[llvm] [InstCombine] Preserve NSW/NUW flags when folding const BOp with min/max (PR #143471)
Alex MacLean via llvm-commits
llvm-commits at lists.llvm.org
Mon Jun 9 19:39:05 PDT 2025
https://github.com/AlexMaclean created https://github.com/llvm/llvm-project/pull/143471
When folding `X Pred C2 ? X BOp C1 : C2 BOp C1` to `min/max(X, C2) BOp C1`, if NUW/NSW flags are present on `X BOp C1` and could be safely applied to `C2 BOp C1`, then they may be added on the BOp after the fold is complete. https://alive2.llvm.org/ce/z/n_3aNJ
Preserving these flags can allow subsequent transforms to re-order the min/max and BOp, which in the case of NVPTX would allow for some potential future transformations which would improve instruction-selection.
>From 6bee710cd443c5fcf0c040b895c636e8ca7836d1 Mon Sep 17 00:00:00 2001
From: Alex Maclean <amaclean at nvidia.com>
Date: Mon, 9 Jun 2025 15:21:40 +0000
Subject: [PATCH 1/2] pre-commit tests
---
.../InstCombine/canonicalize-const-to-bop.ll | 79 +++++++++++++++++++
1 file changed, 79 insertions(+)
diff --git a/llvm/test/Transforms/InstCombine/canonicalize-const-to-bop.ll b/llvm/test/Transforms/InstCombine/canonicalize-const-to-bop.ll
index c08ec1bb7de0d..120232076f9a6 100644
--- a/llvm/test/Transforms/InstCombine/canonicalize-const-to-bop.ll
+++ b/llvm/test/Transforms/InstCombine/canonicalize-const-to-bop.ll
@@ -450,3 +450,82 @@ define i8 @umax_sgt(i8 %x) {
%s = select i1 %cmp, i8 100, i8 %umax
ret i8 %s
}
+
+define i8 @add_sgt_nuw_nsw_safe(i8 %x) {
+; CHECK-LABEL: define i8 @add_sgt_nuw_nsw_safe(
+; CHECK-SAME: i8 [[X:%.*]]) {
+; CHECK-NEXT: [[TMP1:%.*]] = call i8 @llvm.smin.i8(i8 [[X]], i8 100)
+; CHECK-NEXT: [[S:%.*]] = add nsw i8 [[TMP1]], 1
+; CHECK-NEXT: ret i8 [[S]]
+;
+ %add = add nuw nsw i8 %x, 1
+ %cmp = icmp sgt i8 %x, 100
+ %s = select i1 %cmp, i8 101, i8 %add
+ ret i8 %s
+}
+
+define i8 @add_sgt_nuw_only(i8 %x) {
+; CHECK-LABEL: define i8 @add_sgt_nuw_only(
+; CHECK-SAME: i8 [[X:%.*]]) {
+; CHECK-NEXT: [[TMP1:%.*]] = call i8 @llvm.smin.i8(i8 [[X]], i8 100)
+; CHECK-NEXT: [[S:%.*]] = add i8 [[TMP1]], 50
+; CHECK-NEXT: ret i8 [[S]]
+;
+ %add = add nuw nsw i8 %x, 50
+ %cmp = icmp sgt i8 %x, 100
+ %s = select i1 %cmp, i8 150, i8 %add
+ ret i8 %s
+}
+
+define i8 @add_sgt_nsw_only(i8 %x) {
+; CHECK-LABEL: define i8 @add_sgt_nsw_only(
+; CHECK-SAME: i8 [[X:%.*]]) {
+; CHECK-NEXT: [[TMP1:%.*]] = call i8 @llvm.smin.i8(i8 [[X]], i8 100)
+; CHECK-NEXT: [[S:%.*]] = add i8 [[TMP1]], -99
+; CHECK-NEXT: ret i8 [[S]]
+;
+ %add = add nuw nsw i8 %x, -99
+ %cmp = icmp sgt i8 %x, 100
+ %s = select i1 %cmp, i8 1, i8 %add
+ ret i8 %s
+}
+
+
+define i8 @mul_ult_nuw_nsw_safe(i8 %x) {
+; CHECK-LABEL: define i8 @mul_ult_nuw_nsw_safe(
+; CHECK-SAME: i8 [[X:%.*]]) {
+; CHECK-NEXT: [[TMP1:%.*]] = call i8 @llvm.umax.i8(i8 [[X]], i8 10)
+; CHECK-NEXT: [[S:%.*]] = mul i8 [[TMP1]], 3
+; CHECK-NEXT: ret i8 [[S]]
+;
+ %mul = mul nuw nsw i8 %x, 3
+ %cmp = icmp ult i8 %x, 10
+ %s = select i1 %cmp, i8 30, i8 %mul
+ ret i8 %s
+}
+
+define i8 @mul_ult_nuw_only(i8 %x) {
+; CHECK-LABEL: define i8 @mul_ult_nuw_only(
+; CHECK-SAME: i8 [[X:%.*]]) {
+; CHECK-NEXT: [[TMP1:%.*]] = call i8 @llvm.umax.i8(i8 [[X]], i8 10)
+; CHECK-NEXT: [[S:%.*]] = mul i8 [[TMP1]], 25
+; CHECK-NEXT: ret i8 [[S]]
+;
+ %mul = mul nuw nsw i8 %x, 25
+ %cmp = icmp ult i8 %x, 10
+ %s = select i1 %cmp, i8 250, i8 %mul
+ ret i8 %s
+}
+
+define i8 @mul_ult_nsw_only(i8 %x) {
+; CHECK-LABEL: define i8 @mul_ult_nsw_only(
+; CHECK-SAME: i8 [[X:%.*]]) {
+; CHECK-NEXT: [[TMP1:%.*]] = call i8 @llvm.umax.i8(i8 [[X]], i8 40)
+; CHECK-NEXT: [[S:%.*]] = mul i8 [[TMP1]], -2
+; CHECK-NEXT: ret i8 [[S]]
+;
+ %mul = mul nuw nsw i8 %x, -2
+ %cmp = icmp ult i8 %x, 40
+ %s = select i1 %cmp, i8 -80, i8 %mul
+ ret i8 %s
+}
>From 16bc37458eee56af3dbe0f9ff1995c062a41fc05 Mon Sep 17 00:00:00 2001
From: Alex Maclean <amaclean at nvidia.com>
Date: Mon, 9 Jun 2025 15:55:13 +0000
Subject: [PATCH 2/2] [InstCombine] Preserve NSW/NUW flags when folding const
BOp with min/max
---
.../InstCombine/InstCombineInternal.h | 2 ++
.../InstCombine/InstCombineSelect.cpp | 36 ++++++++++++++-----
.../InstCombine/canonicalize-const-to-bop.ll | 16 ++++-----
3 files changed, 37 insertions(+), 17 deletions(-)
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineInternal.h b/llvm/lib/Transforms/InstCombine/InstCombineInternal.h
index 334462d715f95..48f718bae29af 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineInternal.h
+++ b/llvm/lib/Transforms/InstCombine/InstCombineInternal.h
@@ -767,6 +767,8 @@ class LLVM_LIBRARY_VISIBILITY InstCombinerImpl final
Value *A, Value *B, Instruction &Outer,
SelectPatternFlavor SPF2, Value *C);
Instruction *foldSelectInstWithICmp(SelectInst &SI, ICmpInst *ICI);
+ Value *foldSelectWithConstOpToBinOp(ICmpInst *Cmp, Value *TrueVal,
+ Value *FalseVal);
Instruction *foldSelectValueEquivalence(SelectInst &SI, CmpInst &CI);
bool replaceInInstruction(Value *V, Value *Old, Value *New,
unsigned Depth = 0);
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp b/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
index 8f46ae304353d..062b576369ce2 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineSelect.cpp
@@ -1823,9 +1823,9 @@ static Instruction *foldSelectICmpEq(SelectInst &SI, ICmpInst *ICI,
/// Fold `X Pred C1 ? X BOp C2 : C1 BOp C2` to `min/max(X, C1) BOp C2`.
/// This allows for better canonicalization.
-static Value *foldSelectWithConstOpToBinOp(ICmpInst *Cmp, Value *TrueVal,
- Value *FalseVal,
- IRBuilderBase &Builder) {
+Value *InstCombinerImpl::foldSelectWithConstOpToBinOp(ICmpInst *Cmp,
+ Value *TrueVal,
+ Value *FalseVal) {
Constant *C1, *C2, *C3;
Value *X;
CmpPredicate Predicate;
@@ -1889,11 +1889,29 @@ static Value *foldSelectWithConstOpToBinOp(ICmpInst *Cmp, Value *TrueVal,
return nullptr;
}
- Intrinsic::ID IntrinsicID = getMinMaxIntrinsic(SPF);
- Value *Intrinsic = Builder.CreateBinaryIntrinsic(IntrinsicID, X, RHS);
- return IsIntrinsic ? Builder.CreateBinaryIntrinsic(Opcode, Intrinsic, C2)
- : Builder.CreateBinOp(Instruction::BinaryOps(Opcode),
- Intrinsic, C2);
+ Intrinsic::ID MinMaxID = getMinMaxIntrinsic(SPF);
+ Value *MinMax = Builder.CreateBinaryIntrinsic(MinMaxID, X, RHS);
+ if (IsIntrinsic)
+ return Builder.CreateBinaryIntrinsic(Opcode, MinMax, C2);
+
+ const auto BinOpc = Instruction::BinaryOps(Opcode);
+ Value *BinOp = Builder.CreateBinOp(BinOpc, MinMax, C2);
+
+ // If we can attach no-wrap flags to the new instruction, do so if the
+ // old instruction had them and C1 BinOp C2 does not overflow.
+ if (Instruction *BinOpInst = dyn_cast<Instruction>(BinOp)) {
+ if (BinOpc == Instruction::Add || BinOpc == Instruction::Sub ||
+ BinOpc == Instruction::Mul) {
+ Instruction *OldBinOp = cast<BinaryOperator>(TrueVal);
+ if (OldBinOp->hasNoSignedWrap() &&
+ willNotOverflow(BinOpc, RHS, C2, *BinOpInst, /*IsSigned*/ true))
+ BinOpInst->setHasNoSignedWrap();
+ if (OldBinOp->hasNoUnsignedWrap() &&
+ willNotOverflow(BinOpc, RHS, C2, *BinOpInst, /*IsSigned*/ false))
+ BinOpInst->setHasNoUnsignedWrap();
+ }
+ }
+ return BinOp;
}
/// Visit a SelectInst that has an ICmpInst as its first operand.
@@ -1968,7 +1986,7 @@ Instruction *InstCombinerImpl::foldSelectInstWithICmp(SelectInst &SI,
if (Value *V = foldAbsDiff(ICI, TrueVal, FalseVal, Builder))
return replaceInstUsesWith(SI, V);
- if (Value *V = foldSelectWithConstOpToBinOp(ICI, TrueVal, FalseVal, Builder))
+ if (Value *V = foldSelectWithConstOpToBinOp(ICI, TrueVal, FalseVal))
return replaceInstUsesWith(SI, V);
return Changed ? &SI : nullptr;
diff --git a/llvm/test/Transforms/InstCombine/canonicalize-const-to-bop.ll b/llvm/test/Transforms/InstCombine/canonicalize-const-to-bop.ll
index 120232076f9a6..b3093a92624ae 100644
--- a/llvm/test/Transforms/InstCombine/canonicalize-const-to-bop.ll
+++ b/llvm/test/Transforms/InstCombine/canonicalize-const-to-bop.ll
@@ -5,7 +5,7 @@ define i8 @add_and_sgt(i8 %x) {
; CHECK-LABEL: define i8 @add_and_sgt(
; CHECK-SAME: i8 [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call i8 @llvm.smax.i8(i8 [[X]], i8 8)
-; CHECK-NEXT: [[S:%.*]] = add nuw i8 [[TMP1]], 16
+; CHECK-NEXT: [[S:%.*]] = add nuw nsw i8 [[TMP1]], 16
; CHECK-NEXT: ret i8 [[S]]
;
%add = add nsw i8 %x, 16
@@ -155,7 +155,7 @@ define i8 @multi_use_cond_and_sel(i8 %x) {
; CHECK-NEXT: [[CMP:%.*]] = icmp sgt i8 [[X]], 8
; CHECK-NEXT: call void @use(i1 [[CMP]])
; CHECK-NEXT: [[TMP1:%.*]] = call i8 @llvm.smax.i8(i8 [[X]], i8 8)
-; CHECK-NEXT: [[S:%.*]] = add nuw i8 [[TMP1]], 16
+; CHECK-NEXT: [[S:%.*]] = add nuw nsw i8 [[TMP1]], 16
; CHECK-NEXT: call void @use_byte(i8 [[S]])
; CHECK-NEXT: ret i8 [[S]]
;
@@ -455,7 +455,7 @@ define i8 @add_sgt_nuw_nsw_safe(i8 %x) {
; CHECK-LABEL: define i8 @add_sgt_nuw_nsw_safe(
; CHECK-SAME: i8 [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call i8 @llvm.smin.i8(i8 [[X]], i8 100)
-; CHECK-NEXT: [[S:%.*]] = add nsw i8 [[TMP1]], 1
+; CHECK-NEXT: [[S:%.*]] = add nuw nsw i8 [[TMP1]], 1
; CHECK-NEXT: ret i8 [[S]]
;
%add = add nuw nsw i8 %x, 1
@@ -468,7 +468,7 @@ define i8 @add_sgt_nuw_only(i8 %x) {
; CHECK-LABEL: define i8 @add_sgt_nuw_only(
; CHECK-SAME: i8 [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call i8 @llvm.smin.i8(i8 [[X]], i8 100)
-; CHECK-NEXT: [[S:%.*]] = add i8 [[TMP1]], 50
+; CHECK-NEXT: [[S:%.*]] = add nuw i8 [[TMP1]], 50
; CHECK-NEXT: ret i8 [[S]]
;
%add = add nuw nsw i8 %x, 50
@@ -481,7 +481,7 @@ define i8 @add_sgt_nsw_only(i8 %x) {
; CHECK-LABEL: define i8 @add_sgt_nsw_only(
; CHECK-SAME: i8 [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call i8 @llvm.smin.i8(i8 [[X]], i8 100)
-; CHECK-NEXT: [[S:%.*]] = add i8 [[TMP1]], -99
+; CHECK-NEXT: [[S:%.*]] = add nsw i8 [[TMP1]], -99
; CHECK-NEXT: ret i8 [[S]]
;
%add = add nuw nsw i8 %x, -99
@@ -495,7 +495,7 @@ define i8 @mul_ult_nuw_nsw_safe(i8 %x) {
; CHECK-LABEL: define i8 @mul_ult_nuw_nsw_safe(
; CHECK-SAME: i8 [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call i8 @llvm.umax.i8(i8 [[X]], i8 10)
-; CHECK-NEXT: [[S:%.*]] = mul i8 [[TMP1]], 3
+; CHECK-NEXT: [[S:%.*]] = mul nuw nsw i8 [[TMP1]], 3
; CHECK-NEXT: ret i8 [[S]]
;
%mul = mul nuw nsw i8 %x, 3
@@ -508,7 +508,7 @@ define i8 @mul_ult_nuw_only(i8 %x) {
; CHECK-LABEL: define i8 @mul_ult_nuw_only(
; CHECK-SAME: i8 [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call i8 @llvm.umax.i8(i8 [[X]], i8 10)
-; CHECK-NEXT: [[S:%.*]] = mul i8 [[TMP1]], 25
+; CHECK-NEXT: [[S:%.*]] = mul nuw i8 [[TMP1]], 25
; CHECK-NEXT: ret i8 [[S]]
;
%mul = mul nuw nsw i8 %x, 25
@@ -521,7 +521,7 @@ define i8 @mul_ult_nsw_only(i8 %x) {
; CHECK-LABEL: define i8 @mul_ult_nsw_only(
; CHECK-SAME: i8 [[X:%.*]]) {
; CHECK-NEXT: [[TMP1:%.*]] = call i8 @llvm.umax.i8(i8 [[X]], i8 40)
-; CHECK-NEXT: [[S:%.*]] = mul i8 [[TMP1]], -2
+; CHECK-NEXT: [[S:%.*]] = mul nsw i8 [[TMP1]], -2
; CHECK-NEXT: ret i8 [[S]]
;
%mul = mul nuw nsw i8 %x, -2
More information about the llvm-commits
mailing list