Skip to content

[mlir][linalg] Add pattern to clean unused results after fusion #158627

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.

Sign up for GitHub

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

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from
+104 −1
Draft

[mlir][linalg] Add pattern to clean unused results after fusion #158627

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
58 changes: 58 additions & 0 deletions mlir/lib/Dialect/Linalg/Transforms/ElementwiseOpFusion.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2200,6 +2200,63 @@ struct RemoveOutsDependency : public OpRewritePattern<GenericOp> {
}
};

/// Drops an unused result from an elementwise `linalg.generic` by
/// reclassifying its tied `outs` operand as an extra input operand.
struct DropRedundantResultsFromGenericOps
: public OpRewritePattern<linalg::GenericOp> {
using OpRewritePattern<linalg::GenericOp>::OpRewritePattern;
LogicalResult matchAndRewrite(linalg::GenericOp op,
PatternRewriter &rewriter) const override {
if (!linalg::isElementwise(op) || op.getNumResults() < 2U)
return failure();

// Given that the op has no reductions, there is no need to preserve an
// unused result: transform it into an input instead.
auto maybeUnusedRes = llvm::find_if(
op.getResults(), [](OpResult res) { return res.use_empty(); });
if (maybeUnusedRes == op.getResults().end())
return failure();

OpResult unusedRes = *maybeUnusedRes;
const unsigned resIdx = unusedRes.getResultNumber();
auto resTypes = llvm::to_vector(op.getResultTypes());
resTypes.erase(resTypes.begin() + resIdx);
SmallVector<Value> resValues = llvm::to_vector_of<Value>(op.getResults());
resValues.erase(resValues.begin() + resIdx);
const int64_t numInputs = op.getNumDpsInputs();
OpOperand *resOperand = op.getTiedOpOperand(unusedRes);
AffineMap map = op.getIndexingMapMatchingResult(unusedRes);
const unsigned operandIdx = resOperand->getOperandNumber();

// Remove the output operand and add it as an input operand with the same
// map.
SmallVector<Value> outs(op.getOutputs());
outs.erase(outs.begin() + resIdx);
SmallVector<Value> ins(op.getInputs());
ins.insert(ins.begin() + numInputs, resOperand->get());
SmallVector<AffineMap> maps = op.getIndexingMapsArray();
maps.erase(maps.begin() + operandIdx);
maps.insert(maps.begin() + numInputs, map);
rewriter.setInsertionPoint(op);

auto newGenericOp = rewriter.create<linalg::GenericOp>(
op.getLoc(), TypeRange(resTypes), ins, outs, maps,
op.getIteratorTypesArray());

op->setDiscardableAttrs(op->getDiscardableAttrDictionary());
op.getBody()->getTerminator()->eraseOperands(resIdx);
newGenericOp.getRegion().takeBody(op.getBodyRegion());

// Replace the remaining results of the old op with the results of the new
// op.
rewriter.replaceAllUsesWith(resValues, newGenericOp.getResults());

// Remove the old op.
rewriter.eraseOp(op);
return success();
}
};

/// Fold linalg.fill into linalg.generic
struct FoldFillWithGenericOp : public OpRewritePattern<GenericOp> {
using OpRewritePattern<GenericOp>::OpRewritePattern;
Expand Down Expand Up @@ -2262,6 +2319,7 @@ void mlir::linalg::populateElementwiseOpsFusionPatterns(
RemoveOutsDependency>(context);
// Add the patterns that clean up dead operands and results.
populateEraseUnusedOperandsAndResultsPatterns(patterns);
patterns.add<DropRedundantResultsFromGenericOps>(context);
}

void mlir::linalg::populateCollapseDimensions(
Expand Down
47 changes: 46 additions & 1 deletion mlir/test/Dialect/Linalg/fusion-elementwise-ops.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1079,4 +1079,49 @@ module {
// CHECK-NOT: linalg.generic
// CHECK: tensor.expand_shape
// CHECK: linalg.generic {{.*}}, iterator_types = ["parallel", "parallel", "parallel", "parallel", "parallel", "parallel", "reduction"]}
// CHECK-SAME: ins(%[[ARG0]], %[[FUSED]]#1 : tensor<1x1x2x1xf32>, tensor<4x1x1x1xf32>)
// CHECK-SAME: ins(%[[ARG0]], %[[FUSED]]#1 : tensor<1x1x2x1xf32>, tensor<4x1x1x1xf32>)

// -----

// CHECK-LABEL: @drop_unused_results
// CHECK-SAME: [[ARG0:%[a-zA-Z0-9]+]]: tensor<64xf32>, [[ARG1:%[a-zA-Z0-9]+]]: tensor<1x56x56x64xf32>
func.func @drop_unused_results(%arg0: tensor<64xf32>, %arg1: tensor<1x56x56x64xf32>) -> tensor<1x56x56x64xf32> {
%cst = arith.constant 3.40282347E+38 : f32
%cst_0 = arith.constant 0.000000e+00 : f32
// CHECK: [[OUT:%[a-zA-Z0-9]+]] = tensor.empty() : tensor<1x56x56x64xf32>
%0 = tensor.empty() : tensor<1x56x56x64xf32>
// CHECK: [[RES:%[0-9]+]] = linalg.generic {{.*}} ins([[ARG0]], [[ARG1]] : tensor<64xf32>, tensor<1x56x56x64xf32>) outs([[OUT]] : tensor<1x56x56x64xf32>)
%1:2 = linalg.generic {indexing_maps = [affine_map<(d0, d1, d2, d3) -> (d3)>, affine_map<(d0, d1, d2, d3) -> (d0, d1, d2, d3)>, affine_map<(d0, d1, d2, d3) -> (d0, d1, d2, d3)>], iterator_types = ["parallel", "parallel", "parallel", "parallel"]} ins(%arg0 : tensor<64xf32>) outs(%arg1, %0 : tensor<1x56x56x64xf32>, tensor<1x56x56x64xf32>) {
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This input in theory is wrong. I understand your pattern is making the semantics of the operation "right". But for an operation with all parallel iterator types, you cannot read the out value. If you are doing that then this has to be a reduction.
I would put this input operation as having "undefined" behavior and therefore "fixing" the benhavior does not make sense either. This should be fixed on the lowering itself.

We could make this explicitly a verifier error as well.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Well having said that, there is a pattern populateMoveInitOperandsToInput that already seems to do some of this. Maybe if you run that "before" your pass it will fix the issue for you. I think that pattern was added explicitly to fix such "ill-defined" operations.

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

[taking over Pavel whose internship is now finished]

Ack. This pattern was the result of some tensor fusion pattern, but I need to investigate if it's an upstream pattern or not. I've put this PR as draft for the time being while I check whether it was an upstream pattern that caused this invalid IR. All I know is we seem to call populateMoveInitOperandsToInput implicitely via LinalgFoldUnitExtentDimsPass but when removing the pattern added by this patch we get worse code generation. I'll update once we've found the root cause. Thanks for the review so far!

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@MaheshRavishankar where is the documentation that this IR is invalid? I couldn't find something in the online Linalg dialect documentation about out being read-only for parallel-only iterator maps. Is there a verifier that checks that?

^bb0(%in: f32, %out: f32, %out_1: f32):
%2 = arith.addf %in, %out : f32
%3 = arith.minimumf %2, %cst : f32
%4 = arith.maximumf %3, %cst_0 : f32
linalg.yield %2, %4 : f32, f32
} -> (tensor<1x56x56x64xf32>, tensor<1x56x56x64xf32>)
// CHECK: -> tensor<1x56x56x64xf32>
// CHECK: return [[RES]] : tensor<1x56x56x64xf32>
return %1#1 : tensor<1x56x56x64xf32>
}

// -----

// CHECK-LABEL: @swap_drop_unused_results
// CHECK-SAME: [[ARG0:%[a-zA-Z0-9]+]]: tensor<64xf32>, [[ARG1:%[a-zA-Z0-9]+]]: tensor<1x56x56x64xf32>
func.func @swap_drop_unused_results(%arg0: tensor<64xf32>, %arg1: tensor<1x56x56x64xf32>) -> tensor<1x56x56x64xf32> {
%cst = arith.constant 3.40282347E+38 : f32
%cst_0 = arith.constant 0.000000e+00 : f32
// CHECK: [[OUT:%[a-zA-Z0-9]+]] = tensor.empty() : tensor<1x56x56x64xf32>
%0 = tensor.empty() : tensor<1x56x56x64xf32>
// CHECK: [[RES:%[0-9]+]] = linalg.generic {{.*}} ins([[ARG0]] : tensor<64xf32>) outs([[OUT]] : tensor<1x56x56x64xf32>)
%1:2 = linalg.generic {indexing_maps = [affine_map<(d0, d1, d2, d3) -> (d3)>, affine_map<(d0, d1, d2, d3) -> (d0, d1, d2, d3)>, affine_map<(d0, d1, d2, d3) -> (d0, d1, d2, d3)>], iterator_types = ["parallel", "parallel", "parallel", "parallel"]} ins(%arg0 : tensor<64xf32>) outs(%arg1, %0 : tensor<1x56x56x64xf32>, tensor<1x56x56x64xf32>) {
^bb0(%in: f32, %out_1: f32, %out: f32):
%2 = arith.addf %in, %out : f32
%3 = arith.minimumf %2, %cst : f32
%4 = arith.maximumf %3, %cst_0 : f32
linalg.yield %2, %4 : f32, f32
} -> (tensor<1x56x56x64xf32>, tensor<1x56x56x64xf32>)
// CHECK: -> tensor<1x56x56x64xf32>
// CHECK: return [[RES]] : tensor<1x56x56x64xf32>
return %1#0 : tensor<1x56x56x64xf32>
}

Loading