[InstCombine] Simplify @llvm.usub.with.overflow+non-zero check (PR43251)

Summary:
This is again motivated by D67122 sanitizer check enhancement.
That patch seemingly worsens `-fsanitize=pointer-overflow`
overhead from 25% to 50%, which strongly implies missing folds.

In this particular case, given
```
char* test(char& base, unsigned long offset) {
  return &base - offset;
}
```
it will end up producing something like
https://godbolt.org/z/luGEju
which after optimizations reduces down to roughly
```
declare void @use64(i64)
define i1 @test(i8* dereferenceable(1) %base, i64 %offset) {
  %base_int = ptrtoint i8* %base to i64
  %adjusted = sub i64 %base_int, %offset
  call void @use64(i64 %adjusted)
  %not_null = icmp ne i64 %adjusted, 0
  %no_underflow = icmp ule i64 %adjusted, %base_int
  %no_underflow_and_not_null = and i1 %not_null, %no_underflow
  ret i1 %no_underflow_and_not_null
}
```
Without D67122 there was no `%not_null`,
and in this particular case we can "get rid of it", by merging two checks:
Here we are checking: `Base u>= Offset && (Base u- Offset) != 0`, but that is simply `Base u> Offset`

Alive proofs:
https://rise4fun.com/Alive/QOs

The `@llvm.usub.with.overflow` pattern itself is not handled here
because this is the main pattern, that we currently consider canonical.

https://bugs.llvm.org/show_bug.cgi?id=43251

Reviewers: spatel, nikic, xbolva00, majnemer

Reviewed By: xbolva00, majnemer

Subscribers: vsk, majnemer, xbolva00, hiraditya, llvm-commits

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D67356

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@372341 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp b/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp
index 9b2fccac670080c9c139396c67fce7e87875ee73..9f901355b98e0dfcacecd43263b0f69022b3d29c 100644 (file)
--- a/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp
+++ b/lib/Transforms/InstCombine/InstCombineAndOrXor.cpp
@@ -1084,6 +1084,27 @@ static Value *foldUnsignedUnderflowCheck(ICmpInst *ZeroICmp,
       return Builder.CreateICmpULE(Base, Offset);
   }
 
+  if (!match(UnsignedICmp,
+             m_c_ICmp(UnsignedPred, m_Specific(Base), m_Specific(Offset))) ||
+      !ICmpInst::isUnsigned(UnsignedPred))
+    return nullptr;
+  if (UnsignedICmp->getOperand(0) != Base)
+    UnsignedPred = ICmpInst::getSwappedPredicate(UnsignedPred);
+
+  // Base >=/> Offset && (Base - Offset) != 0  <-->  Base > Offset
+  // (no overflow and not null)
+  if ((UnsignedPred == ICmpInst::ICMP_UGE ||
+       UnsignedPred == ICmpInst::ICMP_UGT) &&
+      EqPred == ICmpInst::ICMP_NE && IsAnd)
+    return Builder.CreateICmpUGT(Base, Offset);
+
+  // Base <=/< Offset || (Base - Offset) == 0  <-->  Base <= Offset
+  // (overflow or null)
+  if ((UnsignedPred == ICmpInst::ICMP_ULE ||
+       UnsignedPred == ICmpInst::ICMP_ULT) &&
+      EqPred == ICmpInst::ICMP_EQ && !IsAnd)
+    return Builder.CreateICmpULE(Base, Offset);
+
   return nullptr;
 }
 

diff --git a/test/Transforms/InstCombine/result-of-usub-is-non-zero-and-no-overflow.ll b/test/Transforms/InstCombine/result-of-usub-is-non-zero-and-no-overflow.ll
index ba260c9e7612d3a4cd54d6bb56956e31764251c9..8a5b444d3ede9fe7a8536ff1b636c97c88e1d4b5 100644 (file)
--- a/test/Transforms/InstCombine/result-of-usub-is-non-zero-and-no-overflow.ll
+++ b/test/Transforms/InstCombine/result-of-usub-is-non-zero-and-no-overflow.ll
@@ -24,8 +24,8 @@ define i1 @t0_noncanonical_ignoreme(i8 %base, i8 %offset) {
 ; CHECK-NEXT:    call void @use1(i1 [[NO_UNDERFLOW]])
 ; CHECK-NEXT:    [[NOT_NULL:%.*]] = icmp ne i8 [[ADJUSTED]], 0
 ; CHECK-NEXT:    call void @use1(i1 [[NOT_NULL]])
-; CHECK-NEXT:    [[R:%.*]] = and i1 [[NOT_NULL]], [[NO_UNDERFLOW]]
-; CHECK-NEXT:    ret i1 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ugt i8 [[BASE]], [[OFFSET]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %adjusted = sub i8 %base, %offset
   call void @use8(i8 %adjusted)
@@ -45,8 +45,8 @@ define i1 @t1(i8 %base, i8 %offset) {
 ; CHECK-NEXT:    call void @use1(i1 [[NO_UNDERFLOW]])
 ; CHECK-NEXT:    [[NOT_NULL:%.*]] = icmp ne i8 [[ADJUSTED]], 0
 ; CHECK-NEXT:    call void @use1(i1 [[NOT_NULL]])
-; CHECK-NEXT:    [[R:%.*]] = and i1 [[NOT_NULL]], [[NO_UNDERFLOW]]
-; CHECK-NEXT:    ret i1 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ugt i8 [[BASE]], [[OFFSET]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %adjusted = sub i8 %base, %offset
   call void @use8(i8 %adjusted)
@@ -65,8 +65,8 @@ define i1 @t1_strict(i8 %base, i8 %offset) {
 ; CHECK-NEXT:    call void @use1(i1 [[NO_UNDERFLOW]])
 ; CHECK-NEXT:    [[NOT_NULL:%.*]] = icmp ne i8 [[ADJUSTED]], 0
 ; CHECK-NEXT:    call void @use1(i1 [[NOT_NULL]])
-; CHECK-NEXT:    [[R:%.*]] = and i1 [[NOT_NULL]], [[NO_UNDERFLOW]]
-; CHECK-NEXT:    ret i1 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ugt i8 [[BASE]], [[OFFSET]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %adjusted = sub i8 %base, %offset
   call void @use8(i8 %adjusted)
@@ -115,8 +115,8 @@ define i1 @t3_commutability0(i8 %base, i8 %offset) {
 ; CHECK-NEXT:    call void @use1(i1 [[NO_UNDERFLOW]])
 ; CHECK-NEXT:    [[NOT_NULL:%.*]] = icmp ne i8 [[ADJUSTED]], 0
 ; CHECK-NEXT:    call void @use1(i1 [[NOT_NULL]])
-; CHECK-NEXT:    [[R:%.*]] = and i1 [[NOT_NULL]], [[NO_UNDERFLOW]]
-; CHECK-NEXT:    ret i1 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ugt i8 [[BASE]], [[OFFSET]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %adjusted = sub i8 %base, %offset
   call void @use8(i8 %adjusted)
@@ -135,8 +135,8 @@ define i1 @t4_commutability1(i8 %base, i8 %offset) {
 ; CHECK-NEXT:    call void @use1(i1 [[NO_UNDERFLOW]])
 ; CHECK-NEXT:    [[NOT_NULL:%.*]] = icmp ne i8 [[ADJUSTED]], 0
 ; CHECK-NEXT:    call void @use1(i1 [[NOT_NULL]])
-; CHECK-NEXT:    [[R:%.*]] = and i1 [[NO_UNDERFLOW]], [[NOT_NULL]]
-; CHECK-NEXT:    ret i1 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ugt i8 [[BASE]], [[OFFSET]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %adjusted = sub i8 %base, %offset
   call void @use8(i8 %adjusted)
@@ -155,8 +155,8 @@ define i1 @t5_commutability2(i8 %base, i8 %offset) {
 ; CHECK-NEXT:    call void @use1(i1 [[NO_UNDERFLOW]])
 ; CHECK-NEXT:    [[NOT_NULL:%.*]] = icmp ne i8 [[ADJUSTED]], 0
 ; CHECK-NEXT:    call void @use1(i1 [[NOT_NULL]])
-; CHECK-NEXT:    [[R:%.*]] = and i1 [[NO_UNDERFLOW]], [[NOT_NULL]]
-; CHECK-NEXT:    ret i1 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ugt i8 [[BASE]], [[OFFSET]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %adjusted = sub i8 %base, %offset
   call void @use8(i8 %adjusted)
@@ -206,8 +206,8 @@ define i1 @t7(i8 %base, i8 %offset) {
 ; CHECK-NEXT:    call void @use1(i1 [[UNDERFLOW]])
 ; CHECK-NEXT:    [[NULL:%.*]] = icmp eq i8 [[ADJUSTED]], 0
 ; CHECK-NEXT:    call void @use1(i1 [[NULL]])
-; CHECK-NEXT:    [[R:%.*]] = or i1 [[NULL]], [[UNDERFLOW]]
-; CHECK-NEXT:    ret i1 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ule i8 [[BASE]], [[OFFSET]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %adjusted = sub i8 %base, %offset
   call void @use8(i8 %adjusted)
@@ -226,8 +226,8 @@ define i1 @t7_nonstrict(i8 %base, i8 %offset) {
 ; CHECK-NEXT:    call void @use1(i1 [[UNDERFLOW]])
 ; CHECK-NEXT:    [[NULL:%.*]] = icmp eq i8 [[ADJUSTED]], 0
 ; CHECK-NEXT:    call void @use1(i1 [[NULL]])
-; CHECK-NEXT:    [[R:%.*]] = or i1 [[NULL]], [[UNDERFLOW]]
-; CHECK-NEXT:    ret i1 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ule i8 [[BASE]], [[OFFSET]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %adjusted = sub i8 %base, %offset
   call void @use8(i8 %adjusted)
@@ -272,8 +272,8 @@ define i1 @t9_commutative(i8 %base, i8 %offset) {
 ; CHECK-NEXT:    call void @use1(i1 [[UNDERFLOW]])
 ; CHECK-NEXT:    [[NULL:%.*]] = icmp eq i8 [[ADJUSTED]], 0
 ; CHECK-NEXT:    call void @use1(i1 [[NULL]])
-; CHECK-NEXT:    [[R:%.*]] = or i1 [[NULL]], [[UNDERFLOW]]
-; CHECK-NEXT:    ret i1 [[R]]
+; CHECK-NEXT:    [[TMP1:%.*]] = icmp ule i8 [[BASE]], [[OFFSET]]
+; CHECK-NEXT:    ret i1 [[TMP1]]
 ;
   %adjusted = sub i8 %base, %offset
   call void @use8(i8 %adjusted)