diff options
| author | Georgios Pinitas <georgios.pinitas@arm.com> | 2019-08-23 12:44:11 +0100 |
|---|---|---|
| committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2019-08-24 20:23:49 +0000 |
| commit | 275f99cb09606191c5589952d57175be655de74a (patch) | |
| tree | bf3a7e41930a292069f52d603fe0a63a18304a65 /src/core/CL/kernels/CLDeconvolutionLayerUpsampleKernel.cpp | |
| parent | 601ba3f3ee78f6bbc2d046648b064b9aaa7e88a6 (diff) | |
| download | ComputeLibrary-275f99cb09606191c5589952d57175be655de74a.tar.gz | |
COMPMID-2451: Use kernel lws_hint() on enqueue
Avoid querying device's default lws on kernel enqueue as this is already
cached in the kernel during configuration.
Change-Id: Ia26ecb712caeb8f042356815e0cfd23522764d27
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-on: https://review.mlplatform.org/c/1803
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/CL/kernels/CLDeconvolutionLayerUpsampleKernel.cpp')
| -rw-r--r-- | src/core/CL/kernels/CLDeconvolutionLayerUpsampleKernel.cpp | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/src/core/CL/kernels/CLDeconvolutionLayerUpsampleKernel.cpp b/src/core/CL/kernels/CLDeconvolutionLayerUpsampleKernel.cpp index 295fb5c997..50f654680c 100644 --- a/src/core/CL/kernels/CLDeconvolutionLayerUpsampleKernel.cpp +++ b/src/core/CL/kernels/CLDeconvolutionLayerUpsampleKernel.cpp @@ -129,7 +129,7 @@ void CLDeconvolutionLayerUpsampleKernel::run(const Window &window, cl::CommandQu unsigned int idx = 0; add_3D_tensor_argument(idx, _input, slice_in); add_3D_tensor_argument(idx, _output, slice_out); - enqueue(queue, *this, slice_out); + enqueue(queue, *this, slice_out, lws_hint()); } while(collapsed.slide_window_slice_3D(slice_in) && collapsed.slide_window_slice_3D(slice_out)); break; @@ -148,7 +148,7 @@ void CLDeconvolutionLayerUpsampleKernel::run(const Window &window, cl::CommandQu unsigned int idx = 0; add_3D_tensor_argument(idx, _input, slice_in); add_3D_tensor_argument(idx, _output, slice_out); - enqueue(queue, *this, slice_out); + enqueue(queue, *this, slice_out, lws_hint()); } while(window.slide_window_slice_3D(slice_in) && window.slide_window_slice_3D(slice_out)); break; |