diff options
author | Gunes Bayir <gunes.bayir@arm.com> | 2024-01-17 16:07:03 +0000 |
---|---|---|
committer | Viet-Hoa Do <viet-hoa.do@arm.com> | 2024-02-01 16:00:34 +0000 |
commit | 2b9fa593a0a172bf36a02b5cdb840c6b9b361d7c (patch) | |
tree | a4e2d5ce46443a79a0778e4960462ce3edf106ec /tests/validation/dynamic_fusion/gpu/cl/Sub.cpp | |
parent | 7ab7fca87cca8775f82b0e9efec6a40975910c17 (diff) | |
download | ComputeLibrary-2b9fa593a0a172bf36a02b5cdb840c6b9b361d7c.tar.gz |
Use the stable CKW API in the GPU dynamic fusion backend
- Refactor all kernels to work with the CKW stable API
- Add support for sub-tile in the op_load/op_store CKW operator
- Fix mismatch in resize
- Add comments in all kernels written with CKW to help developers
understand the structure of the code
- Add texture image support in depthwise convolution written with CKW
- Add support for different block sizes in depthwise convolution
- Remove the use of the dynamic fusion helper functions.
- Add support for floor in the op_unary() of CKW
Resolves: COMPMID-6708, COMPMID-6743, COMPMID-6530
Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Signed-off-by: Gunes Bayir <gunes.bayir@arm.com>
Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Signed-off-by: Jakub Sujak <jakub.sujak@arm.com>
Change-Id: I8104ce4d04a3138a1aeb0b84940e1f1c89e76069
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10914
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Jakub Sujak <jakub.sujak@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/dynamic_fusion/gpu/cl/Sub.cpp')
-rw-r--r-- | tests/validation/dynamic_fusion/gpu/cl/Sub.cpp | 12 |
1 files changed, 4 insertions, 8 deletions
diff --git a/tests/validation/dynamic_fusion/gpu/cl/Sub.cpp b/tests/validation/dynamic_fusion/gpu/cl/Sub.cpp index ef9f75b1c0..c7ab1e717c 100644 --- a/tests/validation/dynamic_fusion/gpu/cl/Sub.cpp +++ b/tests/validation/dynamic_fusion/gpu/cl/Sub.cpp @@ -22,9 +22,6 @@ * SOFTWARE. */ -// TODO: Fix testing of CKW Elementwise Binary (COMPMID-6530) -#ifndef ACL_INTERNAL_TEST_CKW_IN_DF - #include "arm_compute/dynamic_fusion/sketch/gpu/GpuWorkloadSketch.h" #include "arm_compute/dynamic_fusion/sketch/gpu/operators/GpuSub.h" @@ -63,13 +60,13 @@ DATA_TEST_CASE(Validate, framework::DatasetMode::ALL, zip(zip( TensorInfo(TensorShape(32U, 13U, 2U), 1, DataType::QASYMM8), // Unsupported data type QASYMM8 TensorInfo(TensorShape(32U, 13U, 2U), 1, DataType::QASYMM8_SIGNED), // Unsupported data type QASYMM8 TensorInfo(TensorShape(32U, 13U, 2U), 1, DataType::F32), // Invalid data type combination - TensorInfo(TensorShape(32U, 13U, 2U), 1, DataType::S16), // S16 is valid data type for Sub - TensorInfo(TensorShape(32U, 13U, 2U), 1, DataType::S32), // S32 is valid data type for Sub + TensorInfo(TensorShape(32U, 13U, 2U), 1, DataType::S16), // Invalid data type combination + TensorInfo(TensorShape(32U, 13U, 2U), 1, DataType::S32), // Invalid data type combination TensorInfo(TensorShape(32U, 13U, 2U), 1, DataType::F32), // Mismatching shapes TensorInfo(TensorShape(32U, 1U, 1U), 1, DataType::F32), // Broadcasting allowed for lhs TensorInfo(TensorShape(32U, 13U, 2U), 1, DataType::F32), TensorInfo(TensorShape(15U, 23U, 3U), 1, DataType::F32), // Broadcast Y dimension is not allowed - TensorInfo(TensorShape( 3U, 8U, 9U), 1, DataType::S16), // Broadcast Z dimension is not allowed + TensorInfo(TensorShape( 3U, 8U, 9U), 1, DataType::S16), // Invalid data type combination TensorInfo(TensorShape(32U, 13U, 2U, 2), 1, DataType::F32), // Batching is allowed }), framework::dataset::make("RhsInfo",{ TensorInfo(TensorShape(32U, 13U, 2U), 1, DataType::F32), @@ -86,7 +83,7 @@ DATA_TEST_CASE(Validate, framework::DatasetMode::ALL, zip(zip( TensorInfo(TensorShape( 3U, 8U, 1U), 1, DataType::S16), TensorInfo(TensorShape(32U, 13U, 2U, 2), 1, DataType::F32), })), - framework::dataset::make("Expected", { true, false, false, false, false, true, true, false, true, true, false, false, true })), + framework::dataset::make("Expected", { true, false, false, false, false, false, false, false, true, true, false, false, true })), input1_info, input2_info, expected) { // Create a new workload sketch @@ -263,4 +260,3 @@ TEST_SUITE_END() // CL } // namespace validation } // namespace test } // namespace arm_compute -#endif // ACL_INTERNAL_TEST_CKW_IN_DF |