diff options
Diffstat (limited to 'src')
-rw-r--r-- | src/core/CL/kernels/CLTransposeKernel.cpp | 7 | ||||
-rw-r--r-- | src/core/NEON/kernels/NETransposeKernel.cpp | 10 |
2 files changed, 12 insertions, 5 deletions
diff --git a/src/core/CL/kernels/CLTransposeKernel.cpp b/src/core/CL/kernels/CLTransposeKernel.cpp index d57d82f22a..81ab217923 100644 --- a/src/core/CL/kernels/CLTransposeKernel.cpp +++ b/src/core/CL/kernels/CLTransposeKernel.cpp @@ -23,7 +23,7 @@ */ #include "arm_compute/core/CL/kernels/CLTransposeKernel.h" -#include "arm_compute/core/AccessWindowTranspose.h" +#include "arm_compute/core/AccessWindowStatic.h" #include "arm_compute/core/CL/CLHelpers.h" #include "arm_compute/core/CL/CLKernelLibrary.h" #include "arm_compute/core/CL/ICLTensor.h" @@ -31,6 +31,7 @@ #include "arm_compute/core/Error.h" #include "arm_compute/core/Helpers.h" #include "arm_compute/core/Types.h" +#include "arm_compute/core/Utils.h" #include <set> #include <sstream> @@ -75,7 +76,9 @@ void CLTransposeKernel::configure(const ICLTensor *input, ICLTensor *output) Window win = calculate_max_window(*input->info(), Steps(num_elems_processed_per_iteration, num_elems_processed_per_iteration)); AccessWindowRectangle input_access(input->info(), 0, 0, num_elems_processed_per_iteration, num_elems_processed_per_iteration); - AccessWindowTranspose output_access(output->info(), 0, 0, num_elems_processed_per_iteration, num_elems_processed_per_iteration); + // TODO (COMPMID-708): Replace AccessWindowStatic with AccessWindowTranspose + AccessWindowStatic output_access(output->info(), 0, 0, ceil_to_multiple(output->info()->dimension(0), num_elems_processed_per_iteration), ceil_to_multiple(output->info()->dimension(1), + num_elems_processed_per_iteration)); update_window_and_padding(win, input_access, output_access); diff --git a/src/core/NEON/kernels/NETransposeKernel.cpp b/src/core/NEON/kernels/NETransposeKernel.cpp index 1cfaafe93a..44becf5a4b 100644 --- a/src/core/NEON/kernels/NETransposeKernel.cpp +++ b/src/core/NEON/kernels/NETransposeKernel.cpp @@ -23,10 +23,11 @@ */ #include "arm_compute/core/NEON/kernels/NETransposeKernel.h" -#include "arm_compute/core/AccessWindowTranspose.h" +#include "arm_compute/core/AccessWindowStatic.h" #include "arm_compute/core/Error.h" #include "arm_compute/core/Helpers.h" #include "arm_compute/core/ITensor.h" +#include "arm_compute/core/Utils.h" #include "arm_compute/core/Validate.h" #include <arm_neon.h> @@ -221,8 +222,11 @@ void NETransposeKernel::configure(const ITensor *input, ITensor *output) } // Configure kernel window - Window win = calculate_max_window(*input->info(), Steps(num_elems_processed_per_iteration, num_elems_processed_per_iteration)); - AccessWindowTranspose output_access(output->info(), 0, 0, num_elems_processed_per_iteration, num_elems_processed_per_iteration); + Window win = calculate_max_window(*input->info(), Steps(num_elems_processed_per_iteration, num_elems_processed_per_iteration)); + + // TODO (COMPMID-708): Replace AccessWindowStatic with AccessWindowTranspose + AccessWindowStatic output_access(output->info(), 0, 0, ceil_to_multiple(output->info()->dimension(0), num_elems_processed_per_iteration), ceil_to_multiple(output->info()->dimension(1), + num_elems_processed_per_iteration)); update_window_and_padding(win, AccessWindowRectangle(input->info(), 0, 0, num_elems_processed_per_iteration, num_elems_processed_per_iteration), |