diff options
| author | Gian Marco <gianmarco.iodice@arm.com> | 2017-12-16 19:33:50 +0000 |
|---|---|---|
| committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:42:33 +0000 |
| commit | 1d25ed54a948639d1894c8b021940df70005d519 (patch) | |
| tree | 96a29126c5b61299d64496fad7f6844412ab2cca /src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp | |
| parent | 57b20109108a90113d29d21ce7d3c873ff19749c (diff) | |
| download | ComputeLibrary-1d25ed54a948639d1894c8b021940df70005d519.tar.gz | |
COMPMID-759 - CLGEMM optimization for McVail benchmarks
This patch introduces an optimization for CLGEMM on Bifrost
architectures which can bring to 40% of FMA utilization on
config 3 of McVail. The new CLGEMM does not require any reshape of
matrix A and matrix B.
This patch also adds the auto-config in CLConvolutionLayer and CLGEMM
and extends the interface for NEGEMM and CLGEMM.
Change-Id: Ibb354eda45e9ca64b14a99700fb21dff5989dda9
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/113716
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Diffstat (limited to 'src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp')
| -rw-r--r-- | src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp b/src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp index f51d0f92d4..19f38bf5a5 100644 --- a/src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp +++ b/src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp @@ -95,7 +95,7 @@ inline std::pair<Status, Window> validate_and_configure_window(ITensorInfo *inpu // Create kernels according to the architecture, data type and input size. if(gpu_target == GPUTarget::BIFROST && data_type == DataType::F32) { - num_elems_processed_per_iteration_x = (input1->dimension(0) <= 1000) ? 2 : 4; + num_elems_processed_per_iteration_x = (input1->dimension(0) <= 1000 && input0->num_dimensions() == 1) ? 2 : 4; } // Configure window @@ -196,7 +196,7 @@ void CLGEMMMatrixMultiplyKernel::configure(const ICLTensor *input0, const ICLTen // The first kernel is optimized for the case of 1000 or less output elements (e.g. FC8 of AlexNet and VGG-16, and // FC1 of Inception v3). The second kernel is optimized for the case of greater than 1000 output elements (e.g. // FC6 and FC7 of AlexNet and VGG-16). - kernel_name = (input1->info()->dimension(0) <= 1000) ? "gemm_mm_floating_point_f32_bifrost_1000" : "gemm_mm_floating_point_f32_bifrost"; + kernel_name = (input1->info()->dimension(0) <= 1000 && input0->info()->num_dimensions() == 1) ? "gemm_mm_floating_point_f32_bifrost_1000" : "gemm_mm_floating_point_f32_bifrost"; // The work-group size equal to the Bifrost quad size has been proved to be optimal for these kernels // via exhaustive autotuning over a range of representative layer configurations. |