19 Commits

Author SHA1 Message Date
Matthias Springer
4c48f016ef [mlir][Affine][NFC] Wrap dialect in "affine" namespace
This cleanup aligns the affine dialect with all the other dialects.

Differential Revision: https://reviews.llvm.org/D148687
2023-04-20 11:19:21 +09:00
Manish Gupta
fc5c1a7676 [mlir][Memref] Fold nvgpu device cp.async on src memref to dst memref
Differential Revision: https://reviews.llvm.org/D148161
2023-04-20 01:09:44 +00:00
Nicolas Vasilache
33468a51db [mlir][Tensor] Add support for insert_slice in FoldTensorSubsetOps
Differential Revision: https://reviews.llvm.org/D148334
2023-04-14 09:34:11 -07:00
Quentin Colombet
faafd26c4d [mlir][MemRef] Move transform related functions in Transforms.h
NFC
2023-03-28 15:20:19 +02:00
Nicolas Vasilache
4dc72d47ce [mlir][Tensor] Add a FoldTensorSubsetOps pass and patterns
These patterns follow FoldMemRefAliasOps which is further refactored for reuse.
In the process, fix FoldMemRefAliasOps handling of strides for vector.transfer ops which was previously incorrect.

These opt-in patterns generalize the existing canonicalizations on vector.transfer ops.
In the future the blanket canonicalizations will be retired.
They are kept for now to minimize porting disruptions.

Differential Revision: https://reviews.llvm.org/D146624
2023-03-23 04:03:27 -07:00
Nicolas Vasilache
829446cb45 [mlir][memref] Use folded composed affine apply ops in FoldMemRefAliasOps
Creating maximally folded and composd affine.apply operation during
FoldMemRefAliasOps composes better with other transformations without having
to interleave canonicalization passes.

Differential Revision: https://reviews.llvm.org/D146515
2023-03-21 22:17:36 -07:00
Lei Zhang
59e4fbfcd0 [mlir][memref] Fold subview into GPU subgroup MMA load/store ops
This commits adds support for folding subview into GPU subgroup
MMA load/store ops.

Reviewed By: ThomasRaoux

Differential Revision: https://reviews.llvm.org/D146150
2023-03-15 17:49:32 +00:00
Nicolas Vasilache
203fad476b [mlir][DialectUtils] Cleanup IndexingUtils and provide more affine variants while reusing implementations
Differential Revision: https://reviews.llvm.org/D145784
2023-03-14 03:44:59 -07:00
Guray Ozen
1cb91b421e [mlir] Add nontemporal field to memref.load/store and convey to llvm.load/store
`llvm.load` op has nonTemporal field which is missing for `memref.load` and `memref.store`. This revision first adds nonTemporal field to memref's load/store op, then it lowers the field to llvm.load/store ops.

Reviewed By: nicolasvasilache

Differential Revision: https://reviews.llvm.org/D142616
2023-02-03 14:03:38 +01:00
Matthias Springer
a2b837ab04 [mlir] GreedyPatternRewriteDriver: Entry point takes single region
The rewrite driver is typically applied to a single region or all regions of the same op. There is no longer an overload to apply the rewrite driver to a list of regions.

This simplifies the rewrite driver implementation because the scope is now a single region as opposed to a list of regions.

Note: This change is not NFC because `config.maxIterations` and `config.maxNumRewrites` is now counted for each region separately. Furthermore, worklist filtering (`scope`) is now applied to each region separately.

Differential Revision: https://reviews.llvm.org/D142611
2023-01-27 11:23:04 +01:00
Matthias Springer
ccb8a4e3f3 [mlir][memref] Fold subview(subview(x))
Folding of rank-reduced subviews is also supported.

Differential Revision: https://reviews.llvm.org/D140110
2022-12-15 17:50:12 +01:00
River Riddle
c692a11e69 [mlir] Flip Async/GPU/MemRef/OpenACC/OpenMP/PDL dialects to prefixed
This flips all of the remaining dialects to prefixed except for linalg, which
will be done in a followup.

Differential Revision: https://reviews.llvm.org/D134995
2022-09-30 16:55:30 -07:00
Jakub Kuderski
abc362a107 [mlir][arith] Change dialect name from Arithmetic to Arith
Suggested by @lattner in https://discourse.llvm.org/t/rfc-define-precise-arith-semantics/65507/22.

Tested with:
`ninja check-mlir check-mlir-integration check-mlir-mlir-spirv-cpu-runner check-mlir-mlir-vulkan-runner check-mlir-examples`

and `bazel build --config=generic_clang @llvm-project//mlir:all`.

Reviewed By: lattner, Mogball, rriddle, jpienaar, mehdi_amini

Differential Revision: https://reviews.llvm.org/D134762
2022-09-29 11:23:28 -04:00
Nicolas Vasilache
b7d47ed1da [mlir][memref] Add support for 0-D transfer / subview fold.
The 0-d case simply forwards the indexing from the source memref and
works out of the box.

Differential Revision: https://reviews.llvm.org/D133536
2022-09-08 15:25:05 -07:00
Mehdi Amini
2fe37d1c7e Apply clang-tidy fixes for performance-unnecessary-value-param in FoldMemRefAliasOps.cpp (NFC) 2022-09-05 12:34:46 +00:00
Michele Scuttari
67d0d7ac0a
[MLIR] Update pass declarations to new autogenerated files
The patch introduces the required changes to update the pass declarations and definitions to use the new autogenerated files and allow dropping the old infrastructure.

Reviewed By: mehdi_amini, rriddle

Differential Review: https://reviews.llvm.org/D132838
2022-08-31 12:28:45 +02:00
Michele Scuttari
039b969b32
Revert "[MLIR] Update pass declarations to new autogenerated files"
This reverts commit 2be8af8f0e0780901213b6fd3013a5268ddc3359.
2022-08-30 22:21:55 +02:00
Michele Scuttari
2be8af8f0e
[MLIR] Update pass declarations to new autogenerated files
The patch introduces the required changes to update the pass declarations and definitions to use the new autogenerated files and allow dropping the old infrastructure.

Reviewed By: mehdi_amini, rriddle

Differential Review: https://reviews.llvm.org/D132838
2022-08-30 21:56:31 +02:00
Arnab Dutta
1b002d2768 Fold memref.expand_shape and memref.collapse_shape ops
Fold memref.expand_shape and memref.collapse_shape ops into their
memref/affine load/store ops.

Reviewed By: bondhugula, nicolasvasilache

Differential Revision: https://reviews.llvm.org/D128986
2022-08-28 06:56:06 +05:30