Skip to content
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

computeSliceParameters: Fix offset when m(0) != 0 #442

Merged
merged 1 commit into from
Jan 15, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
11 changes: 10 additions & 1 deletion mlir/lib/Dialect/Linalg/Utils/Utils.cpp
Original file line number Diff line number Diff line change
Expand Up @@ -599,8 +599,17 @@ computeSliceParameters(OpBuilder &builder, Location loc, Value valueToTile,
// (i.e. the op does not subsample, stepping occurs in the loop).
LLVM_DEBUG(llvm::dbgs() << "computeSliceParameters: submap: " << m << "\n");
IRRewriter rewriter(builder);
OpFoldResult offset = makeComposedFoldedAffineApply(rewriter, loc, m, lbs);
// The offset of the slice is map(lbs) - map(0).
SmallVector<Attribute> zeros(lbs.size(), rewriter.getIndexAttr(0));
SmallVector<Attribute> mAtZero;
auto res = m.constantFold(zeros, mAtZero);
assert(succeeded(res));
auto atZeroInt = getConstantIntValue(mAtZero[0]);
assert(atZeroInt);
OpFoldResult offset = makeComposedFoldedAffineApply(
rewriter, loc, m.getResult(0) - *atZeroInt, lbs);
sliceParams.offsets.push_back(offset);

OpFoldResult closedIntSize =
makeComposedFoldedAffineApply(rewriter, loc, m, subShapeSizes);
// Resulting size needs to be made half open interval again.
Expand Down
25 changes: 25 additions & 0 deletions mlir/test/Dialect/Linalg/tile-offset.mlir
Original file line number Diff line number Diff line change
@@ -0,0 +1,25 @@
// RUN: mlir-opt %s -transform-interpreter -split-input-file | FileCheck %s

// CHECK-LABEL: func @tile_offset
// CHECK-SAME: %[[ARG0:[a-zA-Z0-9_]+]]:
func.func @tile_offset(%arg0 : tensor<9xf32>) -> tensor<6xf32> {
%empty = tensor.empty() : tensor<6xf32>
// CHECK: scf.for %[[ITER:[a-zA-Z0-9_]+]] =
// CHECK: tensor.extract_slice %[[ARG0]][%[[ITER]]] [6] [1]
%generic = linalg.generic
{indexing_maps = [affine_map<(d0) -> (d0 + 3)>,
affine_map<(d0) -> (d0)>],
iterator_types = ["parallel"]} ins(%arg0: tensor<9xf32>) outs(%empty : tensor<6xf32>) {
^bb0(%in : f32, %out: f32):
linalg.yield %in : f32
} -> tensor<6xf32>
return %generic : tensor<6xf32>
}

module attributes {transform.with_named_sequence} {
transform.named_sequence @__transform_main(%arg1: !transform.any_op {transform.readonly}) {
%0 = transform.structured.match ops{["linalg.generic"]} in %arg1 : (!transform.any_op) -> !transform.any_op
%1, %loop = transform.structured.tile_using_for %0 tile_sizes [3] : (!transform.any_op) -> (!transform.any_op, !transform.any_op)
transform.yield
}
}
Loading