master

GGitHub[mlir] [linalg] Add pattern to swap transpose with broadcast (#97063)

9cc11b98创建于 2024年7月23日历史提交

文件	最后提交记录	最后更新时间
affine.mlir	[mlir][Linalg] NFC - Retire LinalgToLLVM pass	2 年前
block-pack-matmul-layout.mlir	[mlir][linalg] Block pack matmul pass (#89782)	2 年前
block-pack-matmul-padding.mlir	[mlir][linalg] Block pack matmul pass (#89782)	2 年前
block-pack-matmul.mlir	[mlir][linalg] Avoid emitting errors in block pack matmul (#93170)	2 年前
bubble-up-extract-slice-op.mlir	[MLIR] Generalize expand_shape to take shape as explicit input (#90040)	2 年前
bufferize.mlir	[mlir][linalg] Add bufferization for linalg.softmax (#97019)	1 年前
canonicalize.mlir	[mlir] [linalg] Add pattern to swap transpose with broadcast (#97063)	1 年前
collapse-dim.mlir	[MLIR] Generalize expand_shape to take shape as explicit input (#90040)	2 年前
constant-fold.mlir	[mlir][linalg] Add linalg.transpose constant folding (#92589)	2 年前
continuous-tiling-full.mlir	[mlir] Makes zip_shortest an optional keyword in transform.foreach (#98492)	1 年前
continuous-tiling-multiway-split.mlir	[MLIR] Add continuous tiling to transform dialect (#82792)	1 年前
conv-interface-invalid.mlir	Revert "Revert "[mlir][linalg] Replace "string" iterator_types attr with enums in LinalgInterface.""	3 年前
convert-conv2d-to-img2col.mlir	[MLIR] Generalize expand_shape to take shape as explicit input (#90040)	2 年前
convert-elementwise-to-linalg.mlir	[mlir][Pass] Include anchor op in -pass-pipeline	3 年前
data-layout-propagation.mlir	[mlir][Linalg] Allow propagation of pack through multi use pad (#98039)	1 年前
decompose-ops.mlir	[mlir][NFC] Remove trailing whitespaces from *.td and *.mlir files.	3 年前
detensorize_0d.mlir	[mlir][NFC] Remove trailing whitespaces from *.td and *.mlir files.	3 年前
detensorize_br_operands.mlir	[mlir][NFC] Remove trailing whitespaces from *.td and *.mlir files.	3 年前
detensorize_entry_block.mlir	[mlir] Fix block merging (#97697)	1 年前
detensorize_if.mlir	[mlir] Fix block merging (#97697)	1 年前
detensorize_trivial.mlir	[mlir][Pass] Include anchor op in -pass-pipeline	3 年前
detensorize_while.mlir	[mlir] Fix block merging (#97697)	1 年前
detensorize_while_impure_cf.mlir	[mlir] Fix block merging (#97697)	1 年前
detensorize_while_pure_cf.mlir	[mlir] Fix block merging (#97697)	1 年前
drop-unit-extent-dims.mlir	[mlir][test] Fix filecheck annotation typos [2/n] (#93476)	1 年前
erase-unused-operands-and-results.mlir	[mlir][linalg] Fold duplicate and unused inputs in linalg.generic	3 年前
fill-interface-invalid.mlir	[mlir][NFC] Update textual references of func to func.func in Linalg tests	4 年前
flatten-elementwise.mlir	[MLIR] Generalize expand_shape to take shape as explicit input (#90040)	2 年前
flatten-unsupported.mlir	[mlir][transform] Emit error message with emitSilenceableFailure (#86146)	2 年前
forward-vector-transfers.mlir	[mlir][NFC] Update textual references of func to func.func in Linalg tests	4 年前
fuse-with-reshape-by-collapsing.mlir	[mlir] Add reshape propagation patterns for tensor.pad (#94489)	1 年前
fusion-elementwise-ops.mlir	[mlir][test] Fix filecheck annotation typos [2/n] (#93476)	1 年前
fusion-elementwise-options.mlir	[mlir][Linalg] Avoid unnecessary propagating producer result to fused op result.	3 年前
fusion-elementwise.mlir	[mlir][Linalg] Avoid unnecessary propagating producer result to fused op result.	3 年前
fusion-multiuse-producer.mlir	[mlir][Linalg] Make Elementwise op fusion return a map from existing values to values in the fused op.	3 年前
fusion-push-reshape.mlir	[MLIR] Generalize expand_shape to take shape as explicit input (#90040)	2 年前
generalize-named-ops.mlir	[mlir][linalg] Add linalg.conv_2d_ngchw_gfchw_q to named ops (#92136)	2 年前
generalize-named-polymorphic-ops.mlir	Remove redundant linalg.matmul_signed (#98615)	1 年前
generalize-pad-tensor.mlir	[mlir][tensor] Make getMixedPadImpl return static values when possible. (#85016)	2 年前
generalize-tensor-pack-tile.mlir	[mlir][transform] Consistent linalg transform op syntax for dynamic index lists (#90897)	2 年前
generalize-tensor-pack.mlir	[mlir][Linalg] Add folders for linalg.transpose (#81709)	2 年前
generalize-tensor-unpack-tile.mlir	[mlir][transform] Consistent linalg transform op syntax for dynamic index lists (#90897)	2 年前
generalize-tensor-unpack.mlir	[mlir][Linalg] Add folders for linalg.transpose (#81709)	2 年前
hoisting.mlir	[mlir][vector] Make the in_bounds attribute mandatory (#97049)	1 年前
inline-scalar-operands.mlir	[mlir][NFC] Remove trailing whitespaces from *.td and *.mlir files.	3 年前
inlining.mlir	[mlir][NFC] Update textual references of func to func.func in Linalg tests	4 年前
int-narrowing.mlir	[mlir][arith] Add narrowing patterns for index casts	3 年前
invalid.mlir	[mlir][linalg] Implement Conv2D using Winograd Conv2D algorithm (#96181)	1 年前
library-calls.mlir	[MLIR][Linalg] Generate unique LibraryCallName for LinalgOps.	3 年前
loops.mlir	[mlir][Transforms] GreedyPatternRewriteDriver: Do not CSE constants during iterations (#75897)	2 年前
match-ops-interpreter.mlir	[mlir][linalg] Add a test for inferConvolutionDimsImpl (#90057)	2 年前
match-ops-invalid.mlir	[mlir][transform] Add elementwise criteria to match.structured.body (#79626)	2 年前
match-ops.mlir	[mlir] add structured (Linalg) transform op matchers	3 年前
matmul-shared-memory-padding.mlir	[mlir][transform] Consistent linalg transform op syntax for dynamic index lists (#90897)	2 年前
mesh-sharding-propagation.mlir	[mlir][mesh] Insert resharding during sharding propagation (#84514)	2 年前
mesh-spmdization.mlir	[mlir][mesh] Fix wrong argument passed to targetShardingInUnsplitLastAxis (#95059)	1 年前
multisize-tiling-full.mlir	[mlir][Transform] Extend transform.foreach to take multiple arguments (#93705)	1 年前
named-ops-fail.mlir	[MLIR][Linalg] Ternary Op & Linalg select (#91461)	2 年前
named-ops.mlir	[mlir][linalg] Add linalg.conv_2d_ngchw_gfchw_q to named ops (#92136)	2 年前
namedop_conversion.mlir	[mlir][linalg] Propagate attributes when doing named ops conversion.	3 年前
one-shot-bufferize-analysis-2fill-extract-matmul-all-perms.mlir	[mlir][linalg][NFC] Cleanup: Drop linalg.inplaceable attribute	3 年前
one-shot-bufferize-analysis.mlir	[mlir][bufferization] Fix bug in bufferization of elementwise ops (#97209)	1 年前
one-shot-bufferize-empty-tensor-elimination.mlir	[mlir][linalg] Fix for invalid IR in eliminate_empty_tensors (#73513)	2 年前
one-shot-bufferize.mlir	[mlir][bufferization] Add "bottom-up from terminators" analysis heuristic (#83964)	2 年前
pad-to-specific-memory-space.mlir	[mlir] use transform-interpreter in test passes (#70040)	2 年前
pad_fusion.mlir	[mlir][Affine] Delete duplicate code: applyMapToValues	2 年前
parallel-loops.mlir	[mlir][SCF] scf.parallel: Make reductions part of the terminator (#75314)	2 年前
promote.mlir	[mlir][memref] Improve memref.subview type inference (#96421)	1 年前
promotion_options.mlir	[mlir][transform] Consistent linalg transform op syntax for dynamic index lists (#90897)	2 年前
rank-reduce-contraction-ops.mlir	[mlir][linalg] Implement patterns for reducing rank of named linalg contraction ops (#95710)	1 年前
reshape_control_fusion.mlir	[MLIR] Generalize expand_shape to take shape as explicit input (#90040)	2 年前
reshape_fusion.mlir	[mlir] Add reshape propagation patterns for tensor.pad (#94489)	1 年前
resolve-shaped-type-result-dims.mlir	[MLIR] Generalize expand_shape to take shape as explicit input (#90040)	2 年前
roundtrip-linalg-named-ops.mlir	[MLIR][Linalg] Add pass to convert linalg.generic back to named ops (#95656)	1 年前
roundtrip.mlir	[mlir][linalg] Implement Conv2D using Winograd Conv2D algorithm (#96181)	1 年前
runtime-verification.mlir	[mlir][linalg] Add runtime verification for linalg ops (#89917)	2 年前
specialize-generic-ops.mlir	[MLIR][Linalg] Add pass to convert linalg.generic back to named ops (#95656)	1 年前
standard.mlir	[mlir][Linalg] Fix crash in LinalgToStandard	3 年前
subtensor-of-padtensor.mlir	[mlir][NFC] Update textual references of func to func.func in Linalg tests	4 年前
swap-extract-slice-with-fill.mlir	[mlir][linalg] Swap tensor.extract_slice(linalg.fill)	3 年前
test-drop-unit-dims.mlir	[mlir][Linalg] Cleanup the drop unit dims pass in Linalg.	2 年前
tile-and-fuse-tensors.mlir	[MLIR][Tensor] Add Destination style RewritePattern for DimOp. (#65780)	2 年前
tile-conv.mlir	[mlir][transform] Consistent linalg transform op syntax for dynamic index lists (#90897)	2 年前
tile-indexed.mlir	[mlir][transform] Consistent linalg transform op syntax for dynamic index lists (#90897)	2 年前
tile-softmax.mlir	[mlir][transform] Consistent linalg transform op syntax for dynamic index lists (#90897)	2 年前
tile-tensors.mlir	[mlir][transform] Consistent linalg transform op syntax for dynamic index lists (#90897)	2 年前
tile-to-forall.mlir	[mlir][transform] Consistent linalg transform op syntax for dynamic index lists (#90897)	2 年前
transform-lower-pack.mlir	[mlir][linalg] Support lowering unpack with outer_dims_perm (#94477)	1 年前
transform-op-bufferize-to-allocation.mlir	[mlir] introduce debug transform dialect extension (#77595)	2 年前
transform-op-compose-masked-vectorize-and-cleanups.mlir	[mlir][transform] Consistent linalg transform op syntax for dynamic index lists (#90897)	2 年前
transform-op-decompose.mlir	[mlir][linalg] Fix numerical issue with softmax (#96090)	1 年前
transform-op-fuse-into-containing.mlir	[mlir] introduce debug transform dialect extension (#77595)	2 年前
transform-op-fuse.mlir	[mlir][transform] Consistent linalg transform op syntax for dynamic index lists (#90897)	2 年前
transform-op-generalize.mlir	[mlir] use transform-interpreter in test passes (#70040)	2 年前
transform-op-gpu-map-copy-to-threads.mlir	[mlir] use transform-interpreter in test passes (#70040)	2 年前
transform-op-hoist-pad-build-packing-loop-nest.mlir	[mlir][transform] Consistent linalg transform op syntax for dynamic index lists (#90897)	2 年前
transform-op-hoist-pad.mlir	[mlir][transform] Consistent linalg transform op syntax for dynamic index lists (#90897)	2 年前
transform-op-insert-slice-to-copy.mlir	[mlir] use transform-interpreter in test passes (#70040)	2 年前
transform-op-interchange.mlir	[mlir] use transform-interpreter in test passes (#70040)	2 年前
transform-op-match.mlir	[mlir] introduce debug transform dialect extension (#77595)	2 年前