caio/clang-p2996

Files

History

Umang Yadav 836201f117 Allow bf16 operands on new MFMAs (#144925 )

New gfx950 MFMA allows bf16 operands. 


c0cc81cdc0/llvm/include/llvm/IR/IntrinsicsAMDGPU.td (L3434)

When running `amdgpu-to-rocdl`, Current logic converts bf16 to i16
always which fails to compile for newer bf16 MFMA e.g.
`v_mfma_f32_16x16x32bf16`.
Backend expects bf16 type for the operands for those newer MFMAs. This
patch fixes it.

CC: @krzysz00  @dhernandez0  @giuseros  @antiagainst  @kuhar

2025-06-19 12:52:31 -05:00

..

benchmark/python

…

[MLIR][IRDL] Added IRDL to C++ Translation (#141248 )

2025-05-25 16:42:30 +02:00

[mlir][vector] Add documentation note on adding new ops (#144308 )

2025-06-17 09:30:35 +01:00

[mlir] Remove deprecated cast member functions (#135556 )

2025-04-14 09:08:34 -04:00

[mlir][cf] Preserve branch weights during cf.cond_br canonicalization. (#144822 )

2025-06-19 10:09:10 -07:00

Allow bf16 operands on new MFMAs (#144925 )

2025-06-19 12:52:31 -05:00

[mlir] [python] Fixed the return type of MemRefType.get_strides_and_offset (#144523 )

2025-06-18 09:53:20 -04:00

Allow bf16 operands on new MFMAs (#144925 )

2025-06-19 12:52:31 -05:00

[mlir][Vector] Add vector.to_elements op (#141457 )

2025-06-18 13:45:43 -07:00

[mlir][tensor] Fix getReassociationForCollapse for tensor/scalar re… (#144118 )

2025-06-13 20:03:24 +02:00

[MLIR][VSCode] update packages to fix CVE-2022-25883 and CVE-2022-3517 (#144479 )

2025-06-17 09:53:11 +01:00

.clang-format

…

.clang-tidy

…

CMakeLists.txt

[MLIR][IRDL] Added IRDL to C++ Translation (#141248 )

2025-05-25 16:42:30 +02:00

LICENSE.TXT

…

README.md

…

README.md

Multi-Level Intermediate Representation

See https://mlir.llvm.org/ for more information.