diff options
| author | George Wort <george.wort@arm.com> | 2019-02-22 16:37:41 +0000 |
|---|---|---|
| committer | Giuseppe Rossini <giuseppe.rossini@arm.com> | 2019-03-15 13:34:00 +0000 |
| commit | 2d7e683e79c8ad328d4930c1f82a46827313faf4 (patch) | |
| tree | eb81f928ecd2543ef80af87f65d1bdef5a78ea2a /src/core/CL | |
| parent | 3814b30623d6a9e570d850fe5ae275fe2117f3f5 (diff) | |
| download | ComputeLibrary-2d7e683e79c8ad328d4930c1f82a46827313faf4.tar.gz | |
COMPMID-1694: Fuse offset contribution with the output stage when we use NEGEMMLowpMatrixMultiplyCore
Change-Id: Ic1a681e4cc03e1eba3bf8485d9cdb17b3e926047
Signed-off-by: giuros01 <giuseppe.rossini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/561
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/CL')
| -rw-r--r-- | src/core/CL/kernels/CLGEMMLowpOffsetContributionOutputStageKernel.cpp | 3 |
1 files changed, 1 insertions, 2 deletions
diff --git a/src/core/CL/kernels/CLGEMMLowpOffsetContributionOutputStageKernel.cpp b/src/core/CL/kernels/CLGEMMLowpOffsetContributionOutputStageKernel.cpp index 83af0c63eb..8fba342e74 100644 --- a/src/core/CL/kernels/CLGEMMLowpOffsetContributionOutputStageKernel.cpp +++ b/src/core/CL/kernels/CLGEMMLowpOffsetContributionOutputStageKernel.cpp @@ -1,5 +1,5 @@ /* - * Copyright (c) 2018 ARM Limited. + * Copyright (c) 2018-2019 ARM Limited. * * SPDX-License-Identifier: MIT * @@ -51,7 +51,6 @@ Status validate_arguments(const ITensorInfo *mm_result, const ITensorInfo *vecto { ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(mm_result, 1, DataType::S32); ARM_COMPUTE_RETURN_ERROR_ON(output_stage.type == GEMMLowpOutputStageType::NONE); - ARM_COMPUTE_RETURN_ERROR_ON(bias == nullptr && a_offset == 0 && b_offset == 0); ARM_COMPUTE_RETURN_ERROR_ON(output_stage.gemmlowp_max_bound > 255); ARM_COMPUTE_RETURN_ERROR_ON(output_stage.gemmlowp_min_bound < 0 || output_stage.gemmlowp_min_bound > output_stage.gemmlowp_max_bound); |