diff options
| author | Gunes Bayir <gunes.bayir@arm.com> | 2022-11-09 09:26:27 +0000 |
|---|---|---|
| committer | Gunes Bayir <gunes.bayir@arm.com> | 2022-11-14 15:01:27 +0000 |
| commit | ec0113dd7749991959ae351934eea0c0d8077dcb (patch) | |
| tree | 792f38b3a05fa85436339d54abddab096e20cc77 /src/gpu/cl/ClKernelLibrary.cpp | |
| parent | 46ede332c7064b85dc538891cad165b3bb427320 (diff) | |
| download | ComputeLibrary-ec0113dd7749991959ae351934eea0c0d8077dcb.tar.gz | |
Optimize Transposed Convolution for CL backend (FP32/16)
This patch optimizes transposed convolution for CL backend by rewriting it in a single kernel instead of three (flip_kernel + upsample + conv). The new kernel skips the upsampling step which reduces the input space of convolution by stride_x * stride_y, resulting in significant performance improvement. It also skips the kernel flipping by traversing the weights accordingly, thus reduces the memory footprint.
Resolves: COMPMID-5676
Signed-off-by: Gunes Bayir <gunes.bayir@arm.com>
Change-Id: I8a333212dc7c5f7f0597aa58b0d56d44814baa14
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8588
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/gpu/cl/ClKernelLibrary.cpp')
| -rw-r--r-- | src/gpu/cl/ClKernelLibrary.cpp | 5 |
1 files changed, 5 insertions, 0 deletions
diff --git a/src/gpu/cl/ClKernelLibrary.cpp b/src/gpu/cl/ClKernelLibrary.cpp index 0f08f5d044..4e036399db 100644 --- a/src/gpu/cl/ClKernelLibrary.cpp +++ b/src/gpu/cl/ClKernelLibrary.cpp @@ -448,6 +448,7 @@ const std::map<std::string, std::string> ClKernelLibrary::_kernel_program_map = { "space_to_batch_nhwc", "nhwc/space_to_batch.cl" }, { "space_to_batch_static_nhwc", "nhwc/space_to_batch.cl" }, { "space_to_depth_nhwc", "nhwc/space_to_depth.cl" }, + { "transposed_convolution_nhwc", "nhwc/transposed_convolution.cl" }, { "upsample_layer_nhwc", "nhwc/upsample_layer.cl" }, { "winograd_filter_transform_4x1_3x1_nhwc", "nhwc/winograd_filter_transform.cl" }, { "winograd_filter_transform_1x4_1x3_nhwc", "nhwc/winograd_filter_transform.cl" }, @@ -943,6 +944,10 @@ const std::map<std::string, std::string> ClKernelLibrary::_program_source_map = #include "./cl_kernels/nhwc/space_to_depth.clembed" }, { + "nhwc/transposed_convolution.cl", +#include "./cl_kernels/nhwc/transposed_convolution.clembed" + }, + { "nhwc/winograd_filter_transform.cl", #include "./cl_kernels/nhwc/winograd_filter_transform.clembed" }, |