aboutsummaryrefslogtreecommitdiff
path: root/tests/validation/dynamic_fusion/gpu/Integration.cpp
diff options
context:
space:
mode:
authorGunes Bayir <gunes.bayir@arm.com>2024-01-17 16:07:03 +0000
committerViet-Hoa Do <viet-hoa.do@arm.com>2024-02-01 16:00:34 +0000
commit2b9fa593a0a172bf36a02b5cdb840c6b9b361d7c (patch)
treea4e2d5ce46443a79a0778e4960462ce3edf106ec /tests/validation/dynamic_fusion/gpu/Integration.cpp
parent7ab7fca87cca8775f82b0e9efec6a40975910c17 (diff)
downloadComputeLibrary-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/Integration.cpp')
-rw-r--r--tests/validation/dynamic_fusion/gpu/Integration.cpp4
1 files changed, 2 insertions, 2 deletions
diff --git a/tests/validation/dynamic_fusion/gpu/Integration.cpp b/tests/validation/dynamic_fusion/gpu/Integration.cpp
index bb9c008f01..80dcaa8f90 100644
--- a/tests/validation/dynamic_fusion/gpu/Integration.cpp
+++ b/tests/validation/dynamic_fusion/gpu/Integration.cpp
@@ -280,10 +280,10 @@ TEST_CASE(Add_Output_Add_Cast_Cast_Output, framework::DatasetMode::ALL)
ITensorInfo *out_1_info = context.create_tensor_info();
CastAttributes cast_0_attr;
- cast_0_attr.data_type(DataType::S32).convert_policy(ConvertPolicy::SATURATE);
+ cast_0_attr.data_type(DataType::F16);
CastAttributes cast_1_attr;
- cast_1_attr.data_type(DataType::F32).convert_policy(ConvertPolicy::SATURATE);
+ cast_1_attr.data_type(DataType::F32);
ITensorInfo *ans_0_info = GpuAdd::create_op(sketch, in_0_info, in_1_info);
GpuOutput::create_op(sketch, ans_0_info, out_0_info);