diff options
| author | Michele Di Giorgio <michele.digiorgio@arm.com> | 2018-04-25 11:58:07 +0100 |
|---|---|---|
| committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:51:50 +0000 |
| commit | b8fc60fc9fe9ad6c48d9618fc65753fbe5813216 (patch) | |
| tree | a9f271d73f573686ba29c724bb3a3cee4b6b203b /src/core/GLES_COMPUTE/kernels/GCGEMMMatrixMultiplyKernel.cpp | |
| parent | 62385bce6baacfa194cff9e6be6d8eaa73bc3fab (diff) | |
| download | ComputeLibrary-b8fc60fc9fe9ad6c48d9618fc65753fbe5813216.tar.gz | |
COMPMID-1086: Optimizing GCGEMM - Add helpers to get target GPU information
This patch moves some of the helper functions in CLHelpers.[h,cpp] to
GPUTarget.[h,cpp] in order to make them avaialable to both CL and GLES backends.
Change-Id: Ib89b05a2084b73eb643b32fac13b8367cc80b6a5
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/128988
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Diffstat (limited to 'src/core/GLES_COMPUTE/kernels/GCGEMMMatrixMultiplyKernel.cpp')
| -rw-r--r-- | src/core/GLES_COMPUTE/kernels/GCGEMMMatrixMultiplyKernel.cpp | 6 |
1 files changed, 4 insertions, 2 deletions
diff --git a/src/core/GLES_COMPUTE/kernels/GCGEMMMatrixMultiplyKernel.cpp b/src/core/GLES_COMPUTE/kernels/GCGEMMMatrixMultiplyKernel.cpp index b4bb5470ad..2bd769cac4 100644 --- a/src/core/GLES_COMPUTE/kernels/GCGEMMMatrixMultiplyKernel.cpp +++ b/src/core/GLES_COMPUTE/kernels/GCGEMMMatrixMultiplyKernel.cpp @@ -42,7 +42,6 @@ #include <string> using namespace arm_compute; -using namespace arm_compute::gles_compute; using namespace arm_compute::misc::shape_calculator; namespace @@ -195,10 +194,13 @@ void GCGEMMMatrixMultiplyKernel::configure(const IGCTensor *input0, const IGCTen _input1 = input1; _output = output; + // Get target architecture + GPUTarget gpu_target = get_target(); + ElementsProcessed num_elements_processed{}; // Configure kernel window - auto win_config = validate_and_configure_window(input0->info(), input1->info(), output->info(), is_interleaved_transposed, reshape_info, GPUTarget::UNKNOWN, num_elements_processed); + auto win_config = validate_and_configure_window(input0->info(), input1->info(), output->info(), is_interleaved_transposed, reshape_info, gpu_target, num_elements_processed); ARM_COMPUTE_ERROR_THROW_ON(win_config.first); IGCKernel::configure(win_config.second); |