diff options
| author | Jakub Sujak <jakub.sujak@arm.com> | 2023-08-24 14:01:20 +0100 |
|---|---|---|
| committer | Jakub Sujak <jakub.sujak@arm.com> | 2023-09-04 14:41:16 +0000 |
| commit | 0d27b2ee8d811d66693555ac1e7be44d93e662e2 (patch) | |
| tree | 8b62a464a8bb9cd46702c8b5a60f3a97e3821b41 /tests/validation/dynamic_fusion | |
| parent | 7ff03b67ba7ce669223f4d807e18fa3efa2f729b (diff) | |
| download | ComputeLibrary-0d27b2ee8d811d66693555ac1e7be44d93e662e2.tar.gz | |
Remove legacy PostOps code
PostOps was the experimental interface for Dynamic Fusion. It is now
replaced by the new Dynamic Fusion interface with code generation using
the Compute Kernel Writer.
Resolves: COMPMID-6190
Change-Id: I813b48facef2fd6f3aee332588886b4f9b3d33d8
Signed-off-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10219
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: SiCong Li <sicong.li@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'tests/validation/dynamic_fusion')
| -rw-r--r-- | tests/validation/dynamic_fusion/gpu/cl/DirectConv2d.cpp | 10 |
1 files changed, 3 insertions, 7 deletions
diff --git a/tests/validation/dynamic_fusion/gpu/cl/DirectConv2d.cpp b/tests/validation/dynamic_fusion/gpu/cl/DirectConv2d.cpp index f27a1796c9..bae8cbf868 100644 --- a/tests/validation/dynamic_fusion/gpu/cl/DirectConv2d.cpp +++ b/tests/validation/dynamic_fusion/gpu/cl/DirectConv2d.cpp @@ -58,7 +58,7 @@ TEST_SUITE(DYNAMIC_FUSION) * No quantized tests | Not supported yet * No grouped CNN tests | Not supported yet * No mixed layout tests | Not needed; only NHWC is supported - * No activation/post op tests | Not needed in fusion + * No activation | Not needed in fusion * No ValidateConvolutionMethod | Only a single method (direct conv2d) is supported * No ReshapeWeights = true tests | Not applicable yet. This parameter only concerns gemm-based conv2d * No RunSmallWithPadding tests | Padding is removed @@ -70,9 +70,7 @@ template <typename T> using DynamicFusionGpuConv2dFixture = DynamicFusionGpuConv2dValidationFixture<CLTensor, CLAccessor, GpuConv2d, T>; TEST_SUITE(FP32) FIXTURE_DATA_TEST_CASE(RunSmall, DynamicFusionGpuConv2dFixture<float>, framework::DatasetMode::ALL, combine(combine(combine(datasets::SmallConvolutionLayerDataset(), - framework::dataset::make("DataType", DataType::F32)), - framework::dataset::make("DataLayout", { DataLayout::NHWC })), - framework::dataset::make("QuantizationInfo", QuantizationInfo()))) + framework::dataset::make("DataType", DataType::F32)), framework::dataset::make("DataLayout", { DataLayout::NHWC })), framework::dataset::make("QuantizationInfo", QuantizationInfo()))) { // Validate output validate(CLAccessor(_target), _reference, tolerance_f32); @@ -81,9 +79,7 @@ TEST_SUITE_END() // FP32 TEST_SUITE(FP16) FIXTURE_DATA_TEST_CASE(RunSmall, DynamicFusionGpuConv2dFixture<half>, framework::DatasetMode::ALL, combine(combine(combine(datasets::SmallConvolutionLayerDataset(), - framework::dataset::make("DataType", DataType::F16)), - framework::dataset::make("DataLayout", { DataLayout::NHWC })), - framework::dataset::make("QuantizationInfo", QuantizationInfo()))) + framework::dataset::make("DataType", DataType::F16)), framework::dataset::make("DataLayout", { DataLayout::NHWC })), framework::dataset::make("QuantizationInfo", QuantizationInfo()))) { // Validate output validate(CLAccessor(_target), _reference, tolerance_f16, tolerance_num); |