Max191 08efa23083

[mlir] Allow multi-result ops in reshape fusion (#108576) ...

Fusion of reshapes by collapsing patterns were restricted to single
result operations, but the implementation supports multi result ops.
This PR removes the restriction, since it is not necessary.

2024-09-16 13:06:38 -04:00

..

Affine

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

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

AMDGPU

[mlir][AMDGPU] Enable emulating vector buffer_atomic_fadd on gfx11 (#108312)

2024-09-12 09:47:52 -05:00

AMX

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

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

Arith

[mlir][arith] Match folding of arith.remf to llvm.frem semantics (#96537)

2024-06-25 21:01:18 +02:00

ArmNeon

[mlir][ArmNeon] Update LowerContractionToSMMLAPattern to support proper unrolling for k dimension (#88591)

2024-04-19 16:49:25 +02:00

ArmSME

[mlir][ArmSME] Rename slice move operations to insert/extract_tile_slice (#106755)

2024-09-02 11:12:40 +01:00

ArmSVE

[mlir][ArmSVE] Add arm_sve.psel operation (#95764)

2024-06-19 13:33:23 +01:00

Async

[mlir][async] Avoid crash when not using func.func (#72801)

2023-11-21 08:40:16 +01:00

Bufferization

[mlir][Transforms] Dialect conversion: Make materializations optional (#107109)

2024-09-05 19:40:58 +02:00

Builtin

…

Complex

[mlir][complex] Canonicalize complex.div by one (#85513)

2024-03-26 13:50:28 +09:00

ControlFlow

[MLIR][CF] Fix cf.switch parsing with result numbers (#87658)

2024-04-04 21:32:47 +02:00

DLTI

[MLIR][DLTI] Enable types as keys in DLTI-query utils (#105995)

2024-08-27 04:41:15 -07:00

EmitC

[MLIR][EmitC] Allow ptrdiff_t as result in sub op (#104921)

2024-08-20 17:36:51 +02:00

Func

[mlir][transform] Add an op for replacing values with function calls (#78398)

2024-01-19 13:21:52 -05:00

GPU

[Func][GPU] Use SymbolUserOpInterface in func::ConstantOp (#107748)

2024-09-09 11:49:16 +02:00

Index

[mlir][Arith] Generalize and improve -int-range-optimizations (#94712)

2024-06-10 09:56:33 -05:00

IRDL

[mlir][irdl] Lookup symbols near dialects instead of locally (#92819)

2024-05-31 09:15:50 +01:00

Linalg

[mlir] Allow multi-result ops in reshape fusion (#108576)

2024-09-16 13:06:38 -04:00

LLVM

[mlir][Conversion] Generalize and fix crash in reconcile-unrealized-casts (#95700)

2024-06-19 16:23:27 +02:00

LLVMIR

[mlir] Fix crash in InsertOpConstantFolder when vector.insert operand is from a llvm.mlir.constant op (#88314)

2024-09-09 01:44:30 +02:00

Math

[MLIR][MathDialect] fix fp32 promotion crash when encounters scf.if (#104451)

2024-08-21 10:08:56 +08:00

MemRef

[memref] Handle edge case in subview of full static size fold (#105635)

2024-08-23 06:52:09 +01:00

Mesh

[mlir][mesh] Introduce DialectInlinerInterface for Mesh dialect (#108297)

2024-09-13 16:39:45 -07:00

MLProgram

[mlir] Make the ml_program dialect allow all of its operations to be inlined. (#85479)

2024-03-15 22:22:09 -07:00

MPI

[mlir] Reland "Initial patch to add an MPI dialect" (#81975)

2024-02-16 20:58:10 +05:30

NVGPU

[mlir][nvgpu] Add nvgpu.rcp OP (#100965)

2024-07-30 09:20:49 +02:00

OpenACC

[acc] Add attribute for combined constructs (#80319)

2024-03-07 10:06:47 -08:00

OpenMP

[MLIR][OpenMP] Improve assemblyFormat handling for clause-based ops (#108023)

2024-09-13 12:57:41 +01:00

PDL

Reapply "[mlir][PDL] Add support for native constraints with results (#82760)"

2024-03-02 20:57:30 +01:00

PDLInterp

Finish renaming getOperandSegmentSizeAttr() from operand_segment_sizes to operandSegmentSizes

2023-08-09 19:37:01 -07:00

Polynomial

[mlir][polynomial] ensure primitive root calculation doesn't overflow (#93368)

2024-05-31 11:56:54 -07:00

Ptr

[mlir][Ptr] Init the Ptr dialect with the !ptr.ptr type. (#86860)

2024-06-27 07:14:34 -05:00

Quant

…

SCF

[MLIR][SCF] Add support for loop pipeline peeling for dynamic loops. (#106436)

2024-09-04 12:24:58 -07:00

Shape

[mlir] New canonicalization patterns for shape.shape_of and tensor.reshape (#98531)

2024-07-19 10:09:31 -04:00

SparseTensor

[mlir][sparse] add parallelization options to mini pipeline (#104233)

2024-08-30 17:47:37 -04:00

SPIRV

[mlir][spirv] Add GroupNonUniformBallotFindLSB and GroupNonUniformBallotFindMSB ops (#104791)

2024-08-19 13:52:18 -04:00

Tensor

[mlir][tensor] Add canonicalization to fold consecutive tensor.pad ops (#107302)

2024-09-09 11:05:37 -04:00

Tosa

[MLIR][TOSA] Add --tosa-reduce-transposes pass (#108260)

2024-09-13 19:16:55 -07:00

Transform

[MLIR][Transform] Allow stateInitializer and stateExporter for applyTransforms (#101186)

2024-09-09 10:57:13 -04:00

UB

[MLIR][UB] Add inliner interface for UB dialect (#67115)

2023-09-22 14:07:47 +02:00

Vector

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

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

X86Vector

…

XeGPU

[MLIR][XeGPU] Refine XeGPU definitions (#100763)

2024-08-02 17:10:02 -05:00

traits.mlir

Released restriction that prevented implicit dynamic-to-static dimension type cast in TOSA ops.

2023-08-01 08:57:08 -07:00