4 Commits

Author SHA1 Message Date
bixia1
840e2ba336 [mlir][sparse] Use DLT in the mangled function names for insertion.
Reviewed By: aartbik

Differential Revision: https://reviews.llvm.org/D140484
2022-12-28 08:21:22 -08:00
Peiming Liu
988733c600 [mlir][sparse] use sparse_tensor::StorageSpecifier to store dim/memSizes
Reviewed By: aartbik

Differential Revision: https://reviews.llvm.org/D140130
2022-12-23 00:47:36 +00:00
bixia1
2aceadda78 [mlir][sparse] Put the implementation for the insertion operation to subroutines.
Previously, we generated inlined implementation for insert operation and
observed MLIR compile time increase due to the size of the main routine. We now
put the insert operation implementation in subroutines and leave the inlining
decision to the MLIR compiler.

Reviewed By: aartbik

Differential Revision: https://reviews.llvm.org/D138957
2022-12-01 13:23:59 -08:00
Aart Bik
129177eaf0 [mlir][sparse] add sparse matmul codegen check tests
This found an insertion point bug in access pattern expansion

Reviewed By: bixia

Differential Revision: https://reviews.llvm.org/D137675
2022-11-08 15:58:30 -08:00