aboutsummaryrefslogtreecommitdiff
path: root/mlir/lib/Dialect/SparseTensor/Transforms/SparseGPUCodegen.cpp
AgeCommit message (Expand)AuthorFilesLines
2025-07-25[mlir][NFC] update `mlir/Dialect` create APIs (33/n) (#150659)Maksim Levental1-5/+5
2025-07-22[mlir][NFC] update `mlir/Dialect` create APIs (21/n) (#149928)Maksim Levental1-139/+146
2025-06-18[mlir][bufferization] Support custom types (1/N) (#142986)Andrei Golubev1-6/+9
2025-05-14[mlir][bufferization][NFC] Rename to_memref to to_buffer (#137180)Andrei Golubev1-1/+1
2025-05-05[mlir] Remove unused local variables (NFC) (#138481)Kazu Hirata1-1/+0
2025-01-29Fix typo "tranpose" (#124929)Jay Foad1-1/+1
2024-09-30[mlir][NFC] Minor cleanup around `ModuleOp` usage (#110498)Matthias Springer1-2/+2
2024-03-06[mlir][sparse] use a consistent order between [dis]assembleOp and sto… (#84...Peiming Liu1-2/+2
2024-02-28[mlir][sparse] code cleanup (using inferred type to construct to_[buf… (#83...Peiming Liu1-9/+9
2024-02-12Apply clang-tidy fixes for modernize-loop-convert in SparseGPUCodegen.cpp (NFC)Mehdi Amini1-2/+2
2024-02-08[mlir][sparse] Implement parsing n out of m (#79935)Yinying Li1-1/+1
2024-02-08[MLIR] Fix crash in AffineMap::replace for zero result maps (#80930)Uday Bondhugula1-1/+3
2024-01-02[mlir][sparse] recognize NVidia 2:4 type for matmul (#76758)Aart Bik1-1/+27
2023-12-20[mlir][SCF] `scf.parallel`: Make reductions part of the terminator (#75314)Matthias Springer1-0/+3
2023-12-17[mlir][SparseTensor][NFC] Remove `isNestedIn` helper function (#75729)Matthias Springer1-10/+1
2023-12-15[NFC][mlir][sparse] remove redundant parameter. (#75551)Peiming Liu1-2/+2
2023-12-12[mlir][sparse] refactor utilities into transform/utils dir (#75250)Aart Bik1-2/+2
2023-12-07[mlir][SparseTensor] Fix invalid IR in `ForallRewriter` pattern (#74547)Matthias Springer1-0/+4
2023-11-14[mlir][sparsifier] fix `isAdmissibleBSR` (#72195)Maksim Levental1-1/+1
2023-11-08[mlir][sparse][gpu] cleanup GPUDataTransferStrategy (#71615)Aart Bik1-166/+55
2023-11-07Changed the phrase sparse-compiler to sparsifier in comments (#71578)Tim Harvey1-3/+3
2023-10-19[mlir][sparse] support BSR for cuSPARSE (libgen path only) (#69646)Aart Bik1-19/+50
2023-09-28[mlir][sparse][gpu] add CSC to libgen GPU sparsification using cuSparse (#67713)Aart Bik1-64/+91
2023-09-28[mlir][sparse] rename sparse_tensor.(un)pack to sparse_tensor.(dis)as… (#67...Peiming Liu1-3/+4
2023-09-19[mlir][sparse][gpu] free all buffers allocated for spGEMM (#66813)Aart Bik1-2/+13
2023-09-19[mlir][Interfaces] `LoopLikeOpInterface`: Support ops with multiple regions (...Matthias Springer1-2/+2
2023-08-14[mlir][sparse][gpu] minor code cleanup for sparse gpu opsAart Bik1-1/+1
2023-08-10[mlir][sparse][gpu] sparsifier GPU libgen for SpGEMM in cuSparseAart Bik1-31/+199
2023-08-01[mlir][sparse][gpu] introduce flag that controls host to device copy strategi...K-Wu1-33/+150
2023-08-01[mlir][sparse][gpu] add 2:4 spmm prune_and_check flagKun Wu1-1/+2
2023-07-10[mlir][sparse][gpu] Impl 2:4 SpMM rewrite for linalg op w/ DENSE24 attrK-Wu1-0/+111
2023-07-06[mlir][sparse][gpu] fix missing deallocAart Bik1-0/+1
2023-06-30[mlir][sparse][gpu] reuse CUDA environment handle throughout instance lifetimeKun Wu1-42/+15
2023-06-21[mlir][sparse][gpu] refine SDDMM pattern for cuSPARSEAart Bik1-67/+48
2023-06-15[mlir][sparse][gpu] recognizing sddmm pattern in GPU libgen pathKun Wu1-0/+188
2023-06-12[mlir][sparse][gpu] guard matvec COO AoSAart Bik1-4/+4
2023-06-09[mlir][sparse][gpu] unify dnmat and dnvec handle and opsKun Wu1-14/+16
2023-06-06[mlir][sparse][gpu] add sm8.0+ tensor core 2:4 sparsity supportKun Wu1-6/+6
2023-06-06[mlir][sparse][gpu] add AoS COO support to cuSPARSEAart Bik1-1/+11
2023-06-02[mlir][sparse][gpu] make computeType mandatoryKun Wu1-6/+16
2023-05-26[mlir] [sparse] [gpu] adding transpose support to spmm spmvKun Wu1-0/+3
2023-05-26[mlir] Move casting calls from methods to function callsTres Popp1-1/+1
2023-05-25[mlir][sparse][gpu] end to end test for matmulAart Bik1-1/+1
2023-05-24[mlir][sparse][gpu] various cuSparse refinementsAart Bik1-18/+13
2023-05-24[mlir] [gpu] [sparse] refined SparseHandle typeKun Wu1-12/+18
2023-05-19[mlir][sparse][gpu] recognize SpMM cuSparse during sparsificationAart Bik1-19/+120
2023-05-15[mlir][sparse][gpu] first implementation of the GPU libgen approachAart Bik1-11/+307
2023-05-12[mlir] Move casting calls from methods to function callsTres Popp1-4/+4
2023-04-21[mlir][sparse][gpu] generate proper memcpy in/out host and deviceAart Bik1-19/+148
2023-04-15[mlir][sparse][gpu] generate single module, unique kernel namesAart Bik1-11/+20
generated by cgit v1.1 at 2026-02-11 05:48:33 +0000