From a8d80583c3b3faa338127ddb9019b6d1085a69ae Mon Sep 17 00:00:00 2001 From: SiCong Li Date: Fri, 19 May 2023 14:23:37 +0100 Subject: Implement FP32/FP16 MatMul NT/NT kernel using the MMUL extension Resolves COMPMID-6194 Signed-off-by: SiCong Li Change-Id: Ie45e2aa9533948b2e5235563cef1d3834494eccf Signed-off-by: SiCong Li Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9739 Reviewed-by: Gunes Bayir Comments-Addressed: Arm Jenkins Tested-by: Arm Jenkins Benchmark: Arm Jenkins --- SConscript | 1 + 1 file changed, 1 insertion(+) (limited to 'SConscript') diff --git a/SConscript b/SConscript index 904d5babf1..320cb2d6fc 100644 --- a/SConscript +++ b/SConscript @@ -395,6 +395,7 @@ if env['opencl'] and env['embed_kernels']: '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/mat_mul_mmul.cl', 'src/core/CL/cl_kernels/common/mat_mul_quantized.cl', 'src/core/CL/cl_kernels/common/mean_stddev_normalization.cl', 'src/core/CL/cl_kernels/common/memset.cl', -- cgit v1.2.1