b183ab741650653289f8ce3bdeb4926521fdbd (patch) | |
tree | 991e9f20340c91c288d52d8f9a64a3729e4a40b0 /src/core/NEON/kernels/arm_gemm/gemm_fp32.cpp | |
parent | 6800117df3be825f0ec5c6cc71c4377322f51b99 (diff) | |
download | ComputeLibrary-c7b183ab741650653289f8ce3bdeb4926521fdbd.tar.gz |
COMPMID-3160: Add Bfloat16 support in NEGEMMConvolutionLayer
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I0e449306c138a562ffc1455e76ec44b2fd059d85
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2860
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/NEON/kernels/arm_gemm/gemm_fp32.cpp')
-rw-r--r-- | src/core/NEON/kernels/arm_gemm/gemm_fp32.cpp | 10 |
1 files changed, 9 insertions, 1 deletions
diff --git a/src/core/NEON/kernels/arm_gemm/gemm_fp32.cpp b/src/core/NEON/kernels/arm_gemm/gemm_fp32.cpp index 35493a609c..96e3ce832c 100644 --- a/src/core/NEON/kernels/arm_gemm/gemm_fp32.cpp +++ b/src/core/NEON/kernels/arm_gemm/gemm_fp32.cpp @@ -44,6 +44,7 @@ #include "kernels/sve_hybrid_fp32_mla_4VLx4.hpp" #include "kernels/sve_interleaved_fp32_mla_3VLx8.hpp" #include "kernels/sve_native_fp32_mla_4VLx4.hpp" +#include "kernels/sve_smallK_hybrid_fp32_mla_1VLx8.hpp" namespace arm_gemm { @@ -73,7 +74,14 @@ static const GemmImplementation<float, float> gemm_fp32_methods[] = }, #ifdef __ARM_FEATURE_SVE -// SVE native / hybrid methods +// SVE smallk / native / hybrid methods +{ + GemmMethod::GEMM_HYBRID, + "smallK_hybrid_fp32_mla_1VLx8", + [](const GemmArgs &args) { return (args._Ksize <= 24) && !args._trA && args._pretransposed_hint; }, + nullptr, + [](const GemmArgs &args) { return new GemmHybrid<smallK_hybrid_fp32_mla_1VLx8, float, float>(args); } +}, { GemmMethod::GEMM_HYBRID, "hybrid_fp32_mla_4VLx4", |