Guray Ozen baf27862dd

[MLIR][NVGPU] Move max threads/blocks size to dialect (NFC) (#124454) ...

This PR moves maximum number of threads in a block and block in a grid
to nvgpu dialect to avoid replicated code.

The limits are defined here:

https://docs.nvidia.com/cuda/cuda-c-programming-guide/#features-and-technical-specifications-technical-specifications-per-compute-capability

2025-02-05 12:38:37 +01:00

..

IR

[mlir] share argument attributes interface between calls and callables (#123176)

2025-02-03 11:27:14 +01:00

Pipelines

[mlir][GPU] Do not strip location info when lowering to NVVM (#120432)

2024-12-19 15:05:45 +01:00

TransformOps

[MLIR][NVGPU] Move max threads/blocks size to dialect (NFC) (#124454)

2025-02-05 12:38:37 +01:00

Transforms

[mlir][IR][NFC] Move free-standing functions to MemRefType (#123465)

2025-01-21 08:48:09 +01:00

Utils

[MLIR] Create GPU utils library & move distribution utils (#119264)

2024-12-13 10:26:57 +01:00

CMakeLists.txt

[mlir][GPU] Implement ValueBoundsOpInterface for GPU ID operations (#122190)

2025-01-09 11:42:22 -08:00