diff options
author | Viet-Hoa Do <viet-hoa.do@arm.com> | 2023-05-17 15:17:48 +0100 |
---|---|---|
committer | Viet-Hoa Do <viet-hoa.do@arm.com> | 2023-06-12 14:41:18 +0000 |
commit | 3fcf3dcf7b6ffc613468ccaca580bde495677440 (patch) | |
tree | 567c85806318a868b0029f969cac823dd48fe44a /tests/validation/fixtures/dynamic_fusion/operators/ActivationFixture.h | |
parent | 48cfd5f7895f13167e4e9cd974dbc1e983e04ed7 (diff) | |
download | ComputeLibrary-3fcf3dcf7b6ffc613468ccaca580bde495677440.tar.gz |
Add multi-sketch support for dynamic fusion
* Tensors are owned by workload context instead of workload sketch
so that they can be used by multiple sketches.
* Add an integration test for multi-sketch case.
Resolves: COMPMID-6148
Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Change-Id: I37d0de5ac103fb2a85020aa1c26e49eb304f47b7
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9706
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: SiCong Li <sicong.li@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'tests/validation/fixtures/dynamic_fusion/operators/ActivationFixture.h')
-rw-r--r-- | tests/validation/fixtures/dynamic_fusion/operators/ActivationFixture.h | 8 |
1 files changed, 4 insertions, 4 deletions
diff --git a/tests/validation/fixtures/dynamic_fusion/operators/ActivationFixture.h b/tests/validation/fixtures/dynamic_fusion/operators/ActivationFixture.h index 9656c497ea..3fb2cc2b7c 100644 --- a/tests/validation/fixtures/dynamic_fusion/operators/ActivationFixture.h +++ b/tests/validation/fixtures/dynamic_fusion/operators/ActivationFixture.h @@ -102,12 +102,12 @@ protected: { // Create a new workload sketch CLCompileContext cl_compile_ctx = CLKernelLibrary::get().get_compile_context(); - GpuWorkloadContext gpu_ctx{ &cl_compile_ctx }; - GpuWorkloadSketch sketch{ &gpu_ctx }; + GpuWorkloadContext context{ &cl_compile_ctx }; + GpuWorkloadSketch sketch{ &context }; // Create sketch tensors - TensorInfo src_info = sketch.create_tensor_info(TensorInfo(shape, 1, _data_type)); - TensorInfo dst_info = sketch.create_tensor_info(TensorInfo(shape, 1, _data_type)); + TensorInfo src_info = context.create_tensor_info(TensorInfo(shape, 1, _data_type)); + TensorInfo dst_info = context.create_tensor_info(TensorInfo(shape, 1, _data_type)); ITensorInfo *ans_0_info = FunctionType::create_op(sketch, &src_info, args...); if(_fuse) |