Matthias Springer 951ab04d6c

[mlir][NVVM] Add no-rollback option to NVVM lowering passes (#168477) ...

Add pass options to run lowerings to NVVM without pattern rollback. This
makes the dialect conversions easier to debug and improves
performance/memory usage.

2025-11-18 13:47:28 +08:00

..

gpu-arith-ops-to-nvvm.mlir

[mlir] lower min/maxnum to libdevice calls (#127323)

2025-02-15 17:53:36 -05:00

gpu-to-nvvm-32b.mlir

[mlir][GPUToNVVM] Add benefit to populate functions (#128484)

2025-02-24 17:27:55 +01:00

gpu-to-nvvm-debuginfo.mlir

[mlir][gpu] Fix bug with GPU hardware intrinsic global location (#144923)

2025-06-22 22:09:44 -06:00

gpu-to-nvvm-invalid-dialect.mlir

[mlir][gpu] GPUToROCDL/NVVM: use generic llvm conversion interface instead of hardcoded conversions. (#124439)

2025-02-13 17:53:12 +03:00

gpu-to-nvvm-target-attr.mlir

[mlir][Transforms] Dialect Conversion Driver without Rollback (#151865)

2025-08-13 17:40:55 +02:00

gpu-to-nvvm.mlir

[mlir][NVVM] Add no-rollback option to NVVM lowering passes (#168477)

2025-11-18 13:47:28 +08:00

memref.mlir

[mlir][NVVM] Add no-rollback option to NVVM lowering passes (#168477)

2025-11-18 13:47:28 +08:00

wmma-ops-to-nvvm.mlir

[mlir][NVVM] Add no-rollback option to NVVM lowering passes (#168477)

2025-11-18 13:47:28 +08:00