max 8f7c8a6ea7 Add gpu::HostUnregisterOp ...

Without explicitly unregistering you will get

```
'cuMemHostRegister(ptr, sizeBytes, 0)' failed with 'CUDA_ERROR_HOST_MEMORY_ALREADY_REGISTERED'
```

in CUDA (for example) after repeated runs (e.g., during benchmarking the same kernel).

Reviewed By: ftynse

Differential Revision: https://reviews.llvm.org/D147277

2023-04-06 15:07:12 -05:00

..

SparseTensor

[mlir][sparse] Renaming "pointer/index" to "position/coordinate"

2023-03-06 12:23:33 -08:00

AsyncRuntime.cpp

Replace void* with std::byte* in AsyncRuntime

2022-12-20 19:17:35 -08:00

CMakeLists.txt

[mlir] Support lowering of dialect attributes attached to top-level modules

2023-03-21 12:54:26 +00:00

CRunnerUtils.cpp

[mlir][crunner] Add support for invoking std::sort.

2022-12-13 12:31:14 -08:00

CudaRuntimeWrappers.cpp

Add gpu::HostUnregisterOp

2023-04-06 15:07:12 -05:00

ExecutionEngine.cpp

[mlir-cpu-runner] Add support for -mattr and -march flags

2023-03-31 07:34:24 +00:00

Float16bits.cpp

[mlir][vector] add support for printing f16 and bf16

2023-03-03 08:58:25 -08:00

JitRunner.cpp

[mlir-cpu-runner] Add support for -mattr and -march flags

2023-03-31 07:34:24 +00:00

OptUtils.cpp

[PassBuilder] Support O0 in default pipelines

2023-03-17 10:00:05 +01:00

RocmRuntimeWrappers.cpp

Add gpu::HostUnregisterOp

2023-04-06 15:07:12 -05:00

RunnerUtils.cpp

[mlir][runner] Add more printMemref functions.

2022-12-12 09:37:50 -08:00

SparseTensorRuntime.cpp

[mlir][sparse] Renaming "pointer/index" to "position/coordinate"

2023-03-06 12:23:33 -08:00