Muzammil c409da2223 [mlir][ROCDL] Add permlanex16 op to allow subgroup reductions on gfx10+ (#135983) ...

Adding Permlanex16Op to ROCDL dialect to enable subgroup reduce lowering
to DPP ops for gfx 10+ devices.
See [this PR](https://github.com/llvm/llvm-project/pull/133204).

---------

Signed-off-by: Muzammiluddin Syed <muzasyed@amd.com>

2025-04-16 16:53:17 -05:00

..

Affine

[MLIR][Affine] Fix getAccessRelation for 0-d memrefs (#132347)

2025-03-21 14:35:20 +05:30

AMDGPU

[MLIR][AMDGPU] Adding dynamic size check to avoid subword buffer load (#135014)

2025-04-15 16:36:25 -04:00

AMX

[MLIR] [AMX] Utilize x86_amx type for AMX dialect in MLIR. (#111197)

2024-11-06 14:30:53 +00:00

Arith

[mlir] [arith] Fix ceildivsi lowering in arith-expand (#133774)

2025-04-02 17:26:58 +01:00

ArmNeon

…

ArmSME

[mlir][ArmSME] Fix crash on empty vector.mask in arm-sme-vector-legalization (#118613)

2024-12-05 08:48:30 +00:00

ArmSVE

[mlir][Arith] Remove arith-to-llvm from func-to-llvm (#120548)

2024-12-20 10:14:04 +01:00

Async

…

Bufferization

[mlir][bufferization] Add tensor-like and buffer-like interfaces (#134220)

2025-04-15 11:38:49 +02:00

Builtin

…

Complex

…

ControlFlow

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

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

DLTI

[MLIR][DLTI] Pretty parsing and printing for DLTI attrs (#113365)

2024-10-31 19:18:24 +00:00

EmitC

[mlir][IR] Improve error message when parsing incorrect type (#134984)

2025-04-09 17:49:47 +02:00

Func

[mlir][func] Remove func-bufferize pass (#114152)

2024-11-20 09:29:26 +09:00

GPU

[mlir] GPUToROCDL: Fix crashes with unsupported shuffle datatypes (#135504)

2025-04-13 20:26:19 +02:00

Index

[MLIR] Add canonicalizations to all eligible index binary ops (#114000)

2024-11-04 13:24:22 -08:00

IRDL

[mlir][irdl] Introduce names in IRDL value lists (#123525)

2025-01-19 21:58:52 +01:00

Linalg

[MLIR][Tensor] Remove tensor.dim canonicalization patterns registered on tensor.expand_shape/tensor.collapse_shape (#134219)

2025-04-11 06:57:34 -04:00

LLVM

[mlir][LLVM] Switch undef for poison for uninitialized values (#125629)

2025-02-06 12:49:30 -06:00

LLVMIR

[mlir][ROCDL] Add permlanex16 op to allow subgroup reductions on gfx10+ (#135983)

2025-04-16 16:53:17 -05:00

Math

[mlir][math] powi with negative exponent should invert at the end (#135735)

2025-04-15 08:02:11 -07:00

MemRef

[mlir][vector] Tighten the semantics of vector.{load|store} (#135151)

2025-04-11 20:08:08 +01:00

Mesh

[mlir][mesh] Exit after signalPassFailure to fix a crash (#132662)

2025-03-24 20:19:56 +08:00

MLProgram

…

MPI

[mlir][mpi] Mandatory Communicator (#133280)

2025-04-01 08:58:55 +02:00

NVGPU

[mlir][nvgpu] Fix crash when handling 0D memref in OptimizeSharedMemoryPass (#124517)

2025-01-28 09:19:51 +08:00

OpenACC

[mlir][acc] Handle OpenACC host_data in LegalizeDataValues (#134767)

2025-04-14 16:29:17 -07:00

OpenMP

[mlir][OpenMP] allow cancellation to not be directly nested (#134084)

2025-04-14 10:39:03 +01:00

PDL

…

PDLInterp

…

Polynomial

…

Ptr

[mlir][Ptr] Add the MemorySpaceAttrInterface interface and dependencies. (#86870)

2025-03-19 10:55:24 -04:00

Quant

Sub-channel quantized type implementation (#120172)

2025-03-23 07:37:55 -05:00

SCF

[mlir][Bufferization] Do not have read semantics for destination of tensor.parallel_insert_slice. (#134169)

2025-04-03 09:47:36 -07:00

Shape

[MLIR][Shape] Support >2 args in shape.broadcast folder (#126808)

2025-04-14 13:50:52 -04:00

SMT

[mlir][SMT] upstream SMT dialect (#131480)

2025-04-11 17:10:09 -04:00

SparseTensor

[mlir][IR] Improve error message when parsing incorrect type (#134984)

2025-04-09 17:49:47 +02:00

SPIRV

[mlir][spirv] Add verification for Bias operand (#134231)

2025-04-04 09:41:54 +01:00

Tensor

[mlir][Tensor] Generalize the pattern to swap tensor.collapse_shape -> tensor.expand_shape. (#133819)

2025-04-15 14:10:18 -07:00

Tosa

[mlir][tosa] Add verifier check for Slice Op (#135853)

2025-04-16 13:58:42 -07:00

Transform

[mlir][irdl] Introduce names in IRDL value lists (#123525)

2025-01-19 21:58:52 +01:00

UB

…

Vector

[mlir][vector] Move extract_strided_slice canonicalization to folding (#135676)

2025-04-16 16:20:05 -04:00

X86Vector

[mlir][x86vector] Simplify intrinsic generation (#133692)

2025-04-09 19:59:37 +02:00

XeGPU

[MLIR][XeGPU] Extend SGMapAttr and Add ConvertLayoutOp (#132425)

2025-04-08 19:46:05 -05:00

traits.mlir

…