diff options
| author | Renato Arantes <renato.arantes@arm.com> | 2024-01-26 17:31:18 +0000 |
|---|---|---|
| committer | Renato Barros Arantes <renato.arantes@arm.com> | 2024-03-21 11:15:30 +0000 |
| commit | 36a75dafdbe6d6a3a6f50bd075fe01f5b7dace38 (patch) | |
| tree | 0701d615ef30444b9d0789db691b59b81fd9e86e /src/core/NEON/kernels/arm_gemm/mergeresults.cpp | |
| parent | d2191150736dde66d79eb97e0c8ee506eef3c8fc (diff) | |
| download | ComputeLibrary-36a75dafdbe6d6a3a6f50bd075fe01f5b7dace38.tar.gz | |
[ONCPUML-1451] Add matmul kernel to enable bf16 to bf16 operations via PyTorch® autocast() function
The full range of tests must be added with [MLINFSW-482] epic due to the lack of reordering kernels implemented in Acl.
Co-Authored-By: David Mansell <David.Mansell@arm.com>
Change-Id: I820d316295a1ec94fdc89c37e4144a268f914c36
Signed-off-by: Renato Arantes <renato.arantes@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/11169
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/NEON/kernels/arm_gemm/mergeresults.cpp')
| -rw-r--r-- | src/core/NEON/kernels/arm_gemm/mergeresults.cpp | 7 |
1 files changed, 6 insertions, 1 deletions
diff --git a/src/core/NEON/kernels/arm_gemm/mergeresults.cpp b/src/core/NEON/kernels/arm_gemm/mergeresults.cpp index 2b712cee61..e100d9fe46 100644 --- a/src/core/NEON/kernels/arm_gemm/mergeresults.cpp +++ b/src/core/NEON/kernels/arm_gemm/mergeresults.cpp @@ -1,5 +1,5 @@ /* - * Copyright (c) 2017-2021 Arm Limited. + * Copyright (c) 2017-2021, 2024 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -30,6 +30,7 @@ #include "arm_gemm.hpp" #include "asmlib.hpp" +#include "bfloat.hpp" #include "utils.hpp" namespace arm_gemm { @@ -114,4 +115,8 @@ template void MergeResults<12u, 8u, false, float, __fp16>(__fp16*, float const*, template void MergeResults<8u, 6u, false, float, __fp16>(__fp16*, float const*, int, int, int, int, int, __fp16 const*, Activation, bool); #endif +#if defined(__arm__) && defined(ARM_COMPUTE_ENABLE_BF16) +template void MergeResults<8u, 6u, false, float, bfloat16>(bfloat16*, float const*, int, int, int, int, int, bfloat16 const*, Activation, bool); +#endif + } // namespace arm_gemm |