Skip to content

[InstCombine] Fold uadd.sat(X, C) - C to umin(X, ~C) #215130

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
dtcxzyw merged 1 commit into from
Aug 10, 2026
+61 −1
Merged

[InstCombine] Fold uadd.sat(X, C) - C to umin(X, ~C) #215130

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
12 changes: 11 additions & 1 deletion llvm/lib/Transforms/InstCombine/InstCombineAddSub.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1003,7 +1003,17 @@ Instruction *InstCombinerImpl::foldAddWithConstant(BinaryOperator &Add) {
return replaceInstUsesWith(
Add, Builder.CreateBinaryIntrinsic(
Intrinsic::usub_sat, X, ConstantInt::get(Add.getType(), -*C)));

// uadd.sat(X, C) + -C --> umin(X, ~C)
// The saturating add gives X + C or UMAX, so subtracting C leaves X or
// UMAX - C. Note UMAX - C == ~C.
{
APInt SatC = -*C;
if (match(Op0, m_OneUse(m_Intrinsic<Intrinsic::uadd_sat>(
m_Value(X), m_SpecificInt(SatC)))))
return replaceInstUsesWith(
Add, Builder.CreateBinaryIntrinsic(Intrinsic::umin, X,
ConstantInt::get(Ty, ~SatC)));
}
// Fold (add (zext (add X, -C)), C) -> (zext X) if X u>= C.
// Truncate C to the narrow type to avoid mismatched width comparisons.
{
Expand Down
50 changes: 50 additions & 0 deletions llvm/test/Transforms/InstCombine/saturating-add-sub.ll
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1367,15 +1367,65 @@ define i8 @test_scalar_uadd_sub_commuted_wrong(i8 %a, i8 %b) {

define i8 @test_scalar_uadd_sub_const(i8 %a) {
; CHECK-LABEL: @test_scalar_uadd_sub_const(
; CHECK-NEXT: [[RES:%.*]] = call i8 @llvm.umin.i8(i8 [[A:%.*]], i8 -43)
; CHECK-NEXT: ret i8 [[RES]]
;
%sat = call i8 @llvm.uadd.sat.i8(i8 %a, i8 42)
%res = sub i8 %sat, 42
ret i8 %res
}

define <2 x i8> @test_vector_uadd_sub_const(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_uadd_sub_const(
; CHECK-NEXT: [[RES:%.*]] = call <2 x i8> @llvm.umin.v2i8(<2 x i8> [[A:%.*]], <2 x i8> splat (i8 -43))
; CHECK-NEXT: ret <2 x i8> [[RES]]
;
%sat = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> %a, <2 x i8> splat (i8 42))
%res = sub <2 x i8> %sat, splat (i8 42)
ret <2 x i8> %res
}

; negative test - the constants do not cancel

define i8 @test_scalar_uadd_sub_const_mismatch(i8 %a) {
; CHECK-LABEL: @test_scalar_uadd_sub_const_mismatch(
; CHECK-NEXT: [[SAT:%.*]] = call i8 @llvm.uadd.sat.i8(i8 [[A:%.*]], i8 42)
; CHECK-NEXT: [[RES:%.*]] = add i8 [[SAT]], -43
; CHECK-NEXT: ret i8 [[RES]]
;
%sat = call i8 @llvm.uadd.sat.i8(i8 %a, i8 42)
%res = sub i8 %sat, 43
ret i8 %res
}

; negative test - extra use of the saturating add

define i8 @test_scalar_uadd_sub_const_multiuse(i8 %a) {
; CHECK-LABEL: @test_scalar_uadd_sub_const_multiuse(
; CHECK-NEXT: [[SAT:%.*]] = call i8 @llvm.uadd.sat.i8(i8 [[A:%.*]], i8 42)
; CHECK-NEXT: [[RES:%.*]] = add i8 [[SAT]], -42
; CHECK-NEXT: call void @usei8(i8 [[SAT]])
; CHECK-NEXT: ret i8 [[RES]]
;
%sat = call i8 @llvm.uadd.sat.i8(i8 %a, i8 42)
%res = sub i8 %sat, 42
call void @usei8(i8 %sat)
ret i8 %res
}

; negative test - non-splat vector

define <2 x i8> @test_vector_uadd_sub_const_nonsplat(<2 x i8> %a) {
; CHECK-LABEL: @test_vector_uadd_sub_const_nonsplat(
; CHECK-NEXT: [[SAT:%.*]] = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> [[A:%.*]], <2 x i8> <i8 42, i8 3>)
; CHECK-NEXT: [[RES:%.*]] = add <2 x i8> [[SAT]], <i8 -42, i8 -3>
; CHECK-NEXT: ret <2 x i8> [[RES]]
;
%sat = call <2 x i8> @llvm.uadd.sat.v2i8(<2 x i8> %a, <2 x i8> <i8 42, i8 3>)
%res = sub <2 x i8> %sat, <i8 42, i8 3>
ret <2 x i8> %res
}

define i1 @scalar_uadd_eq_zero(i8 %a, i8 %b) {
; CHECK-LABEL: @scalar_uadd_eq_zero(
; CHECK-NEXT: [[TMP1:%.*]] = or i8 [[A:%.*]], [[B:%.*]]
Expand Down
Loading