[MLIR][Linalg] Bail out if the tiles provided are more than the number #66007
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@llvm/pr-subscribers-mlir Changesof loops Currently, the compiler crashes if the number of tiles provided exceeds the number of loops.Full diff: https://github.com/llvm/llvm-project/pull/66007.diff 2 Files Affected:
diff --git a/mlir/lib/Dialect/Linalg/TransformOps/LinalgTransformOps.cpp b/mlir/lib/Dialect/Linalg/TransformOps/LinalgTransformOps.cpp
index 1b2283c054c7d34..6539641030f905b 100644
--- a/mlir/lib/Dialect/Linalg/TransformOps/LinalgTransformOps.cpp
+++ b/mlir/lib/Dialect/Linalg/TransformOps/LinalgTransformOps.cpp
@@ -2533,6 +2533,12 @@ transform::TileOp::apply(transform::TransformRewriter &rewriter,
diag.attachNote(op->getLoc()) << "target op";
return diag;
}
+ if (tileSizes.size() > tilingInterface.getLoopIteratorTypes().size()) {
+ DiagnosedSilenceableFailure diag = emitSilenceableError()
+ << "too many tiles for";
+ diag.attachNote(op->getLoc()) << "target op";
+ return diag;
+ }
scf::SCFTilingOptions tilingOptions;
if (!tileSizes.empty()) {
diff --git a/mlir/test/Dialect/Linalg/transform-op-tile.mlir b/mlir/test/Dialect/Linalg/transform-op-tile.mlir
index d4629dcb29c3efc..1ed2ff3732fc324 100644
--- a/mlir/test/Dialect/Linalg/transform-op-tile.mlir
+++ b/mlir/test/Dialect/Linalg/transform-op-tile.mlir
@@ -220,3 +220,20 @@ transform.sequence failures(propagate) {
%0 = transform.structured.match ops{["linalg.matmul"]} in %arg1 : (!transform.any_op) -> !transform.any_op
%1, %loops:3 = transform.structured.tile %0 [4, 4, [4]] : (!transform.any_op) -> (!transform.any_op, !transform.any_op, !transform.any_op, !transform.any_op)
}
+
+// -----
+
+func.func @matmul(%arg0: tensor<128x128xf32>, %arg1: tensor<128x128xf32>,
+ %arg2: tensor<128x128xf32>) -> tensor<128x128xf32> {
+ // expected-note @below {{target op}}
+ %0 = linalg.matmul ins(%arg0, %arg1: tensor<128x128xf32>, tensor<128x128xf32>)
+ outs(%arg2: tensor<128x128xf32>) -> tensor<128x128xf32>
+ return %0 : tensor<128x128xf32>
+}
+
+transform.sequence failures(propagate) {
+^bb0(%arg1: !transform.any_op):
+ %0 = transform.structured.match ops{["linalg.matmul"]} in %arg1 : (!transform.any_op) -> !transform.any_op
+ // expected-error @below {{too many tiles for}}
+ %1, %loops = transform.structured.tile %0 [1, 0, 0, 0] : (!transform.any_op) -> (!transform.any_op, !transform.any_op)
+}
|
|
@llvm/pr-subscribers-mlir-linalg Changesof loops Currently, the compiler crashes if the number of tiles provided exceeds the number of loops.Full diff: https://github.com/llvm/llvm-project/pull/66007.diff 2 Files Affected:
diff --git a/mlir/lib/Dialect/Linalg/TransformOps/LinalgTransformOps.cpp b/mlir/lib/Dialect/Linalg/TransformOps/LinalgTransformOps.cpp
index 1b2283c054c7d34..6539641030f905b 100644
--- a/mlir/lib/Dialect/Linalg/TransformOps/LinalgTransformOps.cpp
+++ b/mlir/lib/Dialect/Linalg/TransformOps/LinalgTransformOps.cpp
@@ -2533,6 +2533,12 @@ transform::TileOp::apply(transform::TransformRewriter &rewriter,
diag.attachNote(op->getLoc()) << "target op";
return diag;
}
+ if (tileSizes.size() > tilingInterface.getLoopIteratorTypes().size()) {
+ DiagnosedSilenceableFailure diag = emitSilenceableError()
+ << "too many tiles for";
+ diag.attachNote(op->getLoc()) << "target op";
+ return diag;
+ }
scf::SCFTilingOptions tilingOptions;
if (!tileSizes.empty()) {
diff --git a/mlir/test/Dialect/Linalg/transform-op-tile.mlir b/mlir/test/Dialect/Linalg/transform-op-tile.mlir
index d4629dcb29c3efc..1ed2ff3732fc324 100644
--- a/mlir/test/Dialect/Linalg/transform-op-tile.mlir
+++ b/mlir/test/Dialect/Linalg/transform-op-tile.mlir
@@ -220,3 +220,20 @@ transform.sequence failures(propagate) {
%0 = transform.structured.match ops{["linalg.matmul"]} in %arg1 : (!transform.any_op) -> !transform.any_op
%1, %loops:3 = transform.structured.tile %0 [4, 4, [4]] : (!transform.any_op) -> (!transform.any_op, !transform.any_op, !transform.any_op, !transform.any_op)
}
+
+// -----
+
+func.func @matmul(%arg0: tensor<128x128xf32>, %arg1: tensor<128x128xf32>,
+ %arg2: tensor<128x128xf32>) -> tensor<128x128xf32> {
+ // expected-note @below {{target op}}
+ %0 = linalg.matmul ins(%arg0, %arg1: tensor<128x128xf32>, tensor<128x128xf32>)
+ outs(%arg2: tensor<128x128xf32>) -> tensor<128x128xf32>
+ return %0 : tensor<128x128xf32>
+}
+
+transform.sequence failures(propagate) {
+^bb0(%arg1: !transform.any_op):
+ %0 = transform.structured.match ops{["linalg.matmul"]} in %arg1 : (!transform.any_op) -> !transform.any_op
+ // expected-error @below {{too many tiles for}}
+ %1, %loops = transform.structured.tile %0 [1, 0, 0, 0] : (!transform.any_op) -> (!transform.any_op, !transform.any_op)
+}
|
Lewuathe
reviewed
Sep 12, 2023
|
|
||
| // ----- | ||
|
|
||
| func.func @matmul(%arg0: tensor<128x128xf32>, %arg1: tensor<128x128xf32>, |
There was a problem hiding this comment.
How about using the function name reflecting the purpose of this test case?
Suggested change
| func.func @matmul(%arg0: tensor<128x128xf32>, %arg1: tensor<128x128xf32>, | |
| func.func @too_many_tile(%arg0: tensor<128x128xf32>, %arg1: tensor<128x128xf32>, |
matthias-springer
approved these changes
Sep 12, 2023
| @@ -2533,6 +2533,12 @@ transform::TileOp::apply(transform::TransformRewriter &rewriter, | |||
| diag.attachNote(op->getLoc()) << "target op"; | |||
| return diag; | |||
| } | |||
| if (tileSizes.size() > tilingInterface.getLoopIteratorTypes().size()) { | |||
| DiagnosedSilenceableFailure diag = emitSilenceableError() | |||
| << "too many tiles for"; | |||
There was a problem hiding this comment.
I'd rephrase this as too many tile sizes provided, expected at most X, found Y.
ftynse
approved these changes
Sep 12, 2023
of loops Currently, the compiler crashes if the number of tiles provided exceeds the number of loops.
chelini
force-pushed
the
fix-crash-tile-op
branch
from
4e8be7b to
0a9556d
Compare
ZijunZhaoCCK
pushed a commit
to ZijunZhaoCCK/llvm-project
that referenced
this pull request
Sep 19, 2023
llvm#66007) Currently, the compiler crashes if the number of tiles provided exceeds the number of loops.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Currently, the compiler crashes if the number of tiles provided exceeds the number of loops.