diff options
author | giuros01 <giuseppe.rossini@arm.com> | 2019-07-09 11:01:34 +0100 |
---|---|---|
committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2019-07-10 13:56:55 +0000 |
commit | c878f1fdcc35c1d346fad6fbe975a55928f73187 (patch) | |
tree | d466a8d8c607a3fe1f6a0a2740ad4c892891a707 /src/core/CL/kernels | |
parent | 01fd6cf41254995539d553baed6093f377871837 (diff) | |
download | ComputeLibrary-c878f1fdcc35c1d346fad6fbe975a55928f73187.tar.gz |
COMPMID-2457: Investigate DirectConvolution failures
We were not correctly handling the case where NumKernels > 1. In order
to handle this, I had to:
- Position the source pointer correctly (in the cl kernel)
- Position the weights pointer correctly (in the cl kernel)
- Set the correct num_elements_read_per_iteration_x and change the input access window
accordingly
Change-Id: Ib2257b50930c822d3623f373dae04f188b46ee56
Signed-off-by: giuros01 <giuseppe.rossini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/1498
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Diffstat (limited to 'src/core/CL/kernels')
-rw-r--r-- | src/core/CL/kernels/CLDirectConvolutionLayerKernel.cpp | 6 |
1 files changed, 5 insertions, 1 deletions
diff --git a/src/core/CL/kernels/CLDirectConvolutionLayerKernel.cpp b/src/core/CL/kernels/CLDirectConvolutionLayerKernel.cpp index b878a2121f..dc4c431c5d 100644 --- a/src/core/CL/kernels/CLDirectConvolutionLayerKernel.cpp +++ b/src/core/CL/kernels/CLDirectConvolutionLayerKernel.cpp @@ -239,6 +239,10 @@ inline void setup_num_elems(unsigned int &num_elems_read_per_iteration_x, unsign { num_elems_read_per_iteration_x = 4; } + else + { + num_elems_read_per_iteration_x = 1; + } switch(kernel_size) { @@ -346,7 +350,7 @@ std::pair<Status, Window> validate_and_configure_window(ITensorInfo *input, ITen if(data_layout == DataLayout::NHWC) { AccessWindowStatic input_access(input, 0, -conv_pad_left, - num_elems_read_per_iteration_x, + ceil_to_multiple(input->dimension(0), num_elems_read_per_iteration_x), ceil_to_multiple(input->dimension(1) + conv_info.pad_right(), num_elems_read_per_iteration_y)); AccessWindowStatic weights_access(weights, 0, 0, weights->dimension(0), weights->dimension(1)); AccessWindowRectangle output_access(output, 0, 0, num_elems_written_per_iteration_x, num_elems_written_per_iteration_y); |