wren romano 221856f5cd [mlir][sparse] Moved a conditional from the RT library to the generated MLIR. ...

When generating code to add an element to SparseTensorCOO (e.g., when doing dense=>sparse conversion), we used to check for nonzero values on the runtime side, whereas now we generate MLIR code to do that check.

Reviewed By: aartbik

Differential Revision: https://reviews.llvm.org/D110121

2021-09-23 12:44:17 -07:00

..

AsyncRuntime.cpp

[mlir:Async] Add the size parameter to the async.group

2021-06-25 10:26:50 -07:00

CMakeLists.txt

[MLIR] Make MLIR cmake variable names consistent

2021-05-24 08:43:10 +05:30

CRunnerUtils.cpp

[mlir] Avoid including <alloca.h> on FreeBSD and NetBSD

2021-08-08 13:32:35 +02:00

CudaRuntimeWrappers.cpp

[mlir] create gpu memset op

2021-09-04 08:13:04 +02:00

ExecutionEngine.cpp

[ExecutionEngine] Fix GEP type

2021-07-17 23:45:00 +02:00

JitRunner.cpp

[mlir] Load dynamic libraries in JitRunner from absolute paths so that GDB can find the symbol tables.

2021-02-19 07:33:35 +01:00

OptUtils.cpp

Revert "Revert "[mlir] Convert from Async dialect to LLVM coroutines""

2020-10-22 15:23:11 -04:00

RocmRuntimeWrappers.cpp

[mlir] create gpu memset op

2021-09-04 08:13:04 +02:00

RunnerUtils.cpp

[mlir] NFC - Add runner util functions to only print MemRef metadata.

2021-03-04 12:35:45 +00:00

SparseUtils.cpp

[mlir][sparse] Moved a conditional from the RT library to the generated MLIR.

2021-09-23 12:44:17 -07:00