diff options
author | SiCong Li <sicong.li@arm.com> | 2022-08-17 17:09:05 +0100 |
---|---|---|
committer | Mohammed Suhail Munshi <MohammedSuhail.Munshi@arm.com> | 2022-09-14 10:49:56 +0000 |
commit | 5687e55250613417c151864cb74229fc91ea6462 (patch) | |
tree | 93ed4ae1dd3aaed3c42726345d2df13b1bebe291 /tests/validation | |
parent | 926f502ca731fa49bcdf949408ce25728616e5f2 (diff) | |
download | ComputeLibrary-5687e55250613417c151864cb74229fc91ea6462.tar.gz |
Fix invalid memory access for dynamically fused Cl Elementwise kernels
The M0 and N0 were incorrectly set for the case of broadcasting when the
elementwise component is non-root.
This is because we previously always use rhs tensor to derive the load
M0, N0. But for non-root components, the addend/divisor tensor can be
in the lhs or rhs. Thus this would fail in case the addend/divisor is in
the lhs.
- Also fixes broken Dynamic Fusion test
Resolves COMPMID-5482
Signed-off-by: SiCong Li <sicong.li@arm.com>
Change-Id: I37f27ffa392781387db15739b1666f1dad28c554
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/445890
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Mohammed Suhail Munshi <mohammedsuhail.munshi@arm.com>
Comments-Addressed: bsgcomp <bsgcomp@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8111
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Pablo Marquez Tello <pablo.tello@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'tests/validation')
-rw-r--r-- | tests/validation/CL/UNIT/dynamic_fusion/ClCompositeKernel.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/tests/validation/CL/UNIT/dynamic_fusion/ClCompositeKernel.cpp b/tests/validation/CL/UNIT/dynamic_fusion/ClCompositeKernel.cpp index 3ffbc077c6..dc98d72f4b 100644 --- a/tests/validation/CL/UNIT/dynamic_fusion/ClCompositeKernel.cpp +++ b/tests/validation/CL/UNIT/dynamic_fusion/ClCompositeKernel.cpp @@ -171,7 +171,7 @@ TEST_CASE(MoveNet_SubGraph_1_DirectConv2d, framework::DatasetMode::ALL) SimpleTensor<float> ref_src_nhwc{ src_shape, data_type, 1, QuantizationInfo(), DataLayout::NHWC }; SimpleTensor<float> ref_wei_nhwc{ wei_shape, data_type, 1, QuantizationInfo(), DataLayout::NHWC }; SimpleTensor<float> ref_bia_nhwc{ bia_shape, data_type, 1, QuantizationInfo(), DataLayout::NHWC }; - SimpleTensor<float> ref_addend_nhwc{ dst_shape, data_type, 1, QuantizationInfo(), DataLayout::NHWC }; + SimpleTensor<float> ref_addend_nhwc{ addend_shape, data_type, 1, QuantizationInfo(), DataLayout::NHWC }; // Fill reference fill<float>(ref_src_nhwc, 0, library.get()); |