Skip to content

[mlir][SCF] Multiply lower bound in loop range folding #111875

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

Merged
merged 2 commits into from
Oct 14, 2024
Merged

[mlir][SCF] Multiply lower bound in loop range folding #111875

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
9a9169c
multiply lower bound in loop range folding
superlopuh Oct 10, 2024
230e32c
remove unnecessary test case
superlopuh Oct 14, 2024
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
2 changes: 2 additions & 0 deletions mlir/lib/Dialect/SCF/Transforms/LoopRangeFolding.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -72,9 +72,11 @@ void ForLoopRangeFolding::runOnOperation() {
op.setUpperBound(ubFold->getResult(0));

} else if (isa<arith::MulIOp>(user)) {
Operation *lbFold = b.clone(*user, lbMap);
Operation *ubFold = b.clone(*user, ubMap);
Operation *stepFold = b.clone(*user, stepMap);

op.setLowerBound(lbFold->getResult(0));
op.setUpperBound(ubFold->getResult(0));
op.setStep(stepFold->getResult(0));
}
Expand Down
80 changes: 60 additions & 20 deletions mlir/test/Dialect/SCF/loop-range.mlir
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,12 +21,13 @@ func.func @fold_one_loop(%arg0: memref<?xi32>, %arg1: index, %arg2: index) {
// CHECK: %[[C4:.*]] = arith.constant 4 : index
// CHECK: %[[I0:.*]] = arith.addi %[[ARG2]], %[[C0]] : index
// CHECK: %[[I1:.*]] = arith.addi %[[ARG2]], %[[ARG1]] : index
// CHECK: %[[I2:.*]] = arith.muli %[[I1]], %[[C4]] : index
// CHECK: %[[I3:.*]] = arith.muli %[[C1]], %[[C4]] : index
// CHECK: scf.for %[[I:.*]] = %[[I0]] to %[[I2]] step %[[I3]] {
// CHECK: %[[I4:.*]] = memref.load %[[ARG0]]{{\[}}%[[I]]
// CHECK: %[[I5:.*]] = arith.muli %[[I4]], %[[I4]] : i32
// CHECK: memref.store %[[I5]], %[[ARG0]]{{\[}}%[[I]]
// CHECK: %[[I2:.*]] = arith.muli %[[I0]], %[[C4]] : index
// CHECK: %[[I3:.*]] = arith.muli %[[I1]], %[[C4]] : index
// CHECK: %[[I4:.*]] = arith.muli %[[C1]], %[[C4]] : index
// CHECK: scf.for %[[I:.*]] = %[[I2]] to %[[I3]] step %[[I4]] {
// CHECK: %[[I5:.*]] = memref.load %[[ARG0]]{{\[}}%[[I]]
// CHECK: %[[I6:.*]] = arith.muli %[[I5]], %[[I5]] : i32
// CHECK: memref.store %[[I6]], %[[ARG0]]{{\[}}%[[I]]

func.func @fold_one_loop2(%arg0: memref<?xi32>, %arg1: index, %arg2: index) {
%c0 = arith.constant 0 : index
Expand Down Expand Up @@ -54,12 +55,48 @@ func.func @fold_one_loop2(%arg0: memref<?xi32>, %arg1: index, %arg2: index) {
// CHECK: scf.for %[[J:.*]] = %[[C0]] to %[[C10]] step %[[C1]] {
// CHECK: %[[I0:.*]] = arith.addi %[[ARG2]], %[[C0]] : index
// CHECK: %[[I1:.*]] = arith.addi %[[ARG2]], %[[ARG1]] : index
// CHECK: %[[I2:.*]] = arith.muli %[[I1]], %[[C4]] : index
// CHECK: %[[I3:.*]] = arith.muli %[[C1]], %[[C4]] : index
// CHECK: scf.for %[[I:.*]] = %[[I0]] to %[[I2]] step %[[I3]] {
// CHECK: %[[I4:.*]] = memref.load %[[ARG0]]{{\[}}%[[I]]
// CHECK: %[[I5:.*]] = arith.muli %[[I4]], %[[I4]] : i32
// CHECK: memref.store %[[I5]], %[[ARG0]]{{\[}}%[[I]]
// CHECK: %[[I2:.*]] = arith.muli %[[I0]], %[[C4]] : index
// CHECK: %[[I3:.*]] = arith.muli %[[I1]], %[[C4]] : index
// CHECK: %[[I4:.*]] = arith.muli %[[C1]], %[[C4]] : index
// CHECK: scf.for %[[I:.*]] = %[[I2]] to %[[I3]] step %[[I4]] {
// CHECK: %[[I5:.*]] = memref.load %[[ARG0]]{{\[}}%[[I]]
// CHECK: %[[I6:.*]] = arith.muli %[[I5]], %[[I5]] : i32
// CHECK: memref.store %[[I6]], %[[ARG0]]{{\[}}%[[I]]

func.func @fold_one_loop3(%arg0: memref<?xi32>, %arg1: index, %arg2: index) {
Copy link
Member

@zero9178 zero9178 Oct 11, 2024

Choose a reason for hiding this comment

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

How is this test different from @fold_one_loop2? To me it looks like the test changes you made for the other test cases seem to cover the lower bound changes. I'd just remove the test otherwise

%c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index
%c4 = arith.constant 4 : index
%c10 = arith.constant 10 : index
scf.for %j = %c0 to %c10 step %c1 {
scf.for %i = %c1 to %arg1 step %c1 {
%0 = arith.addi %arg2, %i : index
%1 = arith.muli %0, %c4 : index
%2 = memref.load %arg0[%1] : memref<?xi32>
%3 = arith.muli %2, %2 : i32
memref.store %3, %arg0[%1] : memref<?xi32>
}
}
return
}

// CHECK-LABEL: func @fold_one_loop3
// CHECK-SAME: (%[[ARG0:.*]]: {{.*}}, %[[ARG1:.*]]: {{.*}}, %[[ARG2:.*]]: {{.*}}
// CHECK: %[[C0:.*]] = arith.constant 0 : index
// CHECK: %[[C1:.*]] = arith.constant 1 : index
// CHECK: %[[C4:.*]] = arith.constant 4 : index
// CHECK: %[[C10:.*]] = arith.constant 10 : index
// CHECK: scf.for %[[J:.*]] = %[[C0]] to %[[C10]] step %[[C1]] {
// CHECK: %[[I0:.*]] = arith.addi %[[ARG2]], %[[C1]] : index
// CHECK: %[[I1:.*]] = arith.addi %[[ARG2]], %[[ARG1]] : index
// CHECK: %[[I2:.*]] = arith.muli %[[I0]], %[[C4]] : index
// CHECK: %[[I3:.*]] = arith.muli %[[I1]], %[[C4]] : index
// CHECK: %[[I4:.*]] = arith.muli %[[C1]], %[[C4]] : index
// CHECK: scf.for %[[I:.*]] = %[[I2]] to %[[I3]] step %[[I4]] {
// CHECK: %[[I5:.*]] = memref.load %[[ARG0]]{{\[}}%[[I]]
// CHECK: %[[I6:.*]] = arith.muli %[[I5]], %[[I5]] : i32
// CHECK: memref.store %[[I6]], %[[ARG0]]{{\[}}%[[I]]


func.func @fold_two_loops(%arg0: memref<?xi32>, %arg1: index, %arg2: index) {
%c0 = arith.constant 0 : index
Expand All @@ -86,14 +123,17 @@ func.func @fold_two_loops(%arg0: memref<?xi32>, %arg1: index, %arg2: index) {
// CHECK: %[[C10:.*]] = arith.constant 10 : index
// CHECK: %[[I0:.*]] = arith.addi %[[ARG2]], %[[C0]] : index
// CHECK: %[[I1:.*]] = arith.addi %[[ARG2]], %[[C10]] : index
// CHECK: scf.for %[[J:.*]] = %[[I0]] to %[[I1]] step %[[C1]] {
// CHECK: %[[I1:.*]] = arith.addi %[[ARG2]], %[[ARG1]] : index
// CHECK: %[[I2:.*]] = arith.muli %[[I1]], %[[C4]] : index
// CHECK: %[[I3:.*]] = arith.muli %[[C1]], %[[C4]] : index
// CHECK: scf.for %[[I:.*]] = %[[J]] to %[[I2]] step %[[I3]] {
// CHECK: %[[I4:.*]] = memref.load %[[ARG0]]{{\[}}%[[I]]
// CHECK: %[[I5:.*]] = arith.muli %[[I4]], %[[I4]] : i32
// CHECK: memref.store %[[I5]], %[[ARG0]]{{\[}}%[[I]]
// CHECK: %[[I2:.*]] = arith.muli %[[I0]], %[[C4]] : index
// CHECK: %[[I3:.*]] = arith.muli %[[I1]], %[[C4]] : index
// CHECK: %[[I4:.*]] = arith.muli %[[C1]], %[[C4]] : index
// CHECK: scf.for %[[J:.*]] = %[[I2]] to %[[I3]] step %[[I4]] {
// CHECK: %[[I5:.*]] = arith.addi %[[ARG2]], %[[ARG1]] : index
// CHECK: %[[I6:.*]] = arith.muli %[[I5]], %[[C4]] : index
// CHECK: %[[I7:.*]] = arith.muli %[[C1]], %[[C4]] : index
// CHECK: scf.for %[[I:.*]] = %[[J]] to %[[I6]] step %[[I7]] {
// CHECK: %[[I8:.*]] = memref.load %[[ARG0]]{{\[}}%[[I]]
// CHECK: %[[I9:.*]] = arith.muli %[[I8]], %[[I8]] : i32
// CHECK: memref.store %[[I9]], %[[ARG0]]{{\[}}%[[I]]

// If an instruction's operands are not defined outside the loop, we cannot
// perform the optimization, as is the case with the arith.muli below. (If
Expand Down
Loading