wren romano aff9c89fab [mlir][sparse] Simplifying closure ... By closing over the `rank` itself rather than `this`, we save a method call on each iteration. A minor optimization, but one that adds up. Depends On D126016 Reviewed By: aartbik Differential Revision: https://reviews.llvm.org/D126019		2022-05-19 15:15:33 -07:00
..
AsyncRuntime.cpp
CMakeLists.txt	[MLIR] Fix build without native arch	2022-05-12 09:50:51 +02:00
CRunnerUtils.cpp	[mlir] Fix the names of exported functions	2022-05-05 13:46:15 -07:00
CudaRuntimeWrappers.cpp	Revert "Fix CUDA runtime wrapper for GPU mem alloc/free to async"	2022-04-12 06:50:27 +00:00
ExecutionEngine.cpp	[mlir:ExecutionEngine] Update use of getAddress now that lookup returns ExecutorAddr	2022-05-05 14:24:32 -07:00
JitRunner.cpp	Apply clang-tidy fixes for performance-unnecessary-value-param in JitRunner.cpp (NFC)	2022-04-19 07:23:12 +00:00
OptUtils.cpp	Reland [mlir] Remove uses of LLVM's legacy pass manager	2022-04-11 16:53:32 -07:00
RocmRuntimeWrappers.cpp
RunnerUtils.cpp	[mlir] Fix the names of exported functions	2022-05-05 13:46:15 -07:00
SparseTensorUtils.cpp	[mlir][sparse] Simplifying closure	2022-05-19 15:15:33 -07:00