diff options
author | Georgios Pinitas <georgios.pinitas@arm.com> | 2021-04-28 10:20:18 +0100 |
---|---|---|
committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2021-05-19 11:38:32 +0000 |
commit | 11d8415aa57b69fb6c83e86a37e3026c22d1d37d (patch) | |
tree | 8f6bb12011ddc7275a8cc071dbf8ffe90a88e8eb /arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h | |
parent | 856f66e6c61b77d03f754cd0fa8439891f0e4aca (diff) | |
download | ComputeLibrary-11d8415aa57b69fb6c83e86a37e3026c22d1d37d.tar.gz |
Port DepthConvert to new Api
- Renames DepthConvert to Cast
- Ports both NEDepthConverLayer and CLDepthConvert variants
- Removes legacy shift capability from DepthConvert, allowing only
shifts of 0
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I806a0f8eb23d23502b632c529fda7edde19c8176
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5565
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h')
-rw-r--r-- | arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h | 11 |
1 files changed, 9 insertions, 2 deletions
diff --git a/arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h b/arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h index e5de45c34f..3d2dbdb104 100644 --- a/arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h +++ b/arm_compute/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.h @@ -34,7 +34,6 @@ class CLCompileContext; class IMemoryManager; class ICLTensor; class ITensorInfo; -class CLDepthConvertLayerKernel; class CLGEMMLowpMatrixMultiplyNativeKernel; class CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel; class CLGEMMLowpOffsetContributionKernel; @@ -49,6 +48,14 @@ class ClGemmReshapeRhsMatrixKernel; } // namespace kernels } // namespace opencl +namespace opencl +{ +namespace kernels +{ +class ClCastKernel; +} // namespace kernels +} // namespace opencl + /** Basic function to execute GEMMLowpMatrixMultiplyCore on OpenCL. */ class CLGEMMLowpMatrixMultiplyCore : public IFunction { @@ -143,7 +150,7 @@ private: MemoryGroup _memory_group; // Kernels used - std::unique_ptr<CLDepthConvertLayerKernel> _weights_to_qasymm8; + std::unique_ptr<opencl::kernels::ClCastKernel> _weights_to_qasymm8; std::unique_ptr<CLGEMMLowpMatrixMultiplyNativeKernel> _mm_native_kernel; std::unique_ptr<CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel> _mm_reshaped_only_rhs_kernel; std::unique_ptr<opencl::kernels::ClGemmReshapeRhsMatrixKernel> _mtx_b_reshape_kernel; |