diff options
| author | Georgios Pinitas <georgios.pinitas@arm.com> | 2019-06-03 17:22:55 +0100 |
|---|---|---|
| committer | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2019-06-04 11:30:42 +0000 |
| commit | bbac660f1959ed2ab58b31a8d5db524883da1754 (patch) | |
| tree | a9aa3bebd26db2cb5564b43e4777336611ab644e /src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp | |
| parent | 4c5469b192665c94118a8a558787cb9cec2d0765 (diff) | |
| download | ComputeLibrary-bbac660f1959ed2ab58b31a8d5db524883da1754.tar.gz | |
COMPMID-2366: (Nightly) Failure in CLGEMMLowp
Change-Id: I4f9d329e23ae4337f044e6ab66c87081fc813877
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-on: https://review.mlplatform.org/c/1273
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Diffstat (limited to 'src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp')
| -rw-r--r-- | src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp index 3ddeeaee41..27d5b28943 100644 --- a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp +++ b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp @@ -133,7 +133,7 @@ std::pair<Status, Window> validate_and_configure_window(ITensorInfo *input0, ITe // Note: bottom paddings are calculated manually as the output can be reinterpreted as 3D tensor // The only way to set properly the paddings, it is to set those explicitly through the AccessWindowStatic - const int m = gemm_info.m(); + const int m = reinterpret_output_as_3d ? gemm_info.m() : input0->dimension(1); const int bottom_pad = (num_elems_processed_per_iteration_y - (m % num_elems_processed_per_iteration_y)) % num_elems_processed_per_iteration_y; win = calculate_max_window(tmp_info, Steps(num_elems_processed_per_iteration_x, num_elems_processed_per_iteration_y)); |