aboutsummaryrefslogtreecommitdiff
path: root/mlir/lib/Dialect/AMDGPU
AgeCommit message (Expand)AuthorFilesLines
3 days[mlir][AMDGPU] Avoid verifier crash in DPPOp on vector operand types (#178887)Ayush Kumar Gaur1-6/+0
4 days[mlir][AMDGPU] Add wrappers for in-memory barriers on gfx1250 (#180112)Krzysztof Drewniak1-0/+29
11 days[NFC][mlir][AMDGPU] Partition dialect .td into multiple files (#178562)Krzysztof Drewniak6-1207/+1288
12 days[mlir] Fix new clang-tidy warning llvm-type-switch-case-types. NFC. (#178487)Jakub Kuderski1-9/+8
2026-01-12[mlir][amdgpu] Remove redundant barriers (#175436)Ivan Butygin1-0/+15
2026-01-06[NFC][AMDGPU] Use getMixedSize in FatRawBufferCastOp dim reification (#174548)Jorn Tuyls1-6/+1
2026-01-02[mlir] Move affine's FoldMemRefAliasOps into its own pass (#172548)Krzysztof Drewniak1-10/+4
2025-12-24[mlir][amdgpu] Fix `gather_to_lds` for 0d memrefs (#173421)Ivan Butygin1-1/+1
2025-12-18[mlir][amdgpu] implement amdgpu.sparse_mfma wrapper for smfmac instructions (...Eric Feng1-0/+72
2025-12-15[mlir][AMDGPU] Add scaled wmma ops for gfx1250 (#169854)Justin Rosner1-0/+97
2025-12-15[mlir][amdgpu] Lower make_gather_dma_descriptor. (#172083)Erick Ochoa Lopez1-26/+58
2025-12-12[MLIR][AMDGPU] Implement reifyDimOfResult for FatRawBufferCastOp (#171839)Zhewen Yu1-0/+13
2025-12-12[mlir][amdgpu] Adds make_dma_gather_base (#171857)Erick Ochoa Lopez1-9/+33
2025-12-08[mlir][amdgpu] `memory_counter_wait` tensor counter support (#171153)Ivan Butygin1-3/+5
2025-12-08[mlir][amdgpu] Fuse adjacent `MemoryCounterWaitOp` (#171148)Ivan Butygin1-0/+45
2025-12-08[mlir][amdgpu] Add workgroup_mask to MakeDmaDescriptorOp (#171103)Tim Gymnich1-0/+3
2025-12-05[mlir][amdgpu] Add lowering for make_dma_descriptor (#169955)Erick Ochoa Lopez1-21/+66
2025-12-04[mlir][AMDGPU] Rename gfx1250 packed extension ops, change firstScaleLane (#1...Krzysztof Drewniak1-4/+4
2025-12-02[mlir][AMDGPU][NFC] Fix overlapping masked load refinements (#159805)Krzysztof Drewniak1-10/+24
2025-12-02[mlir][amdgpu] Lower amdgpu.make_dma_base (#169817)Erick Ochoa Lopez1-0/+18
2025-12-01[mlir][amdgpu] Add amdgpu.make_dma_descriptor (#169407)Erick Ochoa Lopez1-0/+38
2025-11-26[mlir][amdgpu] Add make_dma_base operation (#169086)Erick Ochoa Lopez1-0/+7
2025-11-17[mlir][amdgpu] Add lowerings for ScaledExtPacked816 (#168123)Erick Ochoa Lopez1-16/+29
2025-11-17[mlir][amdgpu] Fix documentation and verifiers (#167369)Erick Ochoa Lopez1-5/+18
2025-10-28[mlir][amdgpu][rocdl] Add gfx1250 wmma ops (#165064)Jakub Kuderski1-4/+6
2025-10-25[mlir][amdgpu] Update mfma assembly format with intrinsic shape (#165037)Jakub Kuderski1-3/+3
2025-10-24[mlir][amdgpu] Add explicit intrinsic shape to wmma (#164920)Jakub Kuderski1-27/+35
2025-10-17[mlir][amdgpu] Add scaled_ext_packed{8,16} operations (#159830)Erick Ochoa Lopez1-0/+19
2025-10-16[mlir][AMGPU] Replace use of SmallVector with ArrayRef, NFC (#163770)Muzammil1-4/+4
2025-10-10[mlir][amdgpu] Add Inliner interface (#162873)Ivan Butygin1-0/+11
2025-09-18[mlir][AMDGPU] Add canonicalization pattern to pack scales for ScaledMFMAOp (...Muzammil2-0/+138
2025-09-18[MLIR] Apply clang-tidy fixes for readability-identifier-naming in AMDGPUDial...Mehdi Amini1-3/+3
2025-09-02[MLIR][BUG] fix {$VARIABLE} usage in CMakeLists.txt (#156183)x123014501-1/+1
2025-08-21[mlir][AMDGPU] Add PermlaneSwapOp (#154345)Tim Gymnich1-0/+12
2025-08-08[mlir][amdgpu] fold memref.subview/expand_shape/collapse_shape into amdgpu.ga...sebvince1-46/+63
2025-08-07[mlir][AMDGPU] Allow non-contiguous destination memrefs for gather_to_lds (#1...Quinn Dawkins1-2/+2
2025-07-24[mlir][AMDGPU] Add canonicalizer for folding casts into gather_to_lds (#150503)Quinn Dawkins1-0/+40
2025-07-24[mlir][NFC] update `mlir/Dialect` create APIs (14/n) (#149920)Maksim Levental3-46/+48
2025-07-24Reapply "[AMDGPU] fold `memref.subview/expand_shape/collapse_shape` into `am...Alan Li2-1/+100
2025-07-23[mlir] Remove unused includes (NFC) (#150266)Kazu Hirata1-2/+0
2025-07-23Revert "[AMDGPU] fold `memref.subview/expand_shape/collapse_shape` in… (#15...Alan Li2-99/+1
2025-07-23[AMDGPU] fold `memref.subview/expand_shape/collapse_shape` into `amdgpu.gathe...Alan Li2-1/+99
2025-07-21[mlir][AMDGPU] Infer canonical layouts for fat_raw_buffer_cast resetOffset (#...Krzysztof Drewniak1-1/+17
2025-07-18[mlir][amdgpu] Properly handle mismatching memref ranks in `amdgpu.gather_to_...Ivan Butygin1-0/+4
2025-07-13[mlir] Remove unused includes (NFC) (#148535)Kazu Hirata1-1/+0
2025-07-10[mlir][AMDGPU] Add better load/store lowering for full mask (#146748)Kunwar Grover1-6/+82
2025-07-09[AMDGPU] [MLIR] Add 96 and 128 bit GatherToLDS for gfx950 (#147496)Daniel Hernandez-Juarez1-4/+5
2025-07-02[MLIR][AMDGPU] Redirect transfer read to masked load lowering (#146705)Zhuoran Yin3-240/+168
2025-06-25[AMDGPU] Adding AMDGPU dialect wrapper for ROCDL transpose loads. (#145395)Alan Li1-0/+34
2025-06-18[mlir][amdgpu][nfc] Add PatternBenefit to populate methods (#144663)Kunwar Grover3-6/+7
generated by cgit v1.1 at 2026-02-10 06:31:51 +0000