llvm-project

History

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

Bug description: Hardware intrinsic functions created during GPU
conversion to NVVM may contain debug info metadata from the original
function which cannot be used out of that function.

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

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][LLVM] Add the ConvertToLLVMAttrInterface and ConvertToLLVMOpInterface interfaces (#99566 )

2024-11-24 10:09:43 -05:00

gpu-to-nvvm.mlir

[MLIR] Mark LLVM::FMAOp as legal (#144671 )

2025-06-18 15:49:00 +02:00

memref.mlir

…

wmma-ops-to-nvvm.mlir

[mlir][LLVM] Switch undef for poison for uninitialized values (#125629 )

2025-02-06 12:49:30 -06:00