diff options
author | SiCong Li <sicong.li@arm.com> | 2023-06-28 09:49:45 +0100 |
---|---|---|
committer | SiCong Li <sicong.li@arm.com> | 2023-07-25 15:48:50 +0000 |
commit | 23882a9014eb3972bca958206866c8e0d0b829cc (patch) | |
tree | 9139b91699099160e26a64abd8cf182bd7447278 /src/dynamic_fusion/sketch/gpu/GpuKernelComponentGraph.cpp | |
parent | 0a59e69fd922b02d9e3b5b043ee7f891061df7be (diff) | |
download | ComputeLibrary-23882a9014eb3972bca958206866c8e0d0b829cc.tar.gz |
Add GpuKernelArgumentBinding for runtime argument setting
* Add flexible runtime argument setting that accept argument bindings
exported from ckw.
* Introduce internal build flag ACL_INTERNAL_TEST_CKW_IN_DF. If set to
true, ckw will be tested in dynamic fusion validation tests. Otherwise
it will not be tested and the dynamic fusion will keep using
ClTemplateWriter instead.
* Fix CKW sampler for elementwise binary to deal with tile sizes > 1
in both dimensions
Resolves: COMPMID-6282
Partially resolves: COMPMID-6260
Signed-off-by: SiCong Li <sicong.li@arm.com>
Change-Id: I0ab225a4484eb2119643d900a4e72806558626ee
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9917
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-by: Anitha Raj <Anitha.Raj@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/dynamic_fusion/sketch/gpu/GpuKernelComponentGraph.cpp')
-rw-r--r-- | src/dynamic_fusion/sketch/gpu/GpuKernelComponentGraph.cpp | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/src/dynamic_fusion/sketch/gpu/GpuKernelComponentGraph.cpp b/src/dynamic_fusion/sketch/gpu/GpuKernelComponentGraph.cpp index b70a192775..5a65ede38b 100644 --- a/src/dynamic_fusion/sketch/gpu/GpuKernelComponentGraph.cpp +++ b/src/dynamic_fusion/sketch/gpu/GpuKernelComponentGraph.cpp @@ -44,14 +44,14 @@ std::vector<DependencyGraph::TensorId> GpuKernelComponentGraph::get_tensor_ids(c return tensor_ids; } -GpuKernelComponentGraph::GpuKernelComponentGraph(GpuComponentServices *services) - : _services{ services }, _components{}, _tensors{}, _dependency_graph{} +GpuKernelComponentGraph::GpuKernelComponentGraph(GpuWorkloadContext *context, GpuComponentServices *services) + : _context{ context }, _services{ services }, _components{}, _tensors{}, _dependency_graph{} { } GpuKernelComponentStream GpuKernelComponentGraph::fuse(const MemoryDescriptorMap &mem_map) const { - GpuKernelComponentStream stream{ _services, mem_map }; + GpuKernelComponentStream stream{ _context, _services, mem_map }; const auto op_seq = _dependency_graph.build_operators_sequence(); stream.new_component_group(); |