diff options
| author | Ramy Elgammal <ramy.elgammal@arm.com> | 2023-03-09 21:15:37 +0000 |
|---|---|---|
| committer | Gunes Bayir <gunes.bayir@arm.com> | 2023-03-17 11:00:57 +0000 |
| commit | 2b6ebfe4270b06b09e45f306e8384950aeca7e4e (patch) | |
| tree | 44a65551aa32352a57090bf550b96cbf5b54222f /src/gpu/cl/ClKernelLibrary.cpp | |
| parent | 40aab11ff88ed432d5028478e531f8d0fc404d4c (diff) | |
| download | ComputeLibrary-2b6ebfe4270b06b09e45f306e8384950aeca7e4e.tar.gz | |
Implement OpenCL MatMul for Lhs NT Rhs T/NT FP32/16
- Implement ClNativeMatMulKernel class
- Implement opencl kernel for LHS non-transposed and RHS non-transposed
- Implement opencl kernel for LHS non-transposed and RHS transposed
- Add test fixture and dataset for matmul
- Implement transpose_tensor() for reference implementation to transpose high dimensional tensors
Resolves: COMPMID-5944, COMPMID-5951
Co-authored-by: Gunes Bayir <gunes.bayir@arm.com>
Co-authored-by: Ramy Elgammal <ramy.elgammal@arm.com>
Change-Id: I1d5b8978f41be27baddb3153ade880472141573f
Signed-off-by: Gunes Bayir <gunes.bayir@arm.com>
Signed-off-by: Ramy Elgammal <ramy.elgammal@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9333
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/gpu/cl/ClKernelLibrary.cpp')
| -rw-r--r-- | src/gpu/cl/ClKernelLibrary.cpp | 8 |
1 files changed, 7 insertions, 1 deletions
diff --git a/src/gpu/cl/ClKernelLibrary.cpp b/src/gpu/cl/ClKernelLibrary.cpp index f788bedc34..482e8c341d 100644 --- a/src/gpu/cl/ClKernelLibrary.cpp +++ b/src/gpu/cl/ClKernelLibrary.cpp @@ -1,5 +1,5 @@ /* - * Copyright (c) 2016-2022 Arm Limited. + * Copyright (c) 2016-2023 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -358,6 +358,8 @@ const std::map<std::string, std::string> ClKernelLibrary::_kernel_program_map = { "strided_slice", "common/slice_ops.cl" }, { "tile", "common/tile.cl" }, { "transpose", "common/transpose.cl" }, + { "mat_mul_native_nt_nt", "common/mat_mul.cl" }, + { "mat_mul_native_nt_t", "common/mat_mul.cl" }, #ifdef ENABLE_NCHW_KERNELS { "batch_to_space_nchw", "nchw/batch_to_space.cl" }, { "batch_to_space_static_nchw", "nchw/batch_to_space.cl" }, @@ -781,6 +783,10 @@ const std::map<std::string, std::string> ClKernelLibrary::_program_source_map = "common/unpooling_layer.cl", #include "./cl_kernels/common/unpooling_layer.clembed" }, + { + "common/mat_mul.cl", +#include "./cl_kernels/common/mat_mul.clembed" + }, #ifdef ENABLE_NCHW_KERNELS { "nchw/batch_to_space.cl", |