-
Notifications
You must be signed in to change notification settings - Fork 13.5k
Issues: llvm/llvm-project
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
[MLIR] Change getBackwardSlice to return a logicalresult rather than crash
mlir:affine
mlir:core
MLIR Core Infrastructure
mlir:gpu
mlir:linalg
mlir:nvgpu
mlir:scf
mlir
#140961
opened May 21, 2025 by
wsmoses
Loading…
Revert "[mlir][affine] allow iter args as valid dims"
mlir:affine
mlir
#140808
opened May 20, 2025 by
ftynse
Loading…
[mlir][SliceAnalysis] Fix stack overflow in graph regions
mlir:affine
mlir
#139694
opened May 13, 2025 by
maerhart
Loading…
[MLIR][Affine] Fix memref replacement in affine-data-copy-generate
mlir:affine
mlir:memref
mlir
#139016
opened May 8, 2025 by
bondhugula
Loading…
[mlir][vector][affine] Allow
--affine-super-vectorize
to vectorize maxnumf/minnumf (2)
mlir:affine
mlir:vector
mlir:vectorops
mlir
#138730
opened May 6, 2025 by
oowekyala
Loading…
[MLIR] Add MemRefElementTypeInterface to gpu.mma_matrix
mlir:affine
mlir:core
MLIR Core Infrastructure
mlir:gpu
mlir:ods
mlir
#132312
opened Mar 21, 2025 by
bondhugula
•
Draft
[MLIR] crashed on Prefer [crash-on-valid] or [crash-on-invalid]
mlir:affine
affine-super-vectorizer-test
pass with assertion failure: `perm[kvp.second] == getAffineConstantExpr(0, context) && "permutationMap already has an entry along dim"'
crash
#131772
opened Mar 18, 2025 by
sweead
[mlir] Add a contiguous<perm, offset> layout, use as identity layout
backend:AMDGPU
mlir:affine
mlir:amdgpu
mlir:bufferization
Bufferization infrastructure
mlir:core
MLIR Core Infrastructure
mlir:gpu
mlir:linalg
mlir:memref
mlir:ods
mlir:python
MLIR Python bindings
mlir:tensor
mlir:vector
mlir:vectorops
mlir
#131663
opened Mar 17, 2025 by
krzysz00
Loading…
[MLIR] crashed on '-affine-super-vectorizer-test': Assertion `use_empty() && "Cannot destroy a value that still has uses!"' failed
crash
Prefer [crash-on-valid] or [crash-on-invalid]
mlir:affine
#131135
opened Mar 13, 2025 by
sweead
[mlir] Inconsistent output when executing MLIR program with
--test-affine-parametric-tile
mlir:affine
#131105
opened Mar 13, 2025 by
Emilyaxe
[MLIR] crashed on '-affine-super-vectorizer-test': Assertion `(ratio || !mustDivide) && "vector.transfer operation in which super-vector size is not an" " integer multiple of sub-vector size"' failed
crash
Prefer [crash-on-valid] or [crash-on-invalid]
mlir:affine
#131096
opened Mar 13, 2025 by
sweead
[MLIR][Affine] Normalize memref.alloc ops with non trivial layout map
mlir:affine
mlir:memref
mlir
#129875
opened Mar 5, 2025 by
arnab-polymage
Loading…
[mlir][affine] add remove-single-iteration-loop pass.
mlir:affine
mlir
#129270
opened Feb 28, 2025 by
linuxlonelyeagle
Loading…
[MLIR][Affine] Loop fusion in a block containing Linalg op
mlir:affine
mlir
#129136
opened Feb 27, 2025 by
aturetsk
Loading…
[mlir][affine] Use value bound inference to determine minimum/maximum trip counts in loop analysis
mlir:affine
mlir:gpu
mlir
#128113
opened Feb 21, 2025 by
linuxlonelyeagle
Loading…
[MLIR] mlir::affine::simplifyConstrainedMinMaxOp creates null operands
mlir:affine
#127436
opened Feb 17, 2025 by
bondhugula
[mlir][Affine] take strides into account for contiguity check
mlir:affine
mlir
#126579
opened Feb 10, 2025 by
gdehame
Loading…
[mlir][Affine] affine-super-vectorize transform op
mlir:affine
mlir
#126522
opened Feb 10, 2025 by
gdehame
Loading…
[MLIR][Affine] Fix affine loop fusion with vector ops #115849, #120227
mlir:affine
mlir
#122799
opened Jan 13, 2025 by
brod4910
Loading…
[Mlir] --affine-super-vectorize="virtual-vector-size=128" crashes in Operation.cpp:214
crash
Prefer [crash-on-valid] or [crash-on-invalid]
mlir:affine
#122213
opened Jan 9, 2025 by
Emilyaxe
[Mlir] --affine-super-vectorizer-test="vector-shape-ratio=4,8" crashes in VectorUtils.cpp:247: bool mlir::matcher::operatesOnSuperVectorsOf
crash
Prefer [crash-on-valid] or [crash-on-invalid]
mlir:affine
#122211
opened Jan 9, 2025 by
Emilyaxe
Previous Next
ProTip!
Mix and match filters to narrow down what you’re looking for.