diff options
| author | SiCongLi <sicong.li@arm.com> | 2021-02-24 15:40:57 +0000 |
|---|---|---|
| committer | SiCong Li <sicong.li@arm.com> | 2021-03-08 09:39:14 +0000 |
| commit | b88272e2dcf09803cd275cfeb5ca1ea743a091ff (patch) | |
| tree | 6637bef6d413bc513ffa451b0993102d7da57f4d /src/core/NEON/kernels/NETransposeKernel.cpp | |
| parent | c7b1e84ac5f3ada1b2f78c66979ef4d44804a955 (diff) | |
| download | ComputeLibrary-b88272e2dcf09803cd275cfeb5ca1ea743a091ff.tar.gz | |
Remove usage of valid window region in NHWC CPU kernels - Part2
Remove set_valid_region methods from all NHWC CPU ML functions /
operators / kernels
Resolves COMPMID-4152 (2/2)
Change-Id: If9725e9c5b0213b87db96675e81b7fb724970b98
Signed-off-by: SiCongLi <sicong.li@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5203
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/NEON/kernels/NETransposeKernel.cpp')
| -rw-r--r-- | src/core/NEON/kernels/NETransposeKernel.cpp | 5 |
1 files changed, 0 insertions, 5 deletions
diff --git a/src/core/NEON/kernels/NETransposeKernel.cpp b/src/core/NEON/kernels/NETransposeKernel.cpp index 980d90b476..cd4ae52873 100644 --- a/src/core/NEON/kernels/NETransposeKernel.cpp +++ b/src/core/NEON/kernels/NETransposeKernel.cpp @@ -494,11 +494,6 @@ void NETransposeKernel::configure(const ITensor *input, ITensor *output) break; } - // Configure kernel window - Coordinates coord; - coord.set_num_dimensions(output->info()->num_dimensions()); - output->info()->set_valid_region(ValidRegion(coord, output->info()->tensor_shape())); - // Note: This kernel performs 16 elements per iteration. // However, since we use a left-over for loop on both dimensions (X and Y), we cannot have any read or write out of memory // For this reason num_elems_processed_per_iteration_x is set to 1 |