lialan ce112a7f44

[MLIR] support dynamic indexing in VectorEmulateNarrowTypes (#114169) ...

* Supports `vector.load` and `vector.transfer_read` ops.
* In the case of dynamic indexing, use per-element insertion/extraction
to build desired narrow type vectors.
* Fixed wrong function comment of `getCompressedMaskOp`.

---------

Co-authored-by: Han-Chung Wang <hanhan0912@gmail.com>

2024-11-05 09:21:03 -08:00

..

CPU/X86

[mlir][vector] Update tests/patterns for vector.transpose (#91359)

2024-05-13 08:13:51 +01:00

break-down-vector-reduction.mlir

[mlir][vector][gpu] Align minf/maxf reduction kind names with arith (#75901)

2023-12-20 00:14:43 -05:00

bufferize-invalid.mlir

[mlir] Remove dialect specific bufferization passes (Reland) (#93535)

2024-05-28 20:04:27 +01:00

bufferize.mlir

[mlir] Remove dialect specific bufferization passes (Reland) (#93535)

2024-05-28 20:04:27 +01:00

canonicalize.mlir

[MLIR][Vector] Add Lowering for vector.step (#113655)

2024-11-01 16:38:36 +00:00

chained-vector-reduction-folding.mlir

[mlir][vector] Add patterns to simplify chained reductions (#73048)

2023-11-22 10:30:04 -05:00

constant-fold.mlir

[mlir][vector] add result type to vector.extract assembly format (#66499)

2023-09-28 11:11:16 +01:00

drop-unit-dims-with-shape-cast.mlir

[mlir][vector] Add pattern for dropping unit dims from for loops (#109585)

2024-09-27 11:43:27 -04:00

eliminate-masks.mlir

[mlir][vector] Add mask elimination transform (#99314)

2024-08-09 10:51:49 +01:00

fold-arith-extf-into-vector-contract.mlir

[mlir][vector] Generalize folding of ext-contractionOp to other types. (#96593)

2024-06-25 09:29:43 -07:00

inlining.mlir

[mlir][Vector] Add initial support for inlining in the presence of vector ops (#70942)

2023-11-01 16:34:04 +01:00

int-range-interface.mlir

[mlir] IntegerRangeAnalysis: handle vector types in getDestWidth() (#114898)

2024-11-05 10:43:16 -06:00

invalid.mlir

[MLIR][Vector] Update Transfer{Read|Write}DropUnitDimsPattern patterns (#112394)

2024-10-26 13:54:04 +01:00

linearize.mlir

[mlir][vector] Bugfix of linearize vector.extract (#106836)

2024-09-04 16:41:56 +08:00

lower-vector-mask.mlir

[mlir][vector] Handle empty MaskOp in LowerVectorMask, MaskOpRewritePattern (#72031)

2023-11-12 08:12:28 +01:00

one-shot-bufferize.mlir

[mlir][vector] Add tests for scalable vectors in one-shot-bufferize.mlir (#102361)

2024-08-09 13:49:49 +01:00

ops.mlir

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

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

scalar-vector-transfer-to-memref.mlir

[mlir][vector] add result type to vector.extract assembly format (#66499)

2023-09-28 11:11:16 +01:00

shape-cast-folder.mlir

[mlir][vector] Add a new TD Op for patterns leveraging ShapeCastOp (#110525)

2024-10-01 10:08:43 +01:00

test-create-broadcast.mlir

…

test-scalable-bounds.mlir

[mlir][vector] Project out anonymous bounds in ScalableValueBoundsConstraintSet (#96499)

2024-07-03 10:04:51 +01:00

transform-op-vector-to-llvm.mlir

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

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

transform-vector.mlir

Revert "[MLIR] Make OneShotModuleBufferize use OpInterface (#110322)" (#113124)

2024-10-22 13:28:44 +01:00

value-bounds-op-interface-impl.mlir

…

vector-bitcast-lowering-transforms.mlir

[mlir][vector] Support scalable vectors when unrolling vector.bitcast (#94197)

2024-06-21 14:38:19 +01:00

vector-break-down-bitcast.mlir

…

vector-broadcast-lowering-transforms.mlir

[mlir][Transforms] GreedyPatternRewriteDriver: Do not CSE constants during iterations (#75897)

2024-01-05 09:22:18 +01:00

vector-contract-matmul-transforms.mlir

…

vector-contract-to-dot-transforms.mlir

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

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

vector-contract-to-matrix-intrinsics-transforms.mlir

[nlir][vector] Constrain ContractionOpToMatmulOpLowering (#102225)

2024-08-07 10:18:14 +01:00

vector-contract-to-outerproduct-matmul-transforms.mlir

[mlir][nfc] Update tests for Contract -> Op transforms (#76054)

2023-12-21 13:20:16 +00:00

vector-contract-to-outerproduct-matvec-transforms.mlir

[mlir] split transform interfaces into a separate library (#85221)

2024-03-20 22:15:17 +01:00

vector-contract-to-parallel-arith-transforms.mlir

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

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

vector-deinterleave-lowering-transforms.mlir

[mlir][vector] Add n-d deinterleave lowering (#94237)

2024-06-07 10:57:00 +01:00

vector-dropleadunitdim-transforms.mlir

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

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

vector-emulate-masked-load-store.mlir

[mlir][vector] Add emulation patterns for vector masked load/store (#74834)

2023-12-15 11:35:48 +00:00

vector-emulate-narrow-type-unaligned.mlir

[MLIR] support dynamic indexing in VectorEmulateNarrowTypes (#114169)

2024-11-05 09:21:03 -08:00

vector-emulate-narrow-type.mlir

[mlir][vector] Add support for vector.maskedstore sub-type emulation. (#73871)

2023-11-30 11:27:06 -08:00

vector-extract-strided-slice-lowering.mlir

[mlir][vector] add result type to vector.extract assembly format (#66499)

2023-09-28 11:11:16 +01:00

vector-gather-lowering.mlir

[mlir][vector] Fix FlattenGather for scalable vectors (#96074)

2024-06-24 08:36:06 +01:00

vector-interleave-lowering-transforms.mlir

[mlir][vector] Add result type to interleave assembly format (#93392)

2024-05-27 11:03:36 -04:00

vector-interleave-to-shuffle.mlir

[mlir][vector] Add result type to interleave assembly format (#93392)

2024-05-27 11:03:36 -04:00

vector-mask-lowering-transforms.mlir

[mlir][Transforms] GreedyPatternRewriteDriver: Do not CSE constants during iterations (#75897)

2024-01-05 09:22:18 +01:00

vector-materialize-mask.mlir

[mlir] split transform interfaces into a separate library (#85221)

2024-03-20 22:15:17 +01:00

vector-mem-transforms.mlir

…

vector-multi-reduction-lowering.mlir

[MLIR][Vector] Add a test of <2x[4]xf32> type on lowering multireduction (#100451)

2024-07-25 13:39:57 -07:00

vector-multi-reduction-outer-lowering.mlir

[mlir] split transform interfaces into a separate library (#85221)

2024-03-20 22:15:17 +01:00

vector-multi-reduction-pass-lowering.mlir

[mlir][vector] Add lower-vector-multi-reduction pass (#87333)

2024-04-09 10:04:25 -07:00

vector-outerproduct-lowering-transforms.mlir

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

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

vector-reduce-to-contract.mlir

[mlir][vector] Group re-order patterns together (#102856)

2024-08-16 16:53:53 +01:00

vector-rewrite-narrow-types.mlir

[mlir][vector] Support n-D vectors in i8 to i4 trunci emulation (#94946)

2024-06-24 10:24:28 +01:00

vector-scalable-create-mask-lowering.mlir

[mlir][Transforms] GreedyPatternRewriteDriver: Do not CSE constants during iterations (#75897)

2024-01-05 09:22:18 +01:00

vector-scan-transforms.mlir

[mlir][vector] add result type to vector.extract assembly format (#66499)

2023-09-28 11:11:16 +01:00

vector-shape-cast-lowering-scalable-vectors.mlir

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

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

vector-shape-cast-lowering-transforms.mlir

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

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

vector-sink.mlir

[mlir][vector] Group re-order patterns together (#102856)

2024-08-16 16:53:53 +01:00

vector-transfer-collapse-inner-most-dims.mlir

[mlir][test] Add comments in a test (nfc) (#99810)

2024-07-21 17:44:12 +01:00

vector-transfer-drop-unit-dims-patterns.mlir

[MLIR][Vector] Update Transfer{Read|Write}DropUnitDimsPattern patterns (#112394)

2024-10-26 13:54:04 +01:00

vector-transfer-flatten.mlir

[mlir][vector][test] Split tests from vector-transfer-flatten.mlir (#102584)

2024-08-09 18:04:25 +01:00

vector-transfer-full-partial-split-copy-transform.mlir

[mlir] split transform interfaces into a separate library (#85221)

2024-03-20 22:15:17 +01:00

vector-transfer-full-partial-split.mlir

[mlir] split transform interfaces into a separate library (#85221)

2024-03-20 22:15:17 +01:00

vector-transfer-permutation-lowering.mlir

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

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

vector-transfer-to-vector-load-store.mlir

[mlir][Vector] Support 0-d vectors natively in TransferOpReduceRank (#112907)

2024-10-22 15:50:16 +01:00

vector-transfer-unroll.mlir

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

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

vector-transferop-opt.mlir

[mlir][vector] Add all view-like ops to transfer flow opt (#110521)

2024-10-02 00:20:44 -04:00

vector-transforms.mlir

[mlir][vector] Add a new TD Op for patterns leveraging ShapeCastOp (#110525)

2024-10-01 10:08:43 +01:00

vector-transpose-lowering.mlir

[mlir][vector] Update tests/patterns for vector.transpose (#91359)

2024-05-13 08:13:51 +01:00

vector-unroll-options.mlir

…

vector-warp-distribute.mlir

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

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