From 2b6ebfe4270b06b09e45f306e8384950aeca7e4e Mon Sep 17 00:00:00 2001 From: Ramy Elgammal Date: Thu, 9 Mar 2023 21:15:37 +0000 Subject: 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 Co-authored-by: Ramy Elgammal Change-Id: I1d5b8978f41be27baddb3153ade880472141573f Signed-off-by: Gunes Bayir Signed-off-by: Ramy Elgammal Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9333 Tested-by: Arm Jenkins Reviewed-by: Gian Marco Iodice Benchmark: Arm Jenkins --- Android.bp | 2 ++ 1 file changed, 2 insertions(+) (limited to 'Android.bp') diff --git a/Android.bp b/Android.bp index 28bc7e20dc..42116d78ca 100644 --- a/Android.bp +++ b/Android.bp @@ -49,6 +49,7 @@ opencl_srcs = [ "src/core/CL/cl_kernels/common/generate_proposals_quantized.cl", "src/core/CL/cl_kernels/common/instance_normalization.cl", "src/core/CL/cl_kernels/common/l2_normalize.cl", + "src/core/CL/cl_kernels/common/mat_mul.cl", "src/core/CL/cl_kernels/common/mean_stddev_normalization.cl", "src/core/CL/cl_kernels/common/memset.cl", "src/core/CL/cl_kernels/common/minmax_layer.cl", @@ -689,6 +690,7 @@ cc_library_static { "src/gpu/cl/kernels/ClIndirectConv2dAddressPrecalculationKernel.cpp", "src/gpu/cl/kernels/ClIndirectConv2dKernel.cpp", "src/gpu/cl/kernels/ClMulKernel.cpp", + "src/gpu/cl/kernels/ClNativeMatMulKernel.cpp", "src/gpu/cl/kernels/ClPermuteKernel.cpp", "src/gpu/cl/kernels/ClPool2dKernel.cpp", "src/gpu/cl/kernels/ClPool3dKernel.cpp", -- cgit v1.2.1