From 9d3bd41030366326e9c8afe5db3a5812a76b135b Mon Sep 17 00:00:00 2001 From: Gian Marco Iodice Date: Fri, 30 Dec 2022 09:45:00 +0000 Subject: Move DWC native heuristic into the heuristic folder MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit - Move the DWC native heuristic from CLDepthwiseConvolutionLayer to heuristic/ - Update the heuristic for Arm® Mali™-G77. Use a smaller block size (4x2) for Fp16 - Call the new heuristic in GpuDepthwiseConv2d Resolves COMPMID-5798 Signed-off-by: Gian Marco Iodice Change-Id: I6bfd30cea76bea2e98202a7a5c1d51709f3382a4 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8889 Comments-Addressed: Arm Jenkins Reviewed-by: Gunes Bayir Tested-by: Arm Jenkins Benchmark: Arm Jenkins --- arm_compute/core/KernelDescriptors.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arm_compute/core') diff --git a/arm_compute/core/KernelDescriptors.h b/arm_compute/core/KernelDescriptors.h index cacbef25ea..4a64032b14 100644 --- a/arm_compute/core/KernelDescriptors.h +++ b/arm_compute/core/KernelDescriptors.h @@ -104,8 +104,8 @@ struct GEMMKernelInfo /** Compute descriptor used by the depthwise convolution native kernel */ struct DWCComputeKernelInfo { - unsigned int n0{ 0 }; /**< Number of columns processed by each thread */ - unsigned int m0{ 0 }; /**< Number of rows processed by each thread */ + unsigned int n0{ 1 }; /**< Number of columns processed by each thread */ + unsigned int m0{ 1 }; /**< Number of rows processed by each thread */ bool export_input_to_cl_image{ false }; /**< Export input to cl_image */ bool export_weights_to_cl_image{ false }; /**< Export the weights to cl_image */ }; -- cgit v1.2.1