llvm-project

History

[mlir][gpu]add AffineScope to gpu.func op. (#118010 )

This PR in order to solve the following problem.
https://github.com/llvm/llvm-project/pull/117721.
To efficiently implement the thread-to-data mapping relationship, I
introduced AffineScope in gpu.func(Data or thread layout).

2024-11-29 11:10:00 +01:00

SuperVectorize

[mlir][vector] Relax the requirements on broadcast dims (#99341 )

2024-10-04 07:41:20 +01:00

access-analysis.mlir

[MLIR][Affine] Fix/complete access index invariance, add isInvariantAccess (#84602 )

2024-03-14 09:14:21 +05:30

affine-data-copy.mlir

[MLIR] Fix unchecked use of memref memory space attr in affine data copy generate (#116763 )

2024-11-23 07:06:06 +05:30

affine-expand-index-ops-as-affine.mlir

[mlir][Affine] Expand affine.[de]linearize_index without affine maps (#116703 )

2024-11-21 11:36:32 -06:00

affine-expand-index-ops.mlir

[mlir][Affine] Expand affine.[de]linearize_index without affine maps (#116703 )

2024-11-21 11:36:32 -06:00

affine-loop-invariant-code-motion.mlir

[MLIR] Fix arbitrary checks in affine LICM (#116469 )

2024-11-23 07:07:56 +05:30

affine-loop-normalize.mlir

…

canonicalize.mlir

[MLIR][Affine] Update ::fold() to have constant basis attr for affine.delinearize_index/linearize_index (#117572 )

2024-11-29 10:22:23 +05:30

constant-fold.mlir

[mlir][affine] Add dependency on UBDialect for PoisonAttr (#77691 )

2024-01-11 19:52:15 +01:00

decompose-affine-ops.mlir

…

dma-generate.mlir

…

dma.mlir

…

inlining.mlir

…

invalid.mlir

[mlir][Affine] Let affine.[de]linearize_index omit outer bounds (#116103 )

2024-11-18 15:41:54 -06:00

load-store-invalid.mlir

[mlir][affine] Fix dim index out of bounds crash (#73266 )

2023-11-28 07:35:09 +01:00

load-store.mlir

…

loop-coalescing.mlir

[mlir][affine] Add static basis support to affine.delinearize (#113846 )

2024-11-04 14:59:13 -06:00

loop-fusion-2.mlir

…

loop-fusion-3.mlir

[mlir][test] Fix filecheck annotation typos [2/n] (#93476 )

2024-06-14 17:16:02 +02:00

loop-fusion-4.mlir

[mlir][bufferization] Fix OneShotBufferize when defaultMemorySpaceFn is used (#91524 )

2024-11-26 09:45:57 -07:00

loop-fusion-dependence-check.mlir

[MLIR] Clean up pass options for test-loop-fusion and affine-super-vectorizer-test (#87606 )

2024-04-04 12:26:33 +02:00

loop-fusion-inner.mlir

Generalize affine fusion to work at all depths and inside other region-holding ops (#72288 )

2023-11-16 08:52:12 +05:30

loop-fusion-scf-mixed.mlir

[MLIR][Affine] Generalize/fix mdg init for region-holding ops with known control flow (#71754 )

2023-11-09 19:54:00 +05:30

loop-fusion-slice-computation.mlir

[MLIR] Clean up pass options for test-loop-fusion and affine-super-vectorizer-test (#87606 )

2024-04-04 12:26:33 +02:00

loop-fusion-transformation.mlir

[MLIR] Clean up pass options for test-loop-fusion and affine-super-vectorizer-test (#87606 )

2024-04-04 12:26:33 +02:00

loop-fusion.mlir

[mlir] fix affine-loop-fusion crash (#76351 )

2023-12-29 10:51:51 +08:00

loop-permute.mlir

…

loop-tiling-parametric.mlir

[mlir] cleanup of structured.tile* transform ops (#67320 )

2023-09-26 09:14:29 +02:00

loop-tiling-validity.mlir

[MLIR][Affine] NFC. Expose affine loop tiling validity utility (#99459 )

2024-07-18 22:06:44 +05:30

loop-tiling.mlir

[mlir] cleanup of structured.tile* transform ops (#67320 )

2023-09-26 09:14:29 +02:00

loop-unswitch.mlir

…

memref-bound-check.mlir

[MLIR] NFC. Move remaining affine test cases to its dialect dir (#67921 )

2023-10-06 08:32:49 +05:30

memref-dependence-check.mlir

[MLIR] NFC. Move remaining affine test cases to its dialect dir (#67921 )

2023-10-06 08:32:49 +05:30

memref-stride-calculation.mlir

[mlir] [IR] Allow zero strides in StridedLayoutAttr (#116463 )

2024-11-21 14:17:28 +08:00

ops.mlir

[mlir][gpu]add AffineScope to gpu.func op. (#118010 )

2024-11-29 11:10:00 +01:00

parallelize.mlir

…

pipeline-data-transfer.mlir

…

scalrep.mlir

[mlir][affine] Fix the crash due to the simultaneous replacement store (#90829 )

2024-09-06 08:21:47 +09:00

simplify-structures.mlir

[mlir][affine] fix the issue of ceildiv-mul-ceildiv form expression not satisfying commutative (#111254 )

2024-10-12 11:25:57 -04:00

slicing-utils.mlir

[MLIR][Analysis] Consolidate topological sort utilities (#92563 )

2024-05-22 08:48:10 +02:00

transform-op-simplify-bounded-affine-ops.mlir

[mlir] use transform-interpreter in test passes (#70040 )

2023-10-24 16:12:34 +02:00

unroll-jam.mlir

…

unroll.mlir

[mlir][test] Fix filecheck annotation typos [2/n] (#93476 )

2024-06-14 17:16:02 +02:00

value-bounds-op-interface-impl.mlir

[mlir][Interfaces] Variable abstraction for ValueBoundsOpInterface (#87980 )

2024-04-16 10:59:02 +02:00

value-bounds-reification.mlir

[mlir][Interfaces][NFC] Add TableGen test op for value bounds tests (#88717 )

2024-04-15 18:14:18 +02:00