[llvm] [InstCombine] Simplify with.overflow intrinsics with assumption information (PR #84016)
Yingwei Zheng via llvm-commits
llvm-commits at lists.llvm.org
Sun Jan 5 03:02:14 PST 2025
https://github.com/dtcxzyw updated https://github.com/llvm/llvm-project/pull/84016
>From e67d8146d755ba9e3c1def485455390a314edfff Mon Sep 17 00:00:00 2001
From: Yingwei Zheng <dtcxzyw2333 at gmail.com>
Date: Tue, 5 Mar 2024 21:39:20 +0800
Subject: [PATCH 1/3] [InstCombine] Add pre-commit tests. NFC.
---
llvm/test/Transforms/InstCombine/overflow.ll | 106 ++++++++++++++++++-
1 file changed, 101 insertions(+), 5 deletions(-)
diff --git a/llvm/test/Transforms/InstCombine/overflow.ll b/llvm/test/Transforms/InstCombine/overflow.ll
index a8969a5ed02c36..cd4289f84e963e 100644
--- a/llvm/test/Transforms/InstCombine/overflow.ll
+++ b/llvm/test/Transforms/InstCombine/overflow.ll
@@ -11,7 +11,7 @@ define i32 @test1(i32 %a, i32 %b) nounwind ssp {
; CHECK-NEXT: [[TMP0:%.*]] = extractvalue { i32, i1 } [[SADD]], 1
; CHECK-NEXT: br i1 [[TMP0]], label [[IF_THEN:%.*]], label [[IF_END:%.*]]
; CHECK: if.then:
-; CHECK-NEXT: tail call void @throwAnExceptionOrWhatever() #[[ATTR2:[0-9]+]]
+; CHECK-NEXT: tail call void @throwAnExceptionOrWhatever() #[[ATTR3:[0-9]+]]
; CHECK-NEXT: br label [[IF_END]]
; CHECK: if.end:
; CHECK-NEXT: [[SADD_RESULT:%.*]] = extractvalue { i32, i1 } [[SADD]], 0
@@ -49,7 +49,7 @@ define i32 @test2(i32 %a, i32 %b, ptr %P) nounwind ssp {
; CHECK-NEXT: [[TMP0:%.*]] = icmp ugt i64 [[ADD_OFF]], 4294967295
; CHECK-NEXT: br i1 [[TMP0]], label [[IF_THEN:%.*]], label [[IF_END:%.*]]
; CHECK: if.then:
-; CHECK-NEXT: tail call void @throwAnExceptionOrWhatever() #[[ATTR2]]
+; CHECK-NEXT: tail call void @throwAnExceptionOrWhatever() #[[ATTR3]]
; CHECK-NEXT: br label [[IF_END]]
; CHECK: if.end:
; CHECK-NEXT: [[CONV9:%.*]] = trunc i64 [[ADD]] to i32
@@ -86,7 +86,7 @@ define i64 @test3(i32 %a, i32 %b) nounwind ssp {
; CHECK-NEXT: [[TMP1:%.*]] = icmp ult i64 [[TMP0]], -4294967296
; CHECK-NEXT: br i1 [[TMP1]], label [[IF_THEN:%.*]], label [[IF_END:%.*]]
; CHECK: if.then:
-; CHECK-NEXT: tail call void @throwAnExceptionOrWhatever() #[[ATTR2]]
+; CHECK-NEXT: tail call void @throwAnExceptionOrWhatever() #[[ATTR3]]
; CHECK-NEXT: br label [[IF_END]]
; CHECK: if.end:
; CHECK-NEXT: ret i64 [[ADD]]
@@ -116,7 +116,7 @@ define zeroext i8 @test4(i8 signext %a, i8 signext %b) nounwind ssp {
; CHECK-NEXT: [[CMP:%.*]] = extractvalue { i8, i1 } [[SADD]], 1
; CHECK-NEXT: br i1 [[CMP]], label [[IF_THEN:%.*]], label [[IF_END:%.*]]
; CHECK: if.then:
-; CHECK-NEXT: tail call void @throwAnExceptionOrWhatever() #[[ATTR2]]
+; CHECK-NEXT: tail call void @throwAnExceptionOrWhatever() #[[ATTR3]]
; CHECK-NEXT: unreachable
; CHECK: if.end:
; CHECK-NEXT: [[SADD_RESULT:%.*]] = extractvalue { i8, i1 } [[SADD]], 0
@@ -150,7 +150,7 @@ define i32 @test8(i64 %a, i64 %b) nounwind ssp {
; CHECK-NEXT: [[TMP1:%.*]] = icmp ult i64 [[TMP0]], -4294967296
; CHECK-NEXT: br i1 [[TMP1]], label [[IF_THEN:%.*]], label [[IF_END:%.*]]
; CHECK: if.then:
-; CHECK-NEXT: tail call void @throwAnExceptionOrWhatever() #[[ATTR2]]
+; CHECK-NEXT: tail call void @throwAnExceptionOrWhatever() #[[ATTR3]]
; CHECK-NEXT: br label [[IF_END]]
; CHECK: if.end:
; CHECK-NEXT: [[CONV9:%.*]] = trunc i64 [[ADD]] to i32
@@ -171,3 +171,99 @@ if.end:
ret i32 %conv9
}
+define i32 @uadd_no_overflow(i32 %a, i32 %b) {
+; CHECK-LABEL: @uadd_no_overflow(
+; CHECK-NEXT: [[VAL:%.*]] = tail call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 [[A:%.*]], i32 [[B:%.*]])
+; CHECK-NEXT: [[OV:%.*]] = extractvalue { i32, i1 } [[VAL]], 1
+; CHECK-NEXT: [[NOWRAP:%.*]] = xor i1 [[OV]], true
+; CHECK-NEXT: tail call void @llvm.assume(i1 [[NOWRAP]])
+; CHECK-NEXT: [[RES:%.*]] = extractvalue { i32, i1 } [[VAL]], 0
+; CHECK-NEXT: ret i32 [[RES]]
+;
+ %val = tail call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 %a, i32 %b)
+ %ov = extractvalue { i32, i1 } %val, 1
+ %nowrap = xor i1 %ov, true
+ tail call void @llvm.assume(i1 %nowrap)
+ %res = extractvalue { i32, i1 } %val, 0
+ ret i32 %res
+}
+
+define i32 @smul_no_overflow(i32 %a, i32 %b) {
+; CHECK-LABEL: @smul_no_overflow(
+; CHECK-NEXT: [[VAL:%.*]] = tail call { i32, i1 } @llvm.smul.with.overflow.i32(i32 [[A:%.*]], i32 [[B:%.*]])
+; CHECK-NEXT: [[OV:%.*]] = extractvalue { i32, i1 } [[VAL]], 1
+; CHECK-NEXT: [[NOWRAP:%.*]] = xor i1 [[OV]], true
+; CHECK-NEXT: tail call void @llvm.assume(i1 [[NOWRAP]])
+; CHECK-NEXT: [[RES:%.*]] = extractvalue { i32, i1 } [[VAL]], 0
+; CHECK-NEXT: ret i32 [[RES]]
+;
+ %val = tail call { i32, i1 } @llvm.smul.with.overflow.i32(i32 %a, i32 %b)
+ %ov = extractvalue { i32, i1 } %val, 1
+ %nowrap = xor i1 %ov, true
+ tail call void @llvm.assume(i1 %nowrap)
+ %res = extractvalue { i32, i1 } %val, 0
+ ret i32 %res
+}
+
+define i32 @smul_overflow(i32 %a, i32 %b) {
+; CHECK-LABEL: @smul_overflow(
+; CHECK-NEXT: [[VAL:%.*]] = tail call { i32, i1 } @llvm.smul.with.overflow.i32(i32 [[A:%.*]], i32 [[B:%.*]])
+; CHECK-NEXT: [[OV:%.*]] = extractvalue { i32, i1 } [[VAL]], 1
+; CHECK-NEXT: tail call void @llvm.assume(i1 [[OV]])
+; CHECK-NEXT: [[RES:%.*]] = extractvalue { i32, i1 } [[VAL]], 0
+; CHECK-NEXT: ret i32 [[RES]]
+;
+ %val = tail call { i32, i1 } @llvm.smul.with.overflow.i32(i32 %a, i32 %b)
+ %ov = extractvalue { i32, i1 } %val, 1
+ tail call void @llvm.assume(i1 %ov)
+ %res = extractvalue { i32, i1 } %val, 0
+ ret i32 %res
+}
+
+define i32 @uadd_no_overflow_invalid1(i32 %a, i32 %b, i1 %cond) {
+; CHECK-LABEL: @uadd_no_overflow_invalid1(
+; CHECK-NEXT: [[VAL:%.*]] = tail call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 [[A:%.*]], i32 [[B:%.*]])
+; CHECK-NEXT: [[RES:%.*]] = extractvalue { i32, i1 } [[VAL]], 0
+; CHECK-NEXT: call void @use(i32 [[RES]])
+; CHECK-NEXT: br i1 [[COND:%.*]], label [[IF_THEN:%.*]], label [[IF_ELSE:%.*]]
+; CHECK: if.then:
+; CHECK-NEXT: [[OV:%.*]] = extractvalue { i32, i1 } [[VAL]], 1
+; CHECK-NEXT: [[NOWRAP:%.*]] = xor i1 [[OV]], true
+; CHECK-NEXT: tail call void @llvm.assume(i1 [[NOWRAP]])
+; CHECK-NEXT: ret i32 [[RES]]
+; CHECK: if.else:
+; CHECK-NEXT: ret i32 0
+;
+ %val = tail call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 %a, i32 %b)
+ %res = extractvalue { i32, i1 } %val, 0
+ call void @use(i32 %res)
+ br i1 %cond, label %if.then, label %if.else
+if.then:
+ %ov = extractvalue { i32, i1 } %val, 1
+ %nowrap = xor i1 %ov, true
+ tail call void @llvm.assume(i1 %nowrap)
+ ret i32 %res
+if.else:
+ ret i32 0
+}
+
+define i32 @uadd_no_overflow_invalid2(i32 %a, i32 %b, i1 %cond) {
+; CHECK-LABEL: @uadd_no_overflow_invalid2(
+; CHECK-NEXT: [[VAL:%.*]] = tail call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 [[A:%.*]], i32 [[B:%.*]])
+; CHECK-NEXT: [[OV:%.*]] = extractvalue { i32, i1 } [[VAL]], 1
+; CHECK-NEXT: [[NOWRAP:%.*]] = xor i1 [[OV]], true
+; CHECK-NEXT: call void @use(i32 0)
+; CHECK-NEXT: tail call void @llvm.assume(i1 [[NOWRAP]])
+; CHECK-NEXT: [[RES:%.*]] = extractvalue { i32, i1 } [[VAL]], 0
+; CHECK-NEXT: ret i32 [[RES]]
+;
+ %val = tail call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 %a, i32 %b)
+ %ov = extractvalue { i32, i1 } %val, 1
+ %nowrap = xor i1 %ov, true
+ call void @use(i32 0) ; It is not guaranteed to transfer execution to its successors
+ tail call void @llvm.assume(i1 %nowrap)
+ %res = extractvalue { i32, i1 } %val, 0
+ ret i32 %res
+}
+
+declare void @use(i32)
>From fa0dcb6cf55590a20ef57d63bd1ee3436dc06ce0 Mon Sep 17 00:00:00 2001
From: Yingwei Zheng <dtcxzyw2333 at gmail.com>
Date: Tue, 5 Mar 2024 21:44:16 +0800
Subject: [PATCH 2/3] [InstCombine] Simplify with.overflow intrinsics with
assumption information
---
.../InstCombine/InstCombineCalls.cpp | 27 +++++++++++++++++++
llvm/test/Transforms/InstCombine/overflow.ll | 16 +++--------
2 files changed, 31 insertions(+), 12 deletions(-)
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
index fd38738e3be80b..4b4a8c6672c556 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -839,6 +839,33 @@ InstCombinerImpl::foldIntrinsicWithOverflowCommon(IntrinsicInst *II) {
if (OptimizeOverflowCheck(WO->getBinaryOp(), WO->isSigned(), WO->getLHS(),
WO->getRHS(), *WO, OperationResult, OverflowResult))
return createOverflowTuple(WO, OperationResult, OverflowResult);
+
+ // See whether we can optimize the overflow check with assumption information.
+ for (User *U : WO->users()) {
+ if (!match(U, m_ExtractValue<1>(m_Value())))
+ continue;
+
+ for (auto &AssumeVH : AC.assumptionsFor(U)) {
+ if (!AssumeVH)
+ continue;
+ CallInst *I = cast<CallInst>(AssumeVH);
+ if (!match(I->getArgOperand(0), m_Not(m_Specific(U))))
+ continue;
+ if (!isValidAssumeForContext(I, II, &DT))
+ continue;
+ Value *Result =
+ Builder.CreateBinOp(WO->getBinaryOp(), WO->getLHS(), WO->getRHS());
+ if (auto *Inst = dyn_cast<Instruction>(Result)) {
+ if (WO->isSigned())
+ Inst->setHasNoSignedWrap();
+ else
+ Inst->setHasNoUnsignedWrap();
+ }
+ return createOverflowTuple(WO, Result,
+ ConstantInt::getFalse(U->getType()));
+ }
+ }
+
return nullptr;
}
diff --git a/llvm/test/Transforms/InstCombine/overflow.ll b/llvm/test/Transforms/InstCombine/overflow.ll
index cd4289f84e963e..22e1631f78ee91 100644
--- a/llvm/test/Transforms/InstCombine/overflow.ll
+++ b/llvm/test/Transforms/InstCombine/overflow.ll
@@ -173,12 +173,8 @@ if.end:
define i32 @uadd_no_overflow(i32 %a, i32 %b) {
; CHECK-LABEL: @uadd_no_overflow(
-; CHECK-NEXT: [[VAL:%.*]] = tail call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 [[A:%.*]], i32 [[B:%.*]])
-; CHECK-NEXT: [[OV:%.*]] = extractvalue { i32, i1 } [[VAL]], 1
-; CHECK-NEXT: [[NOWRAP:%.*]] = xor i1 [[OV]], true
-; CHECK-NEXT: tail call void @llvm.assume(i1 [[NOWRAP]])
-; CHECK-NEXT: [[RES:%.*]] = extractvalue { i32, i1 } [[VAL]], 0
-; CHECK-NEXT: ret i32 [[RES]]
+; CHECK-NEXT: [[TMP1:%.*]] = add nuw i32 [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT: ret i32 [[TMP1]]
;
%val = tail call { i32, i1 } @llvm.uadd.with.overflow.i32(i32 %a, i32 %b)
%ov = extractvalue { i32, i1 } %val, 1
@@ -190,12 +186,8 @@ define i32 @uadd_no_overflow(i32 %a, i32 %b) {
define i32 @smul_no_overflow(i32 %a, i32 %b) {
; CHECK-LABEL: @smul_no_overflow(
-; CHECK-NEXT: [[VAL:%.*]] = tail call { i32, i1 } @llvm.smul.with.overflow.i32(i32 [[A:%.*]], i32 [[B:%.*]])
-; CHECK-NEXT: [[OV:%.*]] = extractvalue { i32, i1 } [[VAL]], 1
-; CHECK-NEXT: [[NOWRAP:%.*]] = xor i1 [[OV]], true
-; CHECK-NEXT: tail call void @llvm.assume(i1 [[NOWRAP]])
-; CHECK-NEXT: [[RES:%.*]] = extractvalue { i32, i1 } [[VAL]], 0
-; CHECK-NEXT: ret i32 [[RES]]
+; CHECK-NEXT: [[TMP1:%.*]] = mul nsw i32 [[A:%.*]], [[B:%.*]]
+; CHECK-NEXT: ret i32 [[TMP1]]
;
%val = tail call { i32, i1 } @llvm.smul.with.overflow.i32(i32 %a, i32 %b)
%ov = extractvalue { i32, i1 } %val, 1
>From 83b42c3954d03e1d14feaaf186d94389ea1cfc36 Mon Sep 17 00:00:00 2001
From: Yingwei Zheng <dtcxzyw2333 at gmail.com>
Date: Sun, 5 Jan 2025 19:01:43 +0800
Subject: [PATCH 3/3] [InstCombine] Address review comments. NFC.
---
llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
index 4b4a8c6672c556..cdb2c11ef046ad 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -851,10 +851,12 @@ InstCombinerImpl::foldIntrinsicWithOverflowCommon(IntrinsicInst *II) {
CallInst *I = cast<CallInst>(AssumeVH);
if (!match(I->getArgOperand(0), m_Not(m_Specific(U))))
continue;
- if (!isValidAssumeForContext(I, II, &DT))
+ if (!isValidAssumeForContext(I, II, /*DT=*/nullptr,
+ /*AllowEphemerals=*/true))
continue;
Value *Result =
Builder.CreateBinOp(WO->getBinaryOp(), WO->getLHS(), WO->getRHS());
+ Result->takeName(WO);
if (auto *Inst = dyn_cast<Instruction>(Result)) {
if (WO->isSigned())
Inst->setHasNoSignedWrap();
More information about the llvm-commits
mailing list