Erick Ochoa Lopez 909c9aacea

[mlir][amdgpu] Add lowerings for ScaledExtPacked816 (#168123) ...

* Adds lowerings for amdgpy.scaled_ext_packed816
* updates verifiers

2025-11-17 16:51:52 -05:00

..

8-bit-floats-ocp.mlir

[mlir][ROCDL] Add fp4 and fp6 conversion intrinsics, fix fp8 immargs (#140801)

2025-05-21 13:50:02 -07:00

8-bit-floats.mlir

[mlir][ROCDL] Add fp4 and fp6 conversion intrinsics, fix fp8 immargs (#140801)

2025-05-21 13:50:02 -07:00

amdgpu-to-rocdl.mlir

[mlir][amdgpu] Add lowerings for ScaledExtPacked816 (#168123)

2025-11-17 16:51:52 -05:00

cvt_scale_pk-gfx1250.mlir

[mlir][amdgpu] Add lowerings for ScaledExtPacked816 (#168123)

2025-11-17 16:51:52 -05:00

dpp.mlir

…

load_lds-gfx950.mlir

[AMDGPU] [MLIR] Add 96 and 128 bit GatherToLDS for gfx950 (#147496)

2025-07-09 11:53:26 -04:00

load_lds.mlir

[mlir][amdgpu] Properly handle mismatching memref ranks in amdgpu.gather_to_lds (#149407)

2025-07-18 00:42:25 +03:00

memory_counter_wait.mlir

[mlir][amdgpu] Add rocdl.s.waitcnt wrapper (#149670)

2025-07-22 23:37:56 +03:00

mfma-gfx950.mlir

[mlir][amdgpu] Update scaled_mfma assembly format with intrinsic shape (#165044)

2025-10-25 11:49:34 +00:00

mfma.mlir

[mlir][amdgpu] Update mfma assembly format with intrinsic shape (#165037)

2025-10-25 05:58:43 -04:00

packed-ext.mlir

[mlir][AMDGPU] Add scaled floating point conversion ops (#141554)

2025-06-13 11:09:11 +02:00

packed-trunc.mlir

[mlir][AMDGPU] Add scaled floating point conversion ops (#141554)

2025-06-13 11:09:11 +02:00

permlane.mlir

[mlir][AMDGPU] Updated PermlaneSwapOp to select correct val (#157586)

2025-09-12 13:45:56 +02:00

swizzle.mlir

…

transpose_load_reject.mlir

[AMDGPU] Adding AMDGPU dialect wrapper for ROCDL transpose loads. (#145395)

2025-06-25 22:58:14 -04:00

transpose_load.mlir

[AMDGPU] [MLIR] Add 96 and 128 bit GatherToLDS for gfx950 (#147496)

2025-07-09 11:53:26 -04:00

wmma-gfx11.mlir

[mlir][ROCDL] Refactor wmma intrinsics to use attributes not operands where possible (#167041)

2025-11-13 19:50:02 -05:00

wmma-gfx12.mlir

[mlir][ROCDL] Refactor wmma intrinsics to use attributes not operands where possible (#167041)

2025-11-13 19:50:02 -05:00

wmma-gfx1250.mlir

[mlir][ROCDL] Refactor wmma intrinsics to use attributes not operands where possible (#167041)

2025-11-13 19:50:02 -05:00