Nishant Patel 570055bf97

[MLIR][XeGPU] Propagate layout from anchor ops before Wg To Sg & Blocking Pass (#179490) ...

This PR calls recoverTemporaryLayout before the XeGPUWgtoSgDistribute &
XeGPUBlocking Pass to recover all the temporary operand layout which
might be required by the transformation patterns for checks and
verification

2026-02-06 15:56:09 -08:00

..

invalid.mlir

[MLIR][XeGPU]: Reject tensor_desc types with unknown bitwidth (#173922)

2026-01-20 13:12:33 -08:00

layout.mlir

[mlir][xegpu] Add definition of SliceAttr (#150146)

2025-08-08 11:27:17 -05:00

move-gpu-func-to-warp-op.mlir

[MLIR][XeGPU] Introduce xegpu::uArch usage in target-sensitive passes (#163801)

2025-10-31 17:33:11 +01:00

ops.mlir

[MLIR][XeGPU] Allow create mem desc from 2d memref (#167767)

2025-11-18 21:31:17 -08:00

peephole-optimize.mlir

[MLIR][XeGPU] Add 2D vector.multi_reduction optimization (#171154)

2026-01-14 12:58:30 +01:00

propagate-layout-inst-data.mlir

[MLIR][XeGPU] Refactor layout propagation utilities (#179016)

2026-02-05 19:26:25 -08:00

propagate-layout-subgroup.mlir

[MLIR][XeGPU] Refactor layout propagation utilities (#179016)

2026-02-05 19:26:25 -08:00

propagate-layout.mlir

[MLIR][XeGPU] Refactor layout propagation utilities (#179016)

2026-02-05 19:26:25 -08:00

resolve-layout-conflicts.mlir

[mlir][xegpu] Add initial support for layout conflict handling. (#173090)

2026-01-28 11:50:42 -08:00

sg-to-wi-experimental-unit.mlir

[mlir][xegpu] Add XeGPUSgToWiDistributeExperimental pass. (#177492)

2026-01-29 09:57:01 -08:00

sg-to-wi-experimental.mlir

[mlir][xegpu] Add XeGPUSgToWiDistributeExperimental pass. (#177492)

2026-01-29 09:57:01 -08:00

subgroup-distribute-unit.mlir

[MLIR] [XeGPU] SG distribution: adding tests for alloca/create_memdesc and remove unncessary check from shape_cast op lowering (#179018)

2026-02-03 09:17:25 -08:00

subgroup-distribute.mlir

[MLIR][XeGPU] Add 2D vector.multi_reduction optimization (#171154)

2026-01-14 12:58:30 +01:00

transform-ops-invalid.mlir

[MLIR][XeGPU][TransformOps] Add insert_prefetch op (#167356)

2025-11-12 10:24:23 +00:00

transform-ops.mlir

[MLIR][XeGPU] Refactor Layout access interface (#172125)

2025-12-17 12:04:58 -08:00

xegpu-attr-interface.mlir

[mlir][xegpu] Change index arithmetic ops to arith ops. (#170390)

2025-12-03 07:48:00 -08:00

xegpu-blocking.mlir

[MLIR][XeGPU] Propagate layout from anchor ops before Wg To Sg & Blocking Pass (#179490)

2026-02-06 15:56:09 -08:00

xegpu-fold-alias-ops.mlir

…

xegpu-unroll-patterns-no-desc-offsets.mlir

[mlir][XeGPU][XeGPUUnroll] Support new syntax with offsets moved to load_nd/store_nd/prefetch_nd (#160323)

2025-09-25 11:31:17 -07:00

xegpu-unroll-patterns.mlir

[MLIR][XeGPU] Refactor Layout access interface (#172125)

2025-12-17 12:04:58 -08:00

xegpu-vector-linearize.mlir

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

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

xegpu-wg-to-sg-elemwise.mlir

[MLIR][XeGPU] Propagate layout from anchor ops before Wg To Sg & Blocking Pass (#179490)

2026-02-06 15:56:09 -08:00

xegpu-wg-to-sg-rr.mlir

[MLIR][XeGPU] Propagate layout from anchor ops before Wg To Sg & Blocking Pass (#179490)

2026-02-06 15:56:09 -08:00

xegpu-wg-to-sg-unify-ops-rr.mlir

[MLIR][XeGPU] Propagate layout from anchor ops before Wg To Sg & Blocking Pass (#179490)

2026-02-06 15:56:09 -08:00

xegpu-wg-to-sg-unify-ops.mlir

[MLIR][XeGPU] Propagate layout from anchor ops before Wg To Sg & Blocking Pass (#179490)

2026-02-06 15:56:09 -08:00

xegpu-wg-to-sg.mlir

[MLIR][XeGPU] Propagate layout from anchor ops before Wg To Sg & Blocking Pass (#179490)

2026-02-06 15:56:09 -08:00