Rewrite dynamic fusion
The new version introduces the following major changes:
* Change public interface to simplify and standardize the user experience
- Use the term "Workload" uniformly
- Simplify operator interface to be a set of static methods:
validate_op(), create_op()
* Separate the kernel writing into its own component (template_writer).
This is to allow the co-development of GpuKernelWriter, and to allow
easy replacement once GpuKernelWriter is mature.
* Optimize the core fusion algorithm used by the component graph. The
details can be found in GpuKernelComponentGraph::fuse()
* Use Gpu instead of Cl prefixes for most of the Workload interfaces
(except for runtime and kernel components, which have to be language specific)
This allows the potential extension to other Gpu langauges in the
future.
* Refactor runtime memory interface so that auxiliary tensor handling
is separate from the user tensor passing. This is because the former
is less stable and may require extension in the future.
* Hide source code object from the user as it is not required at the
moment
* Deprecate the old prototype entirely by disabling it in SCons build
Resolves COMPMID-5510, COMPMID-5512, COMPMID-5513
Change-Id: If69d2362856f2de4503546b7b6cf48a525cf3079
Signed-off-by: SiCong Li <sicong.li@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8406
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-by: Jakub Sujak <jakub.sujak@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>
diff --git a/Android.bp b/Android.bp
index 8c6d700..d02d436 100644
--- a/Android.bp
+++ b/Android.bp
@@ -592,6 +592,24 @@
"src/cpu/operators/CpuTranspose.cpp",
"src/cpu/operators/CpuWinogradConv2d.cpp",
"src/cpu/operators/internal/CpuGemmAssemblyDispatch.cpp",
+ "src/dynamic_fusion/runtime/gpu/cl/ClKernelRuntime.cpp",
+ "src/dynamic_fusion/runtime/gpu/cl/ClWorkloadRuntime.cpp",
+ "src/dynamic_fusion/sketch/OperatorAttributes.cpp",
+ "src/dynamic_fusion/sketch/gpu/GpuKernelArgument.cpp",
+ "src/dynamic_fusion/sketch/gpu/GpuKernelComponentGraph.cpp",
+ "src/dynamic_fusion/sketch/gpu/GpuKernelComponentGroup.cpp",
+ "src/dynamic_fusion/sketch/gpu/GpuKernelComponentStream.cpp",
+ "src/dynamic_fusion/sketch/gpu/GpuLogicalKernel.cpp",
+ "src/dynamic_fusion/sketch/gpu/GpuOperatorGroup.cpp",
+ "src/dynamic_fusion/sketch/gpu/GpuWorkloadContext.cpp",
+ "src/dynamic_fusion/sketch/gpu/GpuWorkloadSketch.cpp",
+ "src/dynamic_fusion/sketch/gpu/components/cl/ClComponentDirectConv2d.cpp",
+ "src/dynamic_fusion/sketch/gpu/components/cl/ClComponentStore.cpp",
+ "src/dynamic_fusion/sketch/gpu/operators/GpuConv2d.cpp",
+ "src/dynamic_fusion/sketch/gpu/template_writer/GpuKernelVariableTable.cpp",
+ "src/dynamic_fusion/sketch/gpu/template_writer/cl/ClTemplateDirectConv2d.cpp",
+ "src/dynamic_fusion/sketch/gpu/template_writer/cl/ClTemplateStore.cpp",
+ "src/dynamic_fusion/sketch/gpu/template_writer/cl/ClTemplateWriter.cpp",
"src/gpu/cl/ClContext.cpp",
"src/gpu/cl/ClKernelLibrary.cpp",
"src/gpu/cl/ClQueue.cpp",