diff options
| author | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2022-12-30 09:45:00 +0000 |
|---|---|---|
| committer | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2022-12-30 13:33:34 +0000 |
| commit | 9d3bd41030366326e9c8afe5db3a5812a76b135b (patch) | |
| tree | e2ee02632bca1a8f671043b2b6ee1f35f8f9c9d5 /arm_compute/core | |
| parent | b7e8626717b2ef81b0d03284c8f6ffdbe9cd2245 (diff) | |
| download | ComputeLibrary-9d3bd41030366326e9c8afe5db3a5812a76b135b.tar.gz | |
Move DWC native heuristic into the heuristic folder
- 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 <gianmarco.iodice@arm.com>
Change-Id: I6bfd30cea76bea2e98202a7a5c1d51709f3382a4
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8889
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/core')
| -rw-r--r-- | arm_compute/core/KernelDescriptors.h | 4 |
1 files changed, 2 insertions, 2 deletions
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 */ }; |