Nishant Patel f291f335c9

[MLIR][XeGPU] Support order attribute and add pattern for vector.transpose in WgToSg Pass (#165307) ...

This PR does the following:
1. Handle order attribute during the delinearization from linear
subgroup Id to multi-dim id.
2. Adds a transformation pattern for vector.transpose in wg to sg pass.
3. Updates CHECKS in the wg to sg tests

2025-11-04 19:37:08 -08:00

..

CMakeLists.txt

[mlir][xegpu] Add OptimizeBlockLoads pass. (#165483)

2025-11-04 13:15:32 -08:00

XeGPUBlocking.cpp

[MLIR][XeGPU] Remove leading unit dims from vector ops before unrolling (#165030)

2025-10-27 09:09:33 -07:00

XeGPUFoldAliasOps.cpp

[mlir] Remove unused includes (NFC) (#150266)

2025-07-23 15:18:53 -07:00

XeGPUOptimizeBlockLoads.cpp

[mlir][xegpu] Add OptimizeBlockLoads pass. (#165483)

2025-11-04 13:15:32 -08:00

XeGPUPropagateLayout.cpp

[mlir][xegpu] Add OptimizeBlockLoads pass. (#165483)

2025-11-04 13:15:32 -08:00

XeGPUSubgroupDistribute.cpp

[MLIR][XeGPU] Matrix load/store subgroup distribution (#165008)

2025-11-03 21:48:27 +01:00

XeGPUUnroll.cpp

[mlir][XeGPU] Add optional layout attribute to LoadGather StoreScatter ops (#163414)

2025-11-04 08:19:47 -08:00

XeGPUVectorLinearize.cpp

[mlir][XeGPU][Transform] Add vectorlinearize transform pass. (#158084)

2025-09-18 17:25:38 -05:00

XeGPUWgToSgDistribute.cpp

[MLIR][XeGPU] Support order attribute and add pattern for vector.transpose in WgToSg Pass (#165307)

2025-11-04 19:37:08 -08:00