diff options
| author | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2021-10-15 10:23:24 +0100 |
|---|---|---|
| committer | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2021-10-18 13:26:35 +0000 |
| commit | c9cecc0e565e7b4978cecc92e03e6c93bb8d0cb9 (patch) | |
| tree | e5e26af2cd1d8537c528a401ddbc729ae7beb2bb /src/gpu/cl/operators/ClGemmLowpMatrixMultiplyCore.cpp | |
| parent | 36118524d2f387be53dc95e5eebabfcb3ec21f31 (diff) | |
| download | ComputeLibrary-c9cecc0e565e7b4978cecc92e03e6c93bb8d0cb9.tar.gz | |
Remove legacy GeMM kernels on OpenCL
Resolves COMPMID-4446
Change-Id: I1d3c2391b67681f4d3af440826aa95b47a1288a6
Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/6444
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/gpu/cl/operators/ClGemmLowpMatrixMultiplyCore.cpp')
| -rw-r--r-- | src/gpu/cl/operators/ClGemmLowpMatrixMultiplyCore.cpp | 1 |
1 files changed, 0 insertions, 1 deletions
diff --git a/src/gpu/cl/operators/ClGemmLowpMatrixMultiplyCore.cpp b/src/gpu/cl/operators/ClGemmLowpMatrixMultiplyCore.cpp index 6fd7e52d5d..7a62186677 100644 --- a/src/gpu/cl/operators/ClGemmLowpMatrixMultiplyCore.cpp +++ b/src/gpu/cl/operators/ClGemmLowpMatrixMultiplyCore.cpp @@ -239,7 +239,6 @@ void ClGemmLowpMatrixMultiplyCore::configure(const CLCompileContext &compile_con GEMMLHSMatrixInfo lhs_info; // Arguments used by GEMMReshapeInfo - // If we pass the matrix A and matrix B reshaped to CLGEMMMatrixMultiplyKernel, we need to pass m, n, k, mult_transpose1xW_width and mult_interleave4x4_height to CLGEMMReshapeInfo // in order to know how the matrices have been reshaped bool reinterpret_input_as_3d = gemm_info.reinterpret_input_as_3d(); const unsigned int m = reinterpret_input_as_3d ? (a->dimension(1) * a->dimension(2)) : a->dimension(1); |