Chris Lattner a004da0d77 [Canonicalize] Switch the default setting to "top down". ...

This provides a sizable compile time improvement by seeding
the worklist in an order that leads to less iterations of the
worklist.

This patch only changes the behavior of the Canonicalize pass
itself, it does not affect other passes that use the
GreedyPatternRewrite driver

Differential Revision: https://reviews.llvm.org/D103053

2021-05-25 13:42:11 -07:00

..

canonicalize.mlir

[Canonicalize] Switch the default setting to "top down".

2021-05-25 13:42:11 -07:00

invalid.mlir

[mlir] Improve TransferOp verifier: broadcasts are in_bounds

2021-05-17 22:35:44 +09:00

ops.mlir

[mlir] Allow empty position in vector.insert and vector.extract

2021-05-13 12:54:18 +09:00

vector-contract-matvec-transforms.mlir

[MLIR] Create memref dialect and move dialect-specific ops from std.

2021-03-15 11:14:09 +01:00

vector-contract-transforms.mlir

[testsuite] Make testsuite more stable vs canonicalization change. NFC.

2021-03-19 18:11:12 -07:00

vector-distribution.mlir

[mlir][vector] Support N-D vector in InsertMap/ExtractMap op

2020-11-13 12:40:17 -08:00

vector-flat-transforms.mlir

[testsuite] Make testsuite more stable vs canonicalization change. NFC.

2021-03-19 18:11:12 -07:00

vector-mem-transforms.mlir

[mlir][vector] canonicalize unmasked gather/scatter/compress/expand directly into l/s

2021-03-05 14:23:50 -08:00

vector-multi-reduction-lowering.mlir

Add patterns to lower vector.multi_reduction into a sequence of vector.reduction

2021-04-30 10:52:21 -07:00

vector-slices-transforms.mlir

Enable FileCheck -enable-var-scope by default in MLIR test

2020-06-12 00:43:09 +00:00

vector-transfer-full-partial-split.mlir

Support VectorTransfer splitting on writes also.

2021-05-11 10:33:27 +02:00

vector-transfer-lowering-to-scf.mlir

[mlir] Use VectorTransferPermutationMapLoweringPatterns in VectorToSCF

2021-05-19 14:46:19 +09:00

vector-transfer-lowering.mlir

[mlir] Lower permutation maps on TransferWriteOps

2021-05-17 15:30:46 +09:00

vector-transfer-unroll.mlir

[mlir][vector] Extend vector transfer unrolling to support permutations and broadcast

2021-05-03 10:47:02 -07:00

vector-transferop-opt.mlir

[mlir][vector] Move transferOp on tensor opt to folder/canonicalization

2021-04-16 08:13:10 -07:00

vector-transforms.mlir

[mlir][vector] Extend pattern to trim lead unit dimension to Splat Op

2021-05-07 13:54:41 -07:00

vector-unroll-options.mlir

[mlir][vector] Add support for unrolling vector.fma

2021-02-16 09:56:25 -05:00