From c86e1ce73bb6d70d255df9bf7700d09db07e7af8 Mon Sep 17 00:00:00 2001 From: Nikita Popov Date: Wed, 1 Sep 2021 23:13:01 +0200 Subject: [PATCH] [SCEVExpander] Simplify pointer overflow check This is a followup to D104662 to generate slightly nicer code for pointer overflow checks. Bypass expandAddToGEP and instead explicitly generate i8 GEPs. This saves some bitcasts and negates the value in a more obvious way. In particular, this prevents SCEV from looking through the umul.with.overflow, same as in the integer case. The wrapping-pointer-ni.ll test deserves a comment: Previously, this generated a typed GEP which used the umulo argument rather than the multiplication result. This results in more compact IR in that case, but effectively does the multiplication twice, the second one is just hidden in the GEP. Reusing the umulo result seems pretty reasonable to me. Differential Revision: https://reviews.llvm.org/D109093 --- .../Utils/ScalarEvolutionExpander.cpp | 11 +- .../LoopAccessAnalysis/wrapping-pointer-ni.ll | 9 +- .../scev-inserted-runtime-check.ll | 50 +++---- .../wrapping-pointer-versioning.ll | 125 ++++++++---------- 4 files changed, 87 insertions(+), 108 deletions(-) diff --git a/llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp b/llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp index ba4876b2f4d4..a4aa1fa46a76 100644 --- a/llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp +++ b/llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp @@ -2490,12 +2490,11 @@ Value *SCEVExpander::generateOverflowCheck(const SCEVAddRecExpr *AR, // Start - |Step| * Backedge > Start Value *Add = nullptr, *Sub = nullptr; if (PointerType *ARPtrTy = dyn_cast(ARTy)) { - const SCEV *MulS = SE.getSCEV(MulV); - const SCEV *NegMulS = SE.getNegativeSCEV(MulS); - Add = Builder.CreateBitCast(expandAddToGEP(MulS, ARPtrTy, Ty, StartValue), - ARPtrTy); - Sub = Builder.CreateBitCast( - expandAddToGEP(NegMulS, ARPtrTy, Ty, StartValue), ARPtrTy); + StartValue = InsertNoopCastOfTo( + StartValue, Builder.getInt8PtrTy(ARPtrTy->getAddressSpace())); + Value *NegMulV = Builder.CreateNeg(MulV); + Add = Builder.CreateGEP(Builder.getInt8Ty(), StartValue, MulV); + Sub = Builder.CreateGEP(Builder.getInt8Ty(), StartValue, NegMulV); } else { Add = Builder.CreateAdd(StartValue, MulV); Sub = Builder.CreateSub(StartValue, MulV); diff --git a/llvm/test/Analysis/LoopAccessAnalysis/wrapping-pointer-ni.ll b/llvm/test/Analysis/LoopAccessAnalysis/wrapping-pointer-ni.ll index 8bceaa212743..61f5405a27bc 100644 --- a/llvm/test/Analysis/LoopAccessAnalysis/wrapping-pointer-ni.ll +++ b/llvm/test/Analysis/LoopAccessAnalysis/wrapping-pointer-ni.ll @@ -17,10 +17,11 @@ define void @"japi1_align!_9477"(%jl_value_t addrspace(10)** %arg) { ; LV: [[OFMul:%[^ ]*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 4, i64 [[Step:%[^ ]*]]) ; LV-NEXT: [[OFMulResult:%[^ ]*]] = extractvalue { i64, i1 } [[OFMul]], 0 ; LV-NEXT: [[OFMulOverflow:%[^ ]*]] = extractvalue { i64, i1 } [[OFMul]], 1 -; LV-NEXT: [[PosGEP:%[^ ]*]] = getelementptr i32, i32 addrspace(13)* [[Base:%[^ ]*]], i64 [[Step]] -; LV-NEXT: [[NegGEP:%[^ ]*]] = getelementptr i32, i32 addrspace(13)* [[Base]], i64 [[NegStep:%[^ ]*]] -; LV-NEXT: icmp ugt i32 addrspace(13)* [[NegGEP]], [[Base]] -; LV-NEXT: icmp ult i32 addrspace(13)* [[PosGEP]], [[Base]] +; LV: [[OFNegMulResult:%[^ ]*]] = sub i64 0, [[OFMulResult]] +; LV-NEXT: [[PosGEP:%[^ ]*]] = getelementptr i8, i8 addrspace(13)* [[Base:%[^ ]*]], i64 [[OFMulResult]] +; LV-NEXT: [[NegGEP:%[^ ]*]] = getelementptr i8, i8 addrspace(13)* [[Base]], i64 [[OFNegMulResult]] +; LV-NEXT: icmp ugt i8 addrspace(13)* [[NegGEP]], [[Base]] +; LV-NEXT: icmp ult i8 addrspace(13)* [[PosGEP]], [[Base]] ; LV-NOT: inttoptr ; LV-NOT: ptrtoint top: diff --git a/llvm/test/Transforms/LoopDistribute/scev-inserted-runtime-check.ll b/llvm/test/Transforms/LoopDistribute/scev-inserted-runtime-check.ll index da2aa44e7e3a..5dd6c28a34c8 100644 --- a/llvm/test/Transforms/LoopDistribute/scev-inserted-runtime-check.ll +++ b/llvm/test/Transforms/LoopDistribute/scev-inserted-runtime-check.ll @@ -29,18 +29,15 @@ define void @f(i32* noalias %a, i32* noalias %b, i32* noalias %c, i32* noalias % ; CHECK-NEXT: [[MUL2:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 8, i64 [[TMP0]]) ; CHECK-NEXT: [[MUL_RESULT3:%.*]] = extractvalue { i64, i1 } [[MUL2]], 0 ; CHECK-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1 -; CHECK-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, i8* [[A5]], i64 [[MUL_RESULT3]] -; CHECK-NEXT: [[TMP11:%.*]] = bitcast i8* [[UGLYGEP]] to i32* -; CHECK-NEXT: [[TMP12:%.*]] = sub i64 [[MUL_RESULT3]], -8 -; CHECK-NEXT: [[TMP13:%.*]] = sub i64 8, [[TMP12]] -; CHECK-NEXT: [[UGLYGEP6:%.*]] = getelementptr i8, i8* [[A5]], i64 [[TMP13]] -; CHECK-NEXT: [[TMP14:%.*]] = bitcast i8* [[UGLYGEP6]] to i32* -; CHECK-NEXT: [[TMP15:%.*]] = icmp ugt i32* [[TMP14]], [[A]] -; CHECK-NEXT: [[TMP16:%.*]] = icmp ult i32* [[TMP11]], [[A]] -; CHECK-NEXT: [[TMP17:%.*]] = select i1 false, i1 [[TMP15]], i1 [[TMP16]] -; CHECK-NEXT: [[TMP18:%.*]] = or i1 [[TMP17]], [[MUL_OVERFLOW4]] -; CHECK-NEXT: [[TMP19:%.*]] = or i1 [[TMP10]], [[TMP18]] -; CHECK-NEXT: br i1 [[TMP19]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH_LDIST1:%.*]] +; CHECK-NEXT: [[TMP11:%.*]] = sub i64 0, [[MUL_RESULT3]] +; CHECK-NEXT: [[TMP12:%.*]] = getelementptr i8, i8* [[A5]], i64 [[MUL_RESULT3]] +; CHECK-NEXT: [[TMP13:%.*]] = getelementptr i8, i8* [[A5]], i64 [[TMP11]] +; CHECK-NEXT: [[TMP14:%.*]] = icmp ugt i8* [[TMP13]], [[A5]] +; CHECK-NEXT: [[TMP15:%.*]] = icmp ult i8* [[TMP12]], [[A5]] +; CHECK-NEXT: [[TMP16:%.*]] = select i1 false, i1 [[TMP14]], i1 [[TMP15]] +; CHECK-NEXT: [[TMP17:%.*]] = or i1 [[TMP16]], [[MUL_OVERFLOW4]] +; CHECK-NEXT: [[TMP18:%.*]] = or i1 [[TMP10]], [[TMP17]] +; CHECK-NEXT: br i1 [[TMP18]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH_LDIST1:%.*]] ; CHECK: for.body.ph.lver.orig: ; CHECK-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]] ; CHECK: for.body.lver.orig: @@ -101,10 +98,10 @@ define void @f(i32* noalias %a, i32* noalias %b, i32* noalias %c, i32* noalias % ; CHECK-NEXT: [[ARRAYIDXC:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 [[MUL_EXT]] ; CHECK-NEXT: store i32 [[MULC]], i32* [[ARRAYIDXC]], align 4 ; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[ADD]], [[N]] -; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT7:%.*]], label [[FOR_BODY]] +; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT6:%.*]], label [[FOR_BODY]] ; CHECK: for.end.loopexit: ; CHECK-NEXT: br label [[FOR_END:%.*]] -; CHECK: for.end.loopexit7: +; CHECK: for.end.loopexit6: ; CHECK-NEXT: br label [[FOR_END]] ; CHECK: for.end: ; CHECK-NEXT: ret void @@ -181,18 +178,15 @@ define void @f_with_offset(i32* noalias %b, i32* noalias %c, i32* noalias %d, i3 ; CHECK-NEXT: [[MUL2:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 8, i64 [[TMP0]]) ; CHECK-NEXT: [[MUL_RESULT3:%.*]] = extractvalue { i64, i1 } [[MUL2]], 0 ; CHECK-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1 -; CHECK-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, i8* bitcast (i32* getelementptr inbounds ([8192 x i32], [8192 x i32]* @global_a, i64 0, i64 42) to i8*), i64 [[MUL_RESULT3]] -; CHECK-NEXT: [[TMP11:%.*]] = bitcast i8* [[UGLYGEP]] to [8192 x i32]* -; CHECK-NEXT: [[TMP12:%.*]] = sub i64 [[MUL_RESULT3]], -8 -; CHECK-NEXT: [[TMP13:%.*]] = sub i64 8, [[TMP12]] -; CHECK-NEXT: [[UGLYGEP5:%.*]] = getelementptr i8, i8* bitcast (i32* getelementptr inbounds ([8192 x i32], [8192 x i32]* @global_a, i64 0, i64 42) to i8*), i64 [[TMP13]] -; CHECK-NEXT: [[TMP14:%.*]] = bitcast i8* [[UGLYGEP5]] to [8192 x i32]* -; CHECK-NEXT: [[TMP15:%.*]] = icmp ugt [8192 x i32]* [[TMP14]], bitcast (i32* getelementptr inbounds ([8192 x i32], [8192 x i32]* @global_a, i64 0, i64 42) to [8192 x i32]*) -; CHECK-NEXT: [[TMP16:%.*]] = icmp ult [8192 x i32]* [[TMP11]], bitcast (i32* getelementptr inbounds ([8192 x i32], [8192 x i32]* @global_a, i64 0, i64 42) to [8192 x i32]*) -; CHECK-NEXT: [[TMP17:%.*]] = select i1 false, i1 [[TMP15]], i1 [[TMP16]] -; CHECK-NEXT: [[TMP18:%.*]] = or i1 [[TMP17]], [[MUL_OVERFLOW4]] -; CHECK-NEXT: [[TMP19:%.*]] = or i1 [[TMP10]], [[TMP18]] -; CHECK-NEXT: br i1 [[TMP19]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH_LDIST1:%.*]] +; CHECK-NEXT: [[TMP11:%.*]] = sub i64 0, [[MUL_RESULT3]] +; CHECK-NEXT: [[TMP12:%.*]] = getelementptr i8, i8* bitcast (i32* getelementptr inbounds ([8192 x i32], [8192 x i32]* @global_a, i64 0, i64 42) to i8*), i64 [[MUL_RESULT3]] +; CHECK-NEXT: [[TMP13:%.*]] = getelementptr i8, i8* bitcast (i32* getelementptr inbounds ([8192 x i32], [8192 x i32]* @global_a, i64 0, i64 42) to i8*), i64 [[TMP11]] +; CHECK-NEXT: [[TMP14:%.*]] = icmp ugt i8* [[TMP13]], bitcast (i32* getelementptr inbounds ([8192 x i32], [8192 x i32]* @global_a, i64 0, i64 42) to i8*) +; CHECK-NEXT: [[TMP15:%.*]] = icmp ult i8* [[TMP12]], bitcast (i32* getelementptr inbounds ([8192 x i32], [8192 x i32]* @global_a, i64 0, i64 42) to i8*) +; CHECK-NEXT: [[TMP16:%.*]] = select i1 false, i1 [[TMP14]], i1 [[TMP15]] +; CHECK-NEXT: [[TMP17:%.*]] = or i1 [[TMP16]], [[MUL_OVERFLOW4]] +; CHECK-NEXT: [[TMP18:%.*]] = or i1 [[TMP10]], [[TMP17]] +; CHECK-NEXT: br i1 [[TMP18]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH_LDIST1:%.*]] ; CHECK: for.body.ph.lver.orig: ; CHECK-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]] ; CHECK: for.body.lver.orig: @@ -253,10 +247,10 @@ define void @f_with_offset(i32* noalias %b, i32* noalias %c, i32* noalias %d, i3 ; CHECK-NEXT: [[ARRAYIDXC:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 [[MUL_EXT]] ; CHECK-NEXT: store i32 [[MULC]], i32* [[ARRAYIDXC]], align 4 ; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[ADD]], [[N]] -; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT6:%.*]], label [[FOR_BODY]] +; CHECK-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT5:%.*]], label [[FOR_BODY]] ; CHECK: for.end.loopexit: ; CHECK-NEXT: br label [[FOR_END:%.*]] -; CHECK: for.end.loopexit6: +; CHECK: for.end.loopexit5: ; CHECK-NEXT: br label [[FOR_END]] ; CHECK: for.end: ; CHECK-NEXT: ret void diff --git a/llvm/test/Transforms/LoopVersioning/wrapping-pointer-versioning.ll b/llvm/test/Transforms/LoopVersioning/wrapping-pointer-versioning.ll index 2a4039d441c3..84a6b67548d1 100644 --- a/llvm/test/Transforms/LoopVersioning/wrapping-pointer-versioning.ll +++ b/llvm/test/Transforms/LoopVersioning/wrapping-pointer-versioning.ll @@ -46,18 +46,15 @@ define void @f1(i16* noalias %a, ; LV-NEXT: [[MUL2:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 4, i64 [[TMP0]]) ; LV-NEXT: [[MUL_RESULT3:%.*]] = extractvalue { i64, i1 } [[MUL2]], 0 ; LV-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1 -; LV-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, i8* [[A5]], i64 [[MUL_RESULT3]] -; LV-NEXT: [[TMP11:%.*]] = bitcast i8* [[UGLYGEP]] to i16* -; LV-NEXT: [[TMP12:%.*]] = sub i64 [[MUL_RESULT3]], -4 -; LV-NEXT: [[TMP13:%.*]] = sub i64 4, [[TMP12]] -; LV-NEXT: [[UGLYGEP6:%.*]] = getelementptr i8, i8* [[A5]], i64 [[TMP13]] -; LV-NEXT: [[TMP14:%.*]] = bitcast i8* [[UGLYGEP6]] to i16* -; LV-NEXT: [[TMP15:%.*]] = icmp ugt i16* [[TMP14]], [[A]] -; LV-NEXT: [[TMP16:%.*]] = icmp ult i16* [[TMP11]], [[A]] -; LV-NEXT: [[TMP17:%.*]] = select i1 false, i1 [[TMP15]], i1 [[TMP16]] -; LV-NEXT: [[TMP18:%.*]] = or i1 [[TMP17]], [[MUL_OVERFLOW4]] -; LV-NEXT: [[TMP19:%.*]] = or i1 [[TMP10]], [[TMP18]] -; LV-NEXT: br i1 [[TMP19]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH:%.*]] +; LV-NEXT: [[TMP11:%.*]] = sub i64 0, [[MUL_RESULT3]] +; LV-NEXT: [[TMP12:%.*]] = getelementptr i8, i8* [[A5]], i64 [[MUL_RESULT3]] +; LV-NEXT: [[TMP13:%.*]] = getelementptr i8, i8* [[A5]], i64 [[TMP11]] +; LV-NEXT: [[TMP14:%.*]] = icmp ugt i8* [[TMP13]], [[A5]] +; LV-NEXT: [[TMP15:%.*]] = icmp ult i8* [[TMP12]], [[A5]] +; LV-NEXT: [[TMP16:%.*]] = select i1 false, i1 [[TMP14]], i1 [[TMP15]] +; LV-NEXT: [[TMP17:%.*]] = or i1 [[TMP16]], [[MUL_OVERFLOW4]] +; LV-NEXT: [[TMP18:%.*]] = or i1 [[TMP10]], [[TMP17]] +; LV-NEXT: br i1 [[TMP18]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH:%.*]] ; LV: for.body.ph.lver.orig: ; LV-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]] ; LV: for.body.lver.orig: @@ -91,10 +88,10 @@ define void @f1(i16* noalias %a, ; LV-NEXT: [[INC]] = add nuw nsw i64 [[IND]], 1 ; LV-NEXT: [[INC1]] = add i32 [[IND1]], 1 ; LV-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INC]], [[N]] -; LV-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT7:%.*]], label [[FOR_BODY]] +; LV-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT6:%.*]], label [[FOR_BODY]] ; LV: for.end.loopexit: ; LV-NEXT: br label [[FOR_END:%.*]] -; LV: for.end.loopexit7: +; LV: for.end.loopexit6: ; LV-NEXT: br label [[FOR_END]] ; LV: for.end: ; LV-NEXT: ret void @@ -181,18 +178,15 @@ define void @f2(i16* noalias %a, ; LV-NEXT: [[MUL_RESULT3:%.*]] = extractvalue { i64, i1 } [[MUL2]], 0 ; LV-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1 ; LV-NEXT: [[SCEVGEP5:%.*]] = bitcast i16* [[SCEVGEP]] to i8* -; LV-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[MUL_RESULT3]] -; LV-NEXT: [[TMP15:%.*]] = bitcast i8* [[UGLYGEP]] to i16* -; LV-NEXT: [[TMP16:%.*]] = sub i64 [[MUL_RESULT3]], -4 -; LV-NEXT: [[TMP17:%.*]] = sub i64 4, [[TMP16]] -; LV-NEXT: [[UGLYGEP6:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[TMP17]] -; LV-NEXT: [[TMP18:%.*]] = bitcast i8* [[UGLYGEP6]] to i16* -; LV-NEXT: [[TMP19:%.*]] = icmp ugt i16* [[TMP18]], [[SCEVGEP]] -; LV-NEXT: [[TMP20:%.*]] = icmp ult i16* [[TMP15]], [[SCEVGEP]] -; LV-NEXT: [[TMP21:%.*]] = select i1 true, i1 [[TMP19]], i1 [[TMP20]] -; LV-NEXT: [[TMP22:%.*]] = or i1 [[TMP21]], [[MUL_OVERFLOW4]] -; LV-NEXT: [[TMP23:%.*]] = or i1 [[TMP11]], [[TMP22]] -; LV-NEXT: br i1 [[TMP23]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH:%.*]] +; LV-NEXT: [[TMP15:%.*]] = sub i64 0, [[MUL_RESULT3]] +; LV-NEXT: [[TMP16:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[MUL_RESULT3]] +; LV-NEXT: [[TMP17:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[TMP15]] +; LV-NEXT: [[TMP18:%.*]] = icmp ugt i8* [[TMP17]], [[SCEVGEP5]] +; LV-NEXT: [[TMP19:%.*]] = icmp ult i8* [[TMP16]], [[SCEVGEP5]] +; LV-NEXT: [[TMP20:%.*]] = select i1 true, i1 [[TMP18]], i1 [[TMP19]] +; LV-NEXT: [[TMP21:%.*]] = or i1 [[TMP20]], [[MUL_OVERFLOW4]] +; LV-NEXT: [[TMP22:%.*]] = or i1 [[TMP11]], [[TMP21]] +; LV-NEXT: br i1 [[TMP22]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH:%.*]] ; LV: for.body.ph.lver.orig: ; LV-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]] ; LV: for.body.lver.orig: @@ -226,10 +220,10 @@ define void @f2(i16* noalias %a, ; LV-NEXT: [[INC]] = add nuw nsw i64 [[IND]], 1 ; LV-NEXT: [[DEC]] = sub i32 [[IND1]], 1 ; LV-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INC]], [[N]] -; LV-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT7:%.*]], label [[FOR_BODY]] +; LV-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT6:%.*]], label [[FOR_BODY]] ; LV: for.end.loopexit: ; LV-NEXT: br label [[FOR_END:%.*]] -; LV: for.end.loopexit7: +; LV: for.end.loopexit6: ; LV-NEXT: br label [[FOR_END]] ; LV: for.end: ; LV-NEXT: ret void @@ -295,18 +289,15 @@ define void @f3(i16* noalias %a, ; LV-NEXT: [[MUL2:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 4, i64 [[TMP0]]) ; LV-NEXT: [[MUL_RESULT3:%.*]] = extractvalue { i64, i1 } [[MUL2]], 0 ; LV-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1 -; LV-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, i8* [[A5]], i64 [[MUL_RESULT3]] -; LV-NEXT: [[TMP11:%.*]] = bitcast i8* [[UGLYGEP]] to i16* -; LV-NEXT: [[TMP12:%.*]] = sub i64 [[MUL_RESULT3]], -4 -; LV-NEXT: [[TMP13:%.*]] = sub i64 4, [[TMP12]] -; LV-NEXT: [[UGLYGEP6:%.*]] = getelementptr i8, i8* [[A5]], i64 [[TMP13]] -; LV-NEXT: [[TMP14:%.*]] = bitcast i8* [[UGLYGEP6]] to i16* -; LV-NEXT: [[TMP15:%.*]] = icmp ugt i16* [[TMP14]], [[A]] -; LV-NEXT: [[TMP16:%.*]] = icmp ult i16* [[TMP11]], [[A]] -; LV-NEXT: [[TMP17:%.*]] = select i1 false, i1 [[TMP15]], i1 [[TMP16]] -; LV-NEXT: [[TMP18:%.*]] = or i1 [[TMP17]], [[MUL_OVERFLOW4]] -; LV-NEXT: [[TMP19:%.*]] = or i1 [[TMP10]], [[TMP18]] -; LV-NEXT: br i1 [[TMP19]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH:%.*]] +; LV-NEXT: [[TMP11:%.*]] = sub i64 0, [[MUL_RESULT3]] +; LV-NEXT: [[TMP12:%.*]] = getelementptr i8, i8* [[A5]], i64 [[MUL_RESULT3]] +; LV-NEXT: [[TMP13:%.*]] = getelementptr i8, i8* [[A5]], i64 [[TMP11]] +; LV-NEXT: [[TMP14:%.*]] = icmp ugt i8* [[TMP13]], [[A5]] +; LV-NEXT: [[TMP15:%.*]] = icmp ult i8* [[TMP12]], [[A5]] +; LV-NEXT: [[TMP16:%.*]] = select i1 false, i1 [[TMP14]], i1 [[TMP15]] +; LV-NEXT: [[TMP17:%.*]] = or i1 [[TMP16]], [[MUL_OVERFLOW4]] +; LV-NEXT: [[TMP18:%.*]] = or i1 [[TMP10]], [[TMP17]] +; LV-NEXT: br i1 [[TMP18]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH:%.*]] ; LV: for.body.ph.lver.orig: ; LV-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]] ; LV: for.body.lver.orig: @@ -340,10 +331,10 @@ define void @f3(i16* noalias %a, ; LV-NEXT: [[INC]] = add nuw nsw i64 [[IND]], 1 ; LV-NEXT: [[INC1]] = add i32 [[IND1]], 1 ; LV-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INC]], [[N]] -; LV-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT7:%.*]], label [[FOR_BODY]] +; LV-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT6:%.*]], label [[FOR_BODY]] ; LV: for.end.loopexit: ; LV-NEXT: br label [[FOR_END:%.*]] -; LV: for.end.loopexit7: +; LV: for.end.loopexit6: ; LV-NEXT: br label [[FOR_END]] ; LV: for.end: ; LV-NEXT: ret void @@ -404,18 +395,15 @@ define void @f4(i16* noalias %a, ; LV-NEXT: [[MUL_RESULT3:%.*]] = extractvalue { i64, i1 } [[MUL2]], 0 ; LV-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1 ; LV-NEXT: [[SCEVGEP5:%.*]] = bitcast i16* [[SCEVGEP]] to i8* -; LV-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[MUL_RESULT3]] -; LV-NEXT: [[TMP13:%.*]] = bitcast i8* [[UGLYGEP]] to i16* -; LV-NEXT: [[TMP14:%.*]] = sub i64 [[MUL_RESULT3]], -4 -; LV-NEXT: [[TMP15:%.*]] = sub i64 4, [[TMP14]] -; LV-NEXT: [[UGLYGEP6:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[TMP15]] -; LV-NEXT: [[TMP16:%.*]] = bitcast i8* [[UGLYGEP6]] to i16* -; LV-NEXT: [[TMP17:%.*]] = icmp ugt i16* [[TMP16]], [[SCEVGEP]] -; LV-NEXT: [[TMP18:%.*]] = icmp ult i16* [[TMP13]], [[SCEVGEP]] -; LV-NEXT: [[TMP19:%.*]] = select i1 true, i1 [[TMP17]], i1 [[TMP18]] -; LV-NEXT: [[TMP20:%.*]] = or i1 [[TMP19]], [[MUL_OVERFLOW4]] -; LV-NEXT: [[TMP21:%.*]] = or i1 [[TMP11]], [[TMP20]] -; LV-NEXT: br i1 [[TMP21]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH:%.*]] +; LV-NEXT: [[TMP13:%.*]] = sub i64 0, [[MUL_RESULT3]] +; LV-NEXT: [[TMP14:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[MUL_RESULT3]] +; LV-NEXT: [[TMP15:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[TMP13]] +; LV-NEXT: [[TMP16:%.*]] = icmp ugt i8* [[TMP15]], [[SCEVGEP5]] +; LV-NEXT: [[TMP17:%.*]] = icmp ult i8* [[TMP14]], [[SCEVGEP5]] +; LV-NEXT: [[TMP18:%.*]] = select i1 true, i1 [[TMP16]], i1 [[TMP17]] +; LV-NEXT: [[TMP19:%.*]] = or i1 [[TMP18]], [[MUL_OVERFLOW4]] +; LV-NEXT: [[TMP20:%.*]] = or i1 [[TMP11]], [[TMP19]] +; LV-NEXT: br i1 [[TMP20]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH:%.*]] ; LV: for.body.ph.lver.orig: ; LV-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]] ; LV: for.body.lver.orig: @@ -449,10 +437,10 @@ define void @f4(i16* noalias %a, ; LV-NEXT: [[INC]] = add nuw nsw i64 [[IND]], 1 ; LV-NEXT: [[DEC]] = sub i32 [[IND1]], 1 ; LV-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INC]], [[N]] -; LV-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT7:%.*]], label [[FOR_BODY]] +; LV-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT6:%.*]], label [[FOR_BODY]] ; LV: for.end.loopexit: ; LV-NEXT: br label [[FOR_END:%.*]] -; LV: for.end.loopexit7: +; LV: for.end.loopexit6: ; LV-NEXT: br label [[FOR_END]] ; LV: for.end: ; LV-NEXT: ret void @@ -521,18 +509,15 @@ define void @f5(i16* noalias %a, ; LV-NEXT: [[MUL_RESULT3:%.*]] = extractvalue { i64, i1 } [[MUL2]], 0 ; LV-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1 ; LV-NEXT: [[SCEVGEP5:%.*]] = bitcast i16* [[SCEVGEP]] to i8* -; LV-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[MUL_RESULT3]] -; LV-NEXT: [[TMP13:%.*]] = bitcast i8* [[UGLYGEP]] to i16* -; LV-NEXT: [[TMP14:%.*]] = sub i64 [[MUL_RESULT3]], -4 -; LV-NEXT: [[TMP15:%.*]] = sub i64 4, [[TMP14]] -; LV-NEXT: [[UGLYGEP6:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[TMP15]] -; LV-NEXT: [[TMP16:%.*]] = bitcast i8* [[UGLYGEP6]] to i16* -; LV-NEXT: [[TMP17:%.*]] = icmp ugt i16* [[TMP16]], [[SCEVGEP]] -; LV-NEXT: [[TMP18:%.*]] = icmp ult i16* [[TMP13]], [[SCEVGEP]] -; LV-NEXT: [[TMP19:%.*]] = select i1 true, i1 [[TMP17]], i1 [[TMP18]] -; LV-NEXT: [[TMP20:%.*]] = or i1 [[TMP19]], [[MUL_OVERFLOW4]] -; LV-NEXT: [[TMP21:%.*]] = or i1 [[TMP11]], [[TMP20]] -; LV-NEXT: br i1 [[TMP21]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH:%.*]] +; LV-NEXT: [[TMP13:%.*]] = sub i64 0, [[MUL_RESULT3]] +; LV-NEXT: [[TMP14:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[MUL_RESULT3]] +; LV-NEXT: [[TMP15:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[TMP13]] +; LV-NEXT: [[TMP16:%.*]] = icmp ugt i8* [[TMP15]], [[SCEVGEP5]] +; LV-NEXT: [[TMP17:%.*]] = icmp ult i8* [[TMP14]], [[SCEVGEP5]] +; LV-NEXT: [[TMP18:%.*]] = select i1 true, i1 [[TMP16]], i1 [[TMP17]] +; LV-NEXT: [[TMP19:%.*]] = or i1 [[TMP18]], [[MUL_OVERFLOW4]] +; LV-NEXT: [[TMP20:%.*]] = or i1 [[TMP11]], [[TMP19]] +; LV-NEXT: br i1 [[TMP20]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH:%.*]] ; LV: for.body.ph.lver.orig: ; LV-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]] ; LV: for.body.lver.orig: @@ -564,10 +549,10 @@ define void @f5(i16* noalias %a, ; LV-NEXT: [[INC]] = add nuw nsw i64 [[IND]], 1 ; LV-NEXT: [[DEC]] = sub i32 [[IND1]], 1 ; LV-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INC]], [[N]] -; LV-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT7:%.*]], label [[FOR_BODY]] +; LV-NEXT: br i1 [[EXITCOND]], label [[FOR_END_LOOPEXIT6:%.*]], label [[FOR_BODY]] ; LV: for.end.loopexit: ; LV-NEXT: br label [[FOR_END:%.*]] -; LV: for.end.loopexit7: +; LV: for.end.loopexit6: ; LV-NEXT: br label [[FOR_END]] ; LV: for.end: ; LV-NEXT: ret void