Krzysztof Drewniak 3452149c05

[mlir][AMDGPU] Support vector<2xbf16> packed atomic fadd (#113929) ...

Now that we use LLVM's native bfloat types in the AMDGPU lowering,
enable vector<2xbf16> for AMDGPU.

2024-10-31 10:52:53 -05:00

..

8-bit-floats.mlir

[mlir][AMDGPU] Add packed 8-bit float conversion ops and lowering

2023-09-28 14:44:16 +00:00

amdgpu-to-rocdl.mlir

[mlir][AMDGPU] Support vector<2xbf16> packed atomic fadd (#113929)

2024-10-31 10:52:53 -05:00

dpp.mlir

[mlir][AMDGPU] Implement AMDGPU DPP operation in MLIR. (#89233)

2024-08-16 11:19:39 -05:00

mfma.mlir

[MLIR] AMDGPUToROCDL: Use a bitcast op to reintepret a vector of i8 as single integer. (#111400)

2024-10-07 14:14:18 -04:00

wmma-gfx12.mlir

[MLIR][AMDGPU] Add support for fp8 ops on gfx12 (#106388)

2024-09-03 17:47:08 +01:00

wmma.mlir

[mlir][AMDGPU] Remove an old bf16 workaround (#108409)

2024-09-12 17:45:39 -05:00