diff options
| author | Gunes Bayir <gunes.bayir@arm.com> | 2021-12-10 16:17:56 +0000 |
|---|---|---|
| committer | Gunes Bayir <gunes.bayir@arm.com> | 2022-07-13 14:47:44 +0000 |
| commit | 4bfc70e31766587c951204c93a127a486e007d0c (patch) | |
| tree | 198b2150c43b14c571c100b8dfa0d3aaa4c968d0 /filelist.json | |
| parent | 29cab36ddd73c174bf6b2de453663aa49c1cc576 (diff) | |
| download | ComputeLibrary-4bfc70e31766587c951204c93a127a486e007d0c.tar.gz | |
Add Gemm MMUL Reshaped Only Rhs Support for FP32/FP16
This patch introduces a GEMM routine that is optimized for Arm(R) Mali(TM)-G715 and Arm(R) Mali(TM)-G615
Resolves: COMPMID-5216
Signed-off-by: Gunes Bayir <gunes.bayir@arm.com>
Change-Id: I2e5d7806f5904347185bb3e250f73d73d6669dba
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/7914
Reviewed-by: SiCong Li <sicong.li@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'filelist.json')
| -rw-r--r-- | filelist.json | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/filelist.json b/filelist.json index ab2cc83a84..513a2207c1 100644 --- a/filelist.json +++ b/filelist.json @@ -479,6 +479,7 @@ "src/gpu/cl/kernels/ClGemmLowpQuantizeDownInt32ScaleByFloatKernel.cpp", "src/gpu/cl/kernels/ClGemmLowpQuantizeDownInt32ScaleKernel.cpp", "src/gpu/cl/kernels/ClGemmMatrixMultiplyNativeKernel.cpp", + "src/gpu/cl/kernels/ClGemmMatrixMultiplyReshapedOnlyRhsMMULKernel.cpp", "src/gpu/cl/kernels/ClGemmMatrixMultiplyReshapedKernel.cpp", "src/gpu/cl/kernels/ClGemmMatrixMultiplyReshapedOnlyRhsKernel.cpp", "src/gpu/cl/kernels/ClGemmReshapeLhsMatrixKernel.cpp", |