diff options
| author | Mohammed Suhail Munshi <MohammedSuhail.Munshi@arm.com> | 2022-09-29 13:07:21 +0100 |
|---|---|---|
| committer | Mohmun02 <MohammedSuhail.Munshi@arm.com> | 2022-10-20 08:36:41 +0000 |
| commit | 6782452c16a286a6dd4a071cfc70bbbcbabb20be (patch) | |
| tree | 601a9d2ba302ed3c93ca21dab8e8dc28ce9c7a04 /tests/validation/NEON/GEMMLowp.cpp | |
| parent | 0a36f58e711a19040b1b65ef0afa83cce0c9dc4c (diff) | |
| download | ComputeLibrary-6782452c16a286a6dd4a071cfc70bbbcbabb20be.tar.gz | |
Add test in GEMMLowp for batch matmul
- Adds tests for batched matrix multiplication
- Bugfix for issue : 3d tensors input tensors with offsets in GemmLowp results in mismatches
Resolves : [COMPMID-5507]
Signed-off-by: Mohammed Suhail Munshi <MohammedSuhail.Munshi@arm.com>
Change-Id: I68e036fbca642c1841dd4321033045aadc8f5636
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/461298
Comments-Addressed: bsgcomp <bsgcomp@arm.com>
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8482
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'tests/validation/NEON/GEMMLowp.cpp')
| -rw-r--r-- | tests/validation/NEON/GEMMLowp.cpp | 10 |
1 files changed, 9 insertions, 1 deletions
diff --git a/tests/validation/NEON/GEMMLowp.cpp b/tests/validation/NEON/GEMMLowp.cpp index 7dd1a479fe..2dcc740b97 100644 --- a/tests/validation/NEON/GEMMLowp.cpp +++ b/tests/validation/NEON/GEMMLowp.cpp @@ -1,5 +1,5 @@ /* - * Copyright (c) 2017-2021 Arm Limited. + * Copyright (c) 2017-2022 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -51,6 +51,7 @@ TEST_SUITE(NEON) TEST_SUITE(GEMMLowp) TEST_SUITE(MatrixMultiplyCore) using NEGEMMLowpMatrixMultiplyCoreFixture = GEMMLowpMatrixMultiplyCoreValidationFixture<Tensor, Accessor, NEGEMMLowpMatrixMultiplyCore>; +using NEGEMMLowpBatchedMatMulFixture = GEMMLowpMatrixMultiplyCoreValidationFixture<Tensor, Accessor, NEGEMMLowpMatrixMultiplyCore, false, false, true>; DATA_TEST_CASE(Configuration, framework::DatasetMode::ALL, framework::dataset::concat(datasets::SmallGEMMLowpDataset(), datasets::LargeGEMMLowpDataset()), shape_a, shape_b, shape_c, a_offset, b_offset) @@ -210,6 +211,13 @@ TEST_CASE(MultipleExecutionWithConfigure, framework::DatasetMode::ALL) } } +TEST_SUITE(BatchedMatMul) +FIXTURE_DATA_TEST_CASE(RunSmall, NEGEMMLowpBatchedMatMulFixture, framework::DatasetMode::ALL, datasets::SmallGEMMLowpBatchedMatMulDataset()) +{ + validate(Accessor(_target), _reference); +} +TEST_SUITE_END() // BatchedMatMul + FIXTURE_DATA_TEST_CASE(RunSmall, NEGEMMLowpMatrixMultiplyCoreFixture, framework::DatasetMode::ALL, datasets::SmallGEMMLowpDataset()) { // Validate output |