diff options
| author | Michele Di Giorgio <michele.digiorgio@arm.com> | 2019-10-08 09:36:26 +0100 |
|---|---|---|
| committer | Michele Di Giorgio <michele.digiorgio@arm.com> | 2019-10-15 10:27:18 +0000 |
| commit | a046e164b96a8441b2fa14ef578f7db46a0e97da (patch) | |
| tree | 9fa2b7e003342b608acd3ed627f47f9d027ef72c /src/core/CL/CLKernelLibrary.cpp | |
| parent | 76c996f3b240eb1f60a566e5b0a5e61fe363685a (diff) | |
| download | ComputeLibrary-a046e164b96a8441b2fa14ef578f7db46a0e97da.tar.gz | |
COMPMID-2600: Implement a new and generic depthwise convolution for CL QASYMM8 NHWC
The NCHW case is supported at function level by permuting the
inputs/outputs to NHWC.
This patch also removes CLDirectConvolutionLayerOutputStageKernel which
is deprecated and some kernels which were only used in the generic case
of depthwise convolution.
Change-Id: I91e0f02d0a2f4a4a352e08c248e648944137fe68
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2056
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Diffstat (limited to 'src/core/CL/CLKernelLibrary.cpp')
| -rw-r--r-- | src/core/CL/CLKernelLibrary.cpp | 5 |
1 files changed, 1 insertions, 4 deletions
diff --git a/src/core/CL/CLKernelLibrary.cpp b/src/core/CL/CLKernelLibrary.cpp index fa5193fde2..7b7263fca7 100644 --- a/src/core/CL/CLKernelLibrary.cpp +++ b/src/core/CL/CLKernelLibrary.cpp @@ -222,6 +222,7 @@ const std::map<std::string, std::string> CLKernelLibrary::_kernel_program_map = { "depthwise_convolution_3x3_nhwc", "depthwise_convolution.cl" }, { "depthwise_convolution_3x3_nhwc_stride1", "depthwise_convolution.cl" }, { "dwc_MxN_native_fp_nhwc", "depthwise_convolution.cl" }, + { "dwc_MxN_native_quantized8_nhwc", "depthwise_convolution_quantized.cl" }, { "dwc_3x3_native_qasymm8_nchw", "depthwise_convolution_quantized.cl" }, { "dwc_3x3_native_qasymm8_dot8_nchw", "depthwise_convolution_quantized.cl" }, { "dwc_3x3_reshaped_qasymm8_nhwc", "depthwise_convolution_quantized.cl" }, @@ -234,9 +235,6 @@ const std::map<std::string, std::string> CLKernelLibrary::_kernel_program_map = { "depthwise_convolution_3x3_stridex1_stridey1_bifrost_f32", "depthwise_convolution.cl" }, { "depthwise_convolution_3x3_stridex2_stridey2_bifrost_f32", "depthwise_convolution.cl" }, { "depthwise_convolution_reshape_weights", "depthwise_convolution.cl" }, - { "depthwise_convolution_reshape_weights_generic", "depthwise_convolution.cl" }, - { "depthwise_im2col", "depthwise_convolution.cl" }, - { "depthwise_vector_to_tensor", "depthwise_convolution.cl" }, { "dequantization_layer", "dequantization_layer.cl" }, { "dequantization_layer_per_channel_nhwc", "dequantization_layer.cl" }, { "dequantization_layer_per_channel_nchw", "dequantization_layer.cl" }, @@ -413,7 +411,6 @@ const std::map<std::string, std::string> CLKernelLibrary::_kernel_program_map = { "NV21_to_RGB888_bt709", "color_convert.cl" }, { "NV21_to_RGBA8888_bt709", "color_convert.cl" }, { "NV21_to_YUV444_bt709", "color_convert.cl" }, - { "output_stage_quantized", "direct_convolution_1x1_3x3_5x5_quantized.cl" }, { "pad_layer_constant", "pad_layer.cl" }, { "pad_layer_symmetric_reflect", "pad_layer.cl" }, { "permute", "permute.cl" }, |