Skip to content

[SCEV] Fold (C1 * A /u C2) -> A /u (C2 /u C1), if C2 > C1. #157656

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 3 commits into from
Sep 11, 2025
Merged

[SCEV] Fold (C1 * A /u C2) -> A /u (C2 /u C1), if C2 > C1. #157656

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9780db8
[SCEV] Fold (C1 * A /u C2) -> A /u (C2 /u C1), if C2 > C1.
fhahn Sep 8, 2025
5764262
!fixup turn check into assert
fhahn Sep 10, 2025
27e033a
Merge branch 'main' into scev-div-larger-than-mul
fhahn Sep 11, 2025
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
18 changes: 13 additions & 5 deletions llvm/lib/Analysis/ScalarEvolution.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3217,18 +3217,26 @@ const SCEV *ScalarEvolution::getMulExpr(SmallVectorImpl<const SCEV *> &Ops,
}

// Try to fold (C1 * D /u C2) -> C1/C2 * D, if C1 and C2 are powers-of-2,
// D is a multiple of C2, and C1 is a multiple of C2.
// D is a multiple of C2, and C1 is a multiple of C2. If C2 is a multiple
// of C1, fold to (D /u (C2 /u C1)).
const SCEV *D;
APInt C1V = LHSC->getAPInt();
// (C1 * D /u C2) == -1 * -C1 * D /u C2 when C1 != INT_MIN.
if (C1V.isNegative() && !C1V.isMinSignedValue())
// (C1 * D /u C2) == -1 * -C1 * D /u C2 when C1 != INT_MIN. Don't treat -1
// as -1 * 1, as it won't enable additional folds.
if (C1V.isNegative() && !C1V.isMinSignedValue() && !C1V.isAllOnes())
C1V = C1V.abs();
const SCEVConstant *C2;
if (C1V.isPowerOf2() &&
match(Ops[1], m_scev_UDiv(m_SCEV(D), m_SCEVConstant(C2))) &&
C2->getAPInt().isPowerOf2() && C1V.uge(C2->getAPInt()) &&
C2->getAPInt().isPowerOf2() &&
C1V.logBase2() <= getMinTrailingZeros(D)) {
const SCEV *NewMul = getMulExpr(getUDivExpr(getConstant(C1V), C2), D);
const SCEV *NewMul;
if (C1V.uge(C2->getAPInt())) {
NewMul = getMulExpr(getUDivExpr(getConstant(C1V), C2), D);
} else {
assert(C1V.ugt(1) && "C1 <= 1 should have been folded earlier");
NewMul = getUDivExpr(D, getUDivExpr(C2, getConstant(C1V)));
}
return C1V == LHSC->getAPInt() ? NewMul : getNegativeSCEV(NewMul);
}
}
Expand Down
2 changes: 1 addition & 1 deletion llvm/test/Analysis/ScalarEvolution/mul-udiv-folds.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,7 +21,7 @@ define void @udiv4_and_udiv2(i1 %c, ptr %A) {
; CHECK-NEXT: %gep.8 = getelementptr i8, ptr %A, i64 %iv
; CHECK-NEXT: --> {(((zext i32 %start to i64) /u 4) + %A),+,1}<%loop> U: full-set S: full-set Exits: (((zext i32 %start to i64) /u 2) + %A) LoopDispositions: { %loop: Computable }
; CHECK-NEXT: %gep.16 = getelementptr i16, ptr %A, i64 %iv
; CHECK-NEXT: --> {((2 * ((zext i32 %start to i64) /u 4))<nuw><nsw> + %A),+,2}<%loop> U: full-set S: full-set Exits: ((zext i32 %start to i64) + %A) LoopDispositions: { %loop: Computable }
; CHECK-NEXT: --> {(((zext i32 %start to i64) /u 2) + %A),+,2}<%loop> U: full-set S: full-set Exits: ((zext i32 %start to i64) + %A) LoopDispositions: { %loop: Computable }
; CHECK-NEXT: %gep.32 = getelementptr i32, ptr %A, i64 %iv
; CHECK-NEXT: --> {((zext i32 %start to i64) + %A),+,4}<%loop> U: full-set S: full-set Exits: ((2 * (zext i32 %start to i64))<nuw><nsw> + %A) LoopDispositions: { %loop: Computable }
; CHECK-NEXT: %gep.40 = getelementptr <{ i32, i8 }>, ptr %A, i64 %iv
Expand Down
3 changes: 1 addition & 2 deletions llvm/test/Transforms/LoopStrengthReduce/duplicated-phis.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,8 +18,7 @@ define i64 @test_duplicated_phis(i64 noundef %N) {
; CHECK: [[FOR_BODY_PREHEADER_NEW]]:
; CHECK-NEXT: [[UNROLL_ITER:%.*]] = and i64 [[MUL]], -4
; CHECK-NEXT: [[TMP4:%.*]] = add i64 [[UNROLL_ITER]], -4
; CHECK-NEXT: [[TMP5:%.*]] = lshr i64 [[TMP4]], 2
; CHECK-NEXT: [[TMP3:%.*]] = shl nuw nsw i64 [[TMP5]], 1
; CHECK-NEXT: [[TMP3:%.*]] = lshr i64 [[TMP4]], 1
; CHECK-NEXT: [[LSR_IV_NEXT:%.*]] = sub i64 -3, [[TMP3]]
; CHECK-NEXT: br label %[[FOR_BODY:.*]]
; CHECK: [[FOR_BODY]]:
Expand Down