diff options
author | Giorgio Arena <giorgio.arena@arm.com> | 2021-02-08 16:31:10 +0000 |
---|---|---|
committer | Giorgio Arena <giorgio.arena@arm.com> | 2021-03-02 09:03:00 +0000 |
commit | 68e29dab4ada6e3457f066c3cf45acf51a204dd9 (patch) | |
tree | a920ebfb51ba39f7b015c919d4e65d71ffbf94be /tests/validation/NEON/DepthwiseConvolutionLayerNative.cpp | |
parent | c1b9b098518211d6f356650a0ce5022a36c623e9 (diff) | |
download | ComputeLibrary-68e29dab4ada6e3457f066c3cf45acf51a204dd9.tar.gz |
Set up configure-only flag for validation. First trial with DepthwiseConvoltion
This is needed in order to validate OpenCL kernel run-time compilation, without necessarily running or validating the kernels' execution
- Add a run-time option for our validation suite to only configure one target function, without allocating, running or validating
- Avoid to map/unmap tensors in CLAccessor if no allocation/validation is required
- Create a new Fixture macro that accepts fixtures split into configure/allocate_and_run/reference, and do the last two only if required
- Adjust fixture and validation files for the first trial function(s) (DepthwiseConvolutionLayer)
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Change-Id: I56fa1ce5ef4ac0c86bcabda686cc277ef5ec69c8
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5048
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-by: Sang-Hoon Park <sang-hoon.park@arm.com>
Diffstat (limited to 'tests/validation/NEON/DepthwiseConvolutionLayerNative.cpp')
-rw-r--r-- | tests/validation/NEON/DepthwiseConvolutionLayerNative.cpp | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/tests/validation/NEON/DepthwiseConvolutionLayerNative.cpp b/tests/validation/NEON/DepthwiseConvolutionLayerNative.cpp index e1af732400..3314227bec 100644 --- a/tests/validation/NEON/DepthwiseConvolutionLayerNative.cpp +++ b/tests/validation/NEON/DepthwiseConvolutionLayerNative.cpp @@ -135,7 +135,7 @@ TEST_CASE(ValidateNoPadding, framework::DatasetMode::ALL) TEST_SUITE(Float) TEST_SUITE(FP32) -FIXTURE_DATA_TEST_CASE(RunSmall, NEDepthwiseConvolutionLayerNativeFixture<float>, framework::DatasetMode::ALL, +FIXTURE_DATA_TEST_CASE_NEW(RunSmall, NEDepthwiseConvolutionLayerNativeFixture<float>, framework::DatasetMode::ALL, combine(combine(combine(combine(combine(combine(combine(combine(combine(combine(width_values_precommit, height_values_precommit), channel_values_precommit), @@ -152,7 +152,7 @@ FIXTURE_DATA_TEST_CASE(RunSmall, NEDepthwiseConvolutionLayerNativeFixture<float> validate(Accessor(_target), _reference, rel_tolerance_f32, 0.f, abs_tolerance_f32); } -FIXTURE_DATA_TEST_CASE(RunLarge, NEDepthwiseConvolutionLayerNativeFixture<float>, framework::DatasetMode::NIGHTLY, +FIXTURE_DATA_TEST_CASE_NEW(RunLarge, NEDepthwiseConvolutionLayerNativeFixture<float>, framework::DatasetMode::NIGHTLY, combine(combine(combine(combine(combine(combine(combine(combine(combine(combine(width_values_nightly, height_values_nightly), channel_values_nightly), |