This is an archive of the discontinued LLVM Phabricator instance.

Differential D109093

[SCEVExpander] Simplify pointer overflow check
ClosedPublic

Authored by nikic on Sep 1 2021, 2:24 PM.

Details

Reviewers
reames
mkazantsev
Commits
rGc86e1ce73bb6: [SCEVExpander] Simplify pointer overflow check
Summary

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 umul argument rather then 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.

Diff Detail

Event Timeline

nikic created this revision.Sep 1 2021, 2:24 PM
Herald added subscribers: javed.absar, hiraditya. · View Herald TranscriptSep 1 2021, 2:24 PM
nikic requested review of this revision.Sep 1 2021, 2:24 PM
Herald added a project: Restricted Project. · View Herald TranscriptSep 1 2021, 2:24 PM
Herald added a subscriber: llvm-commits. · View Herald Transcript
Harbormaster completed remote builds in B122166: Diff 370056.Sep 1 2021, 2:25 PM
mkazantsev accepted this revision.Sep 1 2021, 9:56 PM

Looks fine!

This revision is now accepted and ready to land.Sep 1 2021, 9:56 PM
This revision was landed with ongoing or failed builds.Sep 2 2021, 11:16 AM
Closed by commit rGc86e1ce73bb6: [SCEVExpander] Simplify pointer overflow check (authored by nikic). · Explain Why
This revision was automatically updated to reflect the committed changes.
nikic added a commit: rGc86e1ce73bb6: [SCEVExpander] Simplify pointer overflow check.

Revision Contents

PathSize
llvm/
lib/
Transforms/
Utils/
11 lines
test/
Analysis/
LoopAccessAnalysis/
9 lines
Transforms/
LoopDistribute/
50 lines
LoopVersioning/
125 lines

Diff 370056

llvm/lib/Transforms/Utils/ScalarEvolutionExpander.cpp

Show First 20 Lines • Show All 2,484 Lines • ▼ Show 20 LinesValue *SCEVExpander::generateOverflowCheck(const SCEVAddRecExpr *AR,
Value *MulV = Builder.CreateExtractValue(Mul, 0, "mul.result"); Value *MulV = Builder.CreateExtractValue(Mul, 0, "mul.result");
Value *OfMul = Builder.CreateExtractValue(Mul, 1, "mul.overflow"); Value *OfMul = Builder.CreateExtractValue(Mul, 1, "mul.overflow");
// Compute: // Compute:
// Start + |Step| * Backedge < Start // Start + |Step| * Backedge < Start
// Start - |Step| * Backedge > Start // Start - |Step| * Backedge > Start
Value *Add = nullptr, *Sub = nullptr; Value *Add = nullptr, *Sub = nullptr;
if (PointerType *ARPtrTy = dyn_cast<PointerType>(ARTy)) { if (PointerType *ARPtrTy = dyn_cast<PointerType>(ARTy)) {
const SCEV *MulS = SE.getSCEV(MulV); StartValue = InsertNoopCastOfTo(
const SCEV *NegMulS = SE.getNegativeSCEV(MulS); StartValue, Builder.getInt8PtrTy(ARPtrTy->getAddressSpace()));
Add = Builder.CreateBitCast(expandAddToGEP(MulS, ARPtrTy, Ty, StartValue), Value *NegMulV = Builder.CreateNeg(MulV);
ARPtrTy); Add = Builder.CreateGEP(Builder.getInt8Ty(), StartValue, MulV);
Sub = Builder.CreateBitCast( Sub = Builder.CreateGEP(Builder.getInt8Ty(), StartValue, NegMulV);
expandAddToGEP(NegMulS, ARPtrTy, Ty, StartValue), ARPtrTy);
} else { } else {
Add = Builder.CreateAdd(StartValue, MulV); Add = Builder.CreateAdd(StartValue, MulV);
Sub = Builder.CreateSub(StartValue, MulV); Sub = Builder.CreateSub(StartValue, MulV);
} }
Value *EndCompareGT = Builder.CreateICmp( Value *EndCompareGT = Builder.CreateICmp(
Signed ? ICmpInst::ICMP_SGT : ICmpInst::ICMP_UGT, Sub, StartValue); Signed ? ICmpInst::ICMP_SGT : ICmpInst::ICMP_UGT, Sub, StartValue);
▲ Show 20 Lines • Show All 205 Lines • Show Last 20 Lines

llvm/test/Analysis/LoopAccessAnalysis/wrapping-pointer-ni.ll

Show All 11 Lines
declare i64 @julia_steprange_last_4949() declare i64 @julia_steprange_last_4949()
define void @"japi1_align!_9477"(%jl_value_t addrspace(10)** %arg) { define void @"japi1_align!_9477"(%jl_value_t addrspace(10)** %arg) {
; LV-LAVEL: L26.lver.check ; LV-LAVEL: L26.lver.check
; LV: [[OFMul:%[^ ]*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 4, i64 [[Step:%[^ ]*]]) ; LV: [[OFMul:%[^ ]*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 4, i64 [[Step:%[^ ]*]])
; LV-NEXT: [[OFMulResult:%[^ ]*]] = extractvalue { i64, i1 } [[OFMul]], 0 ; LV-NEXT: [[OFMulResult:%[^ ]*]] = extractvalue { i64, i1 } [[OFMul]], 0
; LV-NEXT: [[OFMulOverflow:%[^ ]*]] = extractvalue { i64, i1 } [[OFMul]], 1 ; LV-NEXT: [[OFMulOverflow:%[^ ]*]] = extractvalue { i64, i1 } [[OFMul]], 1
; LV-NEXT: [[PosGEP:%[^ ]*]] = getelementptr i32, i32 addrspace(13)* [[Base:%[^ ]*]], i64 [[Step]] ; LV: [[OFNegMulResult:%[^ ]*]] = sub i64 0, [[OFMulResult]]
; LV-NEXT: [[NegGEP:%[^ ]*]] = getelementptr i32, i32 addrspace(13)* [[Base]], i64 [[NegStep:%[^ ]*]] ; LV-NEXT: [[PosGEP:%[^ ]*]] = getelementptr i8, i8 addrspace(13)* [[Base:%[^ ]*]], i64 [[OFMulResult]]
; LV-NEXT: icmp ugt i32 addrspace(13)* [[NegGEP]], [[Base]] ; LV-NEXT: [[NegGEP:%[^ ]*]] = getelementptr i8, i8 addrspace(13)* [[Base]], i64 [[OFNegMulResult]]
; LV-NEXT: icmp ult i32 addrspace(13)* [[PosGEP]], [[Base]] ; LV-NEXT: icmp ugt i8 addrspace(13)* [[NegGEP]], [[Base]]
; LV-NEXT: icmp ult i8 addrspace(13)* [[PosGEP]], [[Base]]
; LV-NOT: inttoptr ; LV-NOT: inttoptr
; LV-NOT: ptrtoint ; LV-NOT: ptrtoint
top: top:
%tmp = load %jl_value_t addrspace(10)*, %jl_value_t addrspace(10)** %arg, align 8 %tmp = load %jl_value_t addrspace(10)*, %jl_value_t addrspace(10)** %arg, align 8
%tmp1 = load i32, i32* inttoptr (i64 12 to i32*), align 4 %tmp1 = load i32, i32* inttoptr (i64 12 to i32*), align 4
%tmp2 = sub i32 0, %tmp1 %tmp2 = sub i32 0, %tmp1
%tmp3 = call i64 @julia_steprange_last_4949() %tmp3 = call i64 @julia_steprange_last_4949()
%tmp4 = addrspacecast %jl_value_t addrspace(10)* %tmp to %jl_value_t addrspace(11)* %tmp4 = addrspacecast %jl_value_t addrspace(10)* %tmp to %jl_value_t addrspace(11)*
Show All 23 Lines

llvm/test/Transforms/LoopDistribute/scev-inserted-runtime-check.ll

Show All 23 Lines
; CHECK-NEXT: [[TMP6:%.*]] = select i1 false, i1 [[TMP4]], i1 [[TMP5]] ; CHECK-NEXT: [[TMP6:%.*]] = select i1 false, i1 [[TMP4]], i1 [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = icmp ugt i64 [[TMP0]], 4294967295 ; CHECK-NEXT: [[TMP7:%.*]] = icmp ugt i64 [[TMP0]], 4294967295
; CHECK-NEXT: [[TMP8:%.*]] = or i1 [[TMP6]], [[TMP7]] ; CHECK-NEXT: [[TMP8:%.*]] = or i1 [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP9:%.*]] = or i1 [[TMP8]], [[MUL_OVERFLOW]] ; CHECK-NEXT: [[TMP9:%.*]] = or i1 [[TMP8]], [[MUL_OVERFLOW]]
; CHECK-NEXT: [[TMP10:%.*]] = or i1 false, [[TMP9]] ; CHECK-NEXT: [[TMP10:%.*]] = or i1 false, [[TMP9]]
; CHECK-NEXT: [[MUL2:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 8, i64 [[TMP0]]) ; 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_RESULT3:%.*]] = extractvalue { i64, i1 } [[MUL2]], 0
; CHECK-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1 ; CHECK-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1
; CHECK-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, i8* [[A5]], i64 [[MUL_RESULT3]] ; CHECK-NEXT: [[TMP11:%.*]] = sub i64 0, [[MUL_RESULT3]]
; CHECK-NEXT: [[TMP11:%.*]] = bitcast i8* [[UGLYGEP]] to i32* ; CHECK-NEXT: [[TMP12:%.*]] = getelementptr i8, i8* [[A5]], i64 [[MUL_RESULT3]]
; CHECK-NEXT: [[TMP12:%.*]] = sub i64 [[MUL_RESULT3]], -8 ; CHECK-NEXT: [[TMP13:%.*]] = getelementptr i8, i8* [[A5]], i64 [[TMP11]]
; CHECK-NEXT: [[TMP13:%.*]] = sub i64 8, [[TMP12]] ; CHECK-NEXT: [[TMP14:%.*]] = icmp ugt i8* [[TMP13]], [[A5]]
; CHECK-NEXT: [[UGLYGEP6:%.*]] = getelementptr i8, i8* [[A5]], i64 [[TMP13]] ; CHECK-NEXT: [[TMP15:%.*]] = icmp ult i8* [[TMP12]], [[A5]]
; CHECK-NEXT: [[TMP14:%.*]] = bitcast i8* [[UGLYGEP6]] to i32* ; CHECK-NEXT: [[TMP16:%.*]] = select i1 false, i1 [[TMP14]], i1 [[TMP15]]
; CHECK-NEXT: [[TMP15:%.*]] = icmp ugt i32* [[TMP14]], [[A]] ; CHECK-NEXT: [[TMP17:%.*]] = or i1 [[TMP16]], [[MUL_OVERFLOW4]]
; CHECK-NEXT: [[TMP16:%.*]] = icmp ult i32* [[TMP11]], [[A]] ; CHECK-NEXT: [[TMP18:%.*]] = or i1 [[TMP10]], [[TMP17]]
; CHECK-NEXT: [[TMP17:%.*]] = select i1 false, i1 [[TMP15]], i1 [[TMP16]] ; CHECK-NEXT: br i1 [[TMP18]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH_LDIST1:%.*]]
; 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: for.body.ph.lver.orig: ; CHECK: for.body.ph.lver.orig:
; CHECK-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]] ; CHECK-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]]
; CHECK: for.body.lver.orig: ; CHECK: for.body.lver.orig:
; CHECK-NEXT: [[IND_LVER_ORIG:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[ADD_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ] ; CHECK-NEXT: [[IND_LVER_ORIG:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[ADD_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; CHECK-NEXT: [[IND1_LVER_ORIG:%.*]] = phi i32 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC1_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ] ; CHECK-NEXT: [[IND1_LVER_ORIG:%.*]] = phi i32 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC1_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; CHECK-NEXT: [[MUL_LVER_ORIG:%.*]] = mul i32 [[IND1_LVER_ORIG]], 2 ; CHECK-NEXT: [[MUL_LVER_ORIG:%.*]] = mul i32 [[IND1_LVER_ORIG]], 2
; CHECK-NEXT: [[MUL_EXT_LVER_ORIG:%.*]] = zext i32 [[MUL_LVER_ORIG]] to i64 ; CHECK-NEXT: [[MUL_EXT_LVER_ORIG:%.*]] = zext i32 [[MUL_LVER_ORIG]] to i64
; CHECK-NEXT: [[ARRAYIDXA_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[MUL_EXT_LVER_ORIG]] ; CHECK-NEXT: [[ARRAYIDXA_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[MUL_EXT_LVER_ORIG]]
▲ Show 20 Lines • Show All 44 Lines • ▼ Show 20 Lines
; CHECK-NEXT: [[ARRAYIDXD:%.*]] = getelementptr inbounds i32, i32* [[D]], i64 [[MUL_EXT]] ; CHECK-NEXT: [[ARRAYIDXD:%.*]] = getelementptr inbounds i32, i32* [[D]], i64 [[MUL_EXT]]
; CHECK-NEXT: [[LOADD:%.*]] = load i32, i32* [[ARRAYIDXD]], align 4 ; CHECK-NEXT: [[LOADD:%.*]] = load i32, i32* [[ARRAYIDXD]], align 4
; CHECK-NEXT: [[ARRAYIDXE:%.*]] = getelementptr inbounds i32, i32* [[E]], i64 [[MUL_EXT]] ; CHECK-NEXT: [[ARRAYIDXE:%.*]] = getelementptr inbounds i32, i32* [[E]], i64 [[MUL_EXT]]
; CHECK-NEXT: [[LOADE:%.*]] = load i32, i32* [[ARRAYIDXE]], align 4 ; CHECK-NEXT: [[LOADE:%.*]] = load i32, i32* [[ARRAYIDXE]], align 4
; CHECK-NEXT: [[MULC:%.*]] = mul i32 [[LOADD]], [[LOADE]] ; CHECK-NEXT: [[MULC:%.*]] = mul i32 [[LOADD]], [[LOADE]]
; CHECK-NEXT: [[ARRAYIDXC:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 [[MUL_EXT]] ; CHECK-NEXT: [[ARRAYIDXC:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 [[MUL_EXT]]
; CHECK-NEXT: store i32 [[MULC]], i32* [[ARRAYIDXC]], align 4 ; CHECK-NEXT: store i32 [[MULC]], i32* [[ARRAYIDXC]], align 4
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[ADD]], [[N]] ; 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: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END:%.*]] ; CHECK-NEXT: br label [[FOR_END:%.*]]
; CHECK: for.end.loopexit7: ; CHECK: for.end.loopexit6:
; CHECK-NEXT: br label [[FOR_END]] ; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end: ; CHECK: for.end:
; CHECK-NEXT: ret void ; CHECK-NEXT: ret void
; ;
entry: entry:
br label %for.body br label %for.body
for.body: ; preds = %for.body, %entry for.body: ; preds = %for.body, %entry
▲ Show 20 Lines • Show All 60 Lines • ▼ Show 20 Lines
; CHECK-NEXT: [[TMP6:%.*]] = select i1 false, i1 [[TMP4]], i1 [[TMP5]] ; CHECK-NEXT: [[TMP6:%.*]] = select i1 false, i1 [[TMP4]], i1 [[TMP5]]
; CHECK-NEXT: [[TMP7:%.*]] = icmp ugt i64 [[TMP0]], 4294967295 ; CHECK-NEXT: [[TMP7:%.*]] = icmp ugt i64 [[TMP0]], 4294967295
; CHECK-NEXT: [[TMP8:%.*]] = or i1 [[TMP6]], [[TMP7]] ; CHECK-NEXT: [[TMP8:%.*]] = or i1 [[TMP6]], [[TMP7]]
; CHECK-NEXT: [[TMP9:%.*]] = or i1 [[TMP8]], [[MUL_OVERFLOW]] ; CHECK-NEXT: [[TMP9:%.*]] = or i1 [[TMP8]], [[MUL_OVERFLOW]]
; CHECK-NEXT: [[TMP10:%.*]] = or i1 false, [[TMP9]] ; CHECK-NEXT: [[TMP10:%.*]] = or i1 false, [[TMP9]]
; CHECK-NEXT: [[MUL2:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 8, i64 [[TMP0]]) ; 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_RESULT3:%.*]] = extractvalue { i64, i1 } [[MUL2]], 0
; CHECK-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1 ; 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:%.*]] = sub i64 0, [[MUL_RESULT3]]
; CHECK-NEXT: [[TMP11:%.*]] = bitcast i8* [[UGLYGEP]] to [8192 x i32]* ; 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: [[TMP12:%.*]] = sub i64 [[MUL_RESULT3]], -8 ; 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: [[TMP13:%.*]] = sub i64 8, [[TMP12]] ; 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: [[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: [[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: [[TMP14:%.*]] = bitcast i8* [[UGLYGEP5]] to [8192 x i32]* ; CHECK-NEXT: [[TMP16:%.*]] = select i1 false, i1 [[TMP14]], i1 [[TMP15]]
; 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: [[TMP17:%.*]] = or i1 [[TMP16]], [[MUL_OVERFLOW4]]
; 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: [[TMP18:%.*]] = or i1 [[TMP10]], [[TMP17]]
; CHECK-NEXT: [[TMP17:%.*]] = select i1 false, i1 [[TMP15]], i1 [[TMP16]] ; CHECK-NEXT: br i1 [[TMP18]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH_LDIST1:%.*]]
; 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: for.body.ph.lver.orig: ; CHECK: for.body.ph.lver.orig:
; CHECK-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]] ; CHECK-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]]
; CHECK: for.body.lver.orig: ; CHECK: for.body.lver.orig:
; CHECK-NEXT: [[IND_LVER_ORIG:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[ADD_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ] ; CHECK-NEXT: [[IND_LVER_ORIG:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[ADD_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; CHECK-NEXT: [[IND1_LVER_ORIG:%.*]] = phi i32 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC1_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ] ; CHECK-NEXT: [[IND1_LVER_ORIG:%.*]] = phi i32 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC1_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; CHECK-NEXT: [[MUL_LVER_ORIG:%.*]] = mul i32 [[IND1_LVER_ORIG]], 2 ; CHECK-NEXT: [[MUL_LVER_ORIG:%.*]] = mul i32 [[IND1_LVER_ORIG]], 2
; CHECK-NEXT: [[MUL_EXT_LVER_ORIG:%.*]] = zext i32 [[MUL_LVER_ORIG]] to i64 ; CHECK-NEXT: [[MUL_EXT_LVER_ORIG:%.*]] = zext i32 [[MUL_LVER_ORIG]] to i64
; CHECK-NEXT: [[ARRAYIDXA_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[MUL_EXT_LVER_ORIG]] ; CHECK-NEXT: [[ARRAYIDXA_LVER_ORIG:%.*]] = getelementptr inbounds i32, i32* [[A]], i64 [[MUL_EXT_LVER_ORIG]]
▲ Show 20 Lines • Show All 44 Lines • ▼ Show 20 Lines
; CHECK-NEXT: [[ARRAYIDXD:%.*]] = getelementptr inbounds i32, i32* [[D]], i64 [[MUL_EXT]] ; CHECK-NEXT: [[ARRAYIDXD:%.*]] = getelementptr inbounds i32, i32* [[D]], i64 [[MUL_EXT]]
; CHECK-NEXT: [[LOADD:%.*]] = load i32, i32* [[ARRAYIDXD]], align 4 ; CHECK-NEXT: [[LOADD:%.*]] = load i32, i32* [[ARRAYIDXD]], align 4
; CHECK-NEXT: [[ARRAYIDXE:%.*]] = getelementptr inbounds i32, i32* [[E]], i64 [[MUL_EXT]] ; CHECK-NEXT: [[ARRAYIDXE:%.*]] = getelementptr inbounds i32, i32* [[E]], i64 [[MUL_EXT]]
; CHECK-NEXT: [[LOADE:%.*]] = load i32, i32* [[ARRAYIDXE]], align 4 ; CHECK-NEXT: [[LOADE:%.*]] = load i32, i32* [[ARRAYIDXE]], align 4
; CHECK-NEXT: [[MULC:%.*]] = mul i32 [[LOADD]], [[LOADE]] ; CHECK-NEXT: [[MULC:%.*]] = mul i32 [[LOADD]], [[LOADE]]
; CHECK-NEXT: [[ARRAYIDXC:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 [[MUL_EXT]] ; CHECK-NEXT: [[ARRAYIDXC:%.*]] = getelementptr inbounds i32, i32* [[C]], i64 [[MUL_EXT]]
; CHECK-NEXT: store i32 [[MULC]], i32* [[ARRAYIDXC]], align 4 ; CHECK-NEXT: store i32 [[MULC]], i32* [[ARRAYIDXC]], align 4
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[ADD]], [[N]] ; 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: for.end.loopexit:
; CHECK-NEXT: br label [[FOR_END:%.*]] ; CHECK-NEXT: br label [[FOR_END:%.*]]
; CHECK: for.end.loopexit6: ; CHECK: for.end.loopexit5:
; CHECK-NEXT: br label [[FOR_END]] ; CHECK-NEXT: br label [[FOR_END]]
; CHECK: for.end: ; CHECK: for.end:
; CHECK-NEXT: ret void ; CHECK-NEXT: ret void
; ;
entry: entry:
%a_base = getelementptr [8192 x i32], [8192 x i32]* @global_a, i32 0, i32 0 %a_base = getelementptr [8192 x i32], [8192 x i32]* @global_a, i32 0, i32 0
%a_intptr = ptrtoint i32* %a_base to i64 %a_intptr = ptrtoint i32* %a_base to i64
call void @use64(i64 %a_intptr) call void @use64(i64 %a_intptr)
▲ Show 20 Lines • Show All 123 Lines • Show Last 20 Lines

llvm/test/Transforms/LoopVersioning/wrapping-pointer-versioning.ll

Show All 40 Lines
; LV-NEXT: [[TMP6:%.*]] = select i1 false, i1 [[TMP4]], i1 [[TMP5]] ; LV-NEXT: [[TMP6:%.*]] = select i1 false, i1 [[TMP4]], i1 [[TMP5]]
; LV-NEXT: [[TMP7:%.*]] = icmp ugt i64 [[TMP0]], 4294967295 ; LV-NEXT: [[TMP7:%.*]] = icmp ugt i64 [[TMP0]], 4294967295
; LV-NEXT: [[TMP8:%.*]] = or i1 [[TMP6]], [[TMP7]] ; LV-NEXT: [[TMP8:%.*]] = or i1 [[TMP6]], [[TMP7]]
; LV-NEXT: [[TMP9:%.*]] = or i1 [[TMP8]], [[MUL_OVERFLOW]] ; LV-NEXT: [[TMP9:%.*]] = or i1 [[TMP8]], [[MUL_OVERFLOW]]
; LV-NEXT: [[TMP10:%.*]] = or i1 false, [[TMP9]] ; LV-NEXT: [[TMP10:%.*]] = or i1 false, [[TMP9]]
; LV-NEXT: [[MUL2:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 4, i64 [[TMP0]]) ; 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_RESULT3:%.*]] = extractvalue { i64, i1 } [[MUL2]], 0
; LV-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1 ; LV-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1
; LV-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, i8* [[A5]], i64 [[MUL_RESULT3]] ; LV-NEXT: [[TMP11:%.*]] = sub i64 0, [[MUL_RESULT3]]
; LV-NEXT: [[TMP11:%.*]] = bitcast i8* [[UGLYGEP]] to i16* ; LV-NEXT: [[TMP12:%.*]] = getelementptr i8, i8* [[A5]], i64 [[MUL_RESULT3]]
; LV-NEXT: [[TMP12:%.*]] = sub i64 [[MUL_RESULT3]], -4 ; LV-NEXT: [[TMP13:%.*]] = getelementptr i8, i8* [[A5]], i64 [[TMP11]]
; LV-NEXT: [[TMP13:%.*]] = sub i64 4, [[TMP12]] ; LV-NEXT: [[TMP14:%.*]] = icmp ugt i8* [[TMP13]], [[A5]]
; LV-NEXT: [[UGLYGEP6:%.*]] = getelementptr i8, i8* [[A5]], i64 [[TMP13]] ; LV-NEXT: [[TMP15:%.*]] = icmp ult i8* [[TMP12]], [[A5]]
; LV-NEXT: [[TMP14:%.*]] = bitcast i8* [[UGLYGEP6]] to i16* ; LV-NEXT: [[TMP16:%.*]] = select i1 false, i1 [[TMP14]], i1 [[TMP15]]
; LV-NEXT: [[TMP15:%.*]] = icmp ugt i16* [[TMP14]], [[A]] ; LV-NEXT: [[TMP17:%.*]] = or i1 [[TMP16]], [[MUL_OVERFLOW4]]
; LV-NEXT: [[TMP16:%.*]] = icmp ult i16* [[TMP11]], [[A]] ; LV-NEXT: [[TMP18:%.*]] = or i1 [[TMP10]], [[TMP17]]
; LV-NEXT: [[TMP17:%.*]] = select i1 false, i1 [[TMP15]], i1 [[TMP16]] ; LV-NEXT: br i1 [[TMP18]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH:%.*]]
; 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: for.body.ph.lver.orig: ; LV: for.body.ph.lver.orig:
; LV-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]] ; LV-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]]
; LV: for.body.lver.orig: ; LV: for.body.lver.orig:
; LV-NEXT: [[IND_LVER_ORIG:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ] ; LV-NEXT: [[IND_LVER_ORIG:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; LV-NEXT: [[IND1_LVER_ORIG:%.*]] = phi i32 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC1_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ] ; LV-NEXT: [[IND1_LVER_ORIG:%.*]] = phi i32 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC1_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; LV-NEXT: [[MUL_LVER_ORIG:%.*]] = mul i32 [[IND1_LVER_ORIG]], 2 ; LV-NEXT: [[MUL_LVER_ORIG:%.*]] = mul i32 [[IND1_LVER_ORIG]], 2
; LV-NEXT: [[MUL_EXT_LVER_ORIG:%.*]] = zext i32 [[MUL_LVER_ORIG]] to i64 ; LV-NEXT: [[MUL_EXT_LVER_ORIG:%.*]] = zext i32 [[MUL_LVER_ORIG]] to i64
; LV-NEXT: [[ARRAYIDXA_LVER_ORIG:%.*]] = getelementptr i16, i16* [[A]], i64 [[MUL_EXT_LVER_ORIG]] ; LV-NEXT: [[ARRAYIDXA_LVER_ORIG:%.*]] = getelementptr i16, i16* [[A]], i64 [[MUL_EXT_LVER_ORIG]]
Show All 17 Lines
; LV-NEXT: [[LOADA:%.*]] = load i16, i16* [[ARRAYIDXA]], align 2 ; LV-NEXT: [[LOADA:%.*]] = load i16, i16* [[ARRAYIDXA]], align 2
; LV-NEXT: [[ARRAYIDXB:%.*]] = getelementptr i16, i16* [[B]], i64 [[IND]] ; LV-NEXT: [[ARRAYIDXB:%.*]] = getelementptr i16, i16* [[B]], i64 [[IND]]
; LV-NEXT: [[LOADB:%.*]] = load i16, i16* [[ARRAYIDXB]], align 2 ; LV-NEXT: [[LOADB:%.*]] = load i16, i16* [[ARRAYIDXB]], align 2
; LV-NEXT: [[ADD:%.*]] = mul i16 [[LOADA]], [[LOADB]] ; LV-NEXT: [[ADD:%.*]] = mul i16 [[LOADA]], [[LOADB]]
; LV-NEXT: store i16 [[ADD]], i16* [[ARRAYIDXA]], align 2 ; LV-NEXT: store i16 [[ADD]], i16* [[ARRAYIDXA]], align 2
; LV-NEXT: [[INC]] = add nuw nsw i64 [[IND]], 1 ; LV-NEXT: [[INC]] = add nuw nsw i64 [[IND]], 1
; LV-NEXT: [[INC1]] = add i32 [[IND1]], 1 ; LV-NEXT: [[INC1]] = add i32 [[IND1]], 1
; LV-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INC]], [[N]] ; 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: for.end.loopexit:
; LV-NEXT: br label [[FOR_END:%.*]] ; LV-NEXT: br label [[FOR_END:%.*]]
; LV: for.end.loopexit7: ; LV: for.end.loopexit6:
; LV-NEXT: br label [[FOR_END]] ; LV-NEXT: br label [[FOR_END]]
; LV: for.end: ; LV: for.end:
; LV-NEXT: ret void ; LV-NEXT: ret void
; ;
i16* noalias %b, i64 %N) { i16* noalias %b, i64 %N) {
entry: entry:
br label %for.body br label %for.body
▲ Show 20 Lines • Show All 70 Lines • ▼ Show 20 Lines
; LV-NEXT: [[TMP12:%.*]] = trunc i64 [[N]] to i31 ; LV-NEXT: [[TMP12:%.*]] = trunc i64 [[N]] to i31
; LV-NEXT: [[TMP13:%.*]] = zext i31 [[TMP12]] to i64 ; LV-NEXT: [[TMP13:%.*]] = zext i31 [[TMP12]] to i64
; LV-NEXT: [[TMP14:%.*]] = shl nuw nsw i64 [[TMP13]], 1 ; LV-NEXT: [[TMP14:%.*]] = shl nuw nsw i64 [[TMP13]], 1
; LV-NEXT: [[SCEVGEP:%.*]] = getelementptr i16, i16* [[A:%.*]], i64 [[TMP14]] ; LV-NEXT: [[SCEVGEP:%.*]] = getelementptr i16, i16* [[A:%.*]], i64 [[TMP14]]
; LV-NEXT: [[MUL2:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 4, i64 [[TMP0]]) ; 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_RESULT3:%.*]] = extractvalue { i64, i1 } [[MUL2]], 0
; LV-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1 ; LV-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1
; LV-NEXT: [[SCEVGEP5:%.*]] = bitcast i16* [[SCEVGEP]] to i8* ; LV-NEXT: [[SCEVGEP5:%.*]] = bitcast i16* [[SCEVGEP]] to i8*
; LV-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[MUL_RESULT3]] ; LV-NEXT: [[TMP15:%.*]] = sub i64 0, [[MUL_RESULT3]]
; LV-NEXT: [[TMP15:%.*]] = bitcast i8* [[UGLYGEP]] to i16* ; LV-NEXT: [[TMP16:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[MUL_RESULT3]]
; LV-NEXT: [[TMP16:%.*]] = sub i64 [[MUL_RESULT3]], -4 ; LV-NEXT: [[TMP17:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[TMP15]]
; LV-NEXT: [[TMP17:%.*]] = sub i64 4, [[TMP16]] ; LV-NEXT: [[TMP18:%.*]] = icmp ugt i8* [[TMP17]], [[SCEVGEP5]]
; LV-NEXT: [[UGLYGEP6:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[TMP17]] ; LV-NEXT: [[TMP19:%.*]] = icmp ult i8* [[TMP16]], [[SCEVGEP5]]
; LV-NEXT: [[TMP18:%.*]] = bitcast i8* [[UGLYGEP6]] to i16* ; LV-NEXT: [[TMP20:%.*]] = select i1 true, i1 [[TMP18]], i1 [[TMP19]]
; LV-NEXT: [[TMP19:%.*]] = icmp ugt i16* [[TMP18]], [[SCEVGEP]] ; LV-NEXT: [[TMP21:%.*]] = or i1 [[TMP20]], [[MUL_OVERFLOW4]]
; LV-NEXT: [[TMP20:%.*]] = icmp ult i16* [[TMP15]], [[SCEVGEP]] ; LV-NEXT: [[TMP22:%.*]] = or i1 [[TMP11]], [[TMP21]]
; LV-NEXT: [[TMP21:%.*]] = select i1 true, i1 [[TMP19]], i1 [[TMP20]] ; LV-NEXT: br i1 [[TMP22]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH:%.*]]
; 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: for.body.ph.lver.orig: ; LV: for.body.ph.lver.orig:
; LV-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]] ; LV-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]]
; LV: for.body.lver.orig: ; LV: for.body.lver.orig:
; LV-NEXT: [[IND_LVER_ORIG:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ] ; LV-NEXT: [[IND_LVER_ORIG:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; LV-NEXT: [[IND1_LVER_ORIG:%.*]] = phi i32 [ [[TRUNCN]], [[FOR_BODY_PH_LVER_ORIG]] ], [ [[DEC_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ] ; LV-NEXT: [[IND1_LVER_ORIG:%.*]] = phi i32 [ [[TRUNCN]], [[FOR_BODY_PH_LVER_ORIG]] ], [ [[DEC_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; LV-NEXT: [[MUL_LVER_ORIG:%.*]] = mul i32 [[IND1_LVER_ORIG]], 2 ; LV-NEXT: [[MUL_LVER_ORIG:%.*]] = mul i32 [[IND1_LVER_ORIG]], 2
; LV-NEXT: [[MUL_EXT_LVER_ORIG:%.*]] = zext i32 [[MUL_LVER_ORIG]] to i64 ; LV-NEXT: [[MUL_EXT_LVER_ORIG:%.*]] = zext i32 [[MUL_LVER_ORIG]] to i64
; LV-NEXT: [[ARRAYIDXA_LVER_ORIG:%.*]] = getelementptr i16, i16* [[A]], i64 [[MUL_EXT_LVER_ORIG]] ; LV-NEXT: [[ARRAYIDXA_LVER_ORIG:%.*]] = getelementptr i16, i16* [[A]], i64 [[MUL_EXT_LVER_ORIG]]
Show All 17 Lines
; LV-NEXT: [[LOADA:%.*]] = load i16, i16* [[ARRAYIDXA]], align 2 ; LV-NEXT: [[LOADA:%.*]] = load i16, i16* [[ARRAYIDXA]], align 2
; LV-NEXT: [[ARRAYIDXB:%.*]] = getelementptr i16, i16* [[B]], i64 [[IND]] ; LV-NEXT: [[ARRAYIDXB:%.*]] = getelementptr i16, i16* [[B]], i64 [[IND]]
; LV-NEXT: [[LOADB:%.*]] = load i16, i16* [[ARRAYIDXB]], align 2 ; LV-NEXT: [[LOADB:%.*]] = load i16, i16* [[ARRAYIDXB]], align 2
; LV-NEXT: [[ADD:%.*]] = mul i16 [[LOADA]], [[LOADB]] ; LV-NEXT: [[ADD:%.*]] = mul i16 [[LOADA]], [[LOADB]]
; LV-NEXT: store i16 [[ADD]], i16* [[ARRAYIDXA]], align 2 ; LV-NEXT: store i16 [[ADD]], i16* [[ARRAYIDXA]], align 2
; LV-NEXT: [[INC]] = add nuw nsw i64 [[IND]], 1 ; LV-NEXT: [[INC]] = add nuw nsw i64 [[IND]], 1
; LV-NEXT: [[DEC]] = sub i32 [[IND1]], 1 ; LV-NEXT: [[DEC]] = sub i32 [[IND1]], 1
; LV-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INC]], [[N]] ; 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: for.end.loopexit:
; LV-NEXT: br label [[FOR_END:%.*]] ; LV-NEXT: br label [[FOR_END:%.*]]
; LV: for.end.loopexit7: ; LV: for.end.loopexit6:
; LV-NEXT: br label [[FOR_END]] ; LV-NEXT: br label [[FOR_END]]
; LV: for.end: ; LV: for.end:
; LV-NEXT: ret void ; LV-NEXT: ret void
; ;
i16* noalias %b, i64 %N) { i16* noalias %b, i64 %N) {
entry: entry:
%TruncN = trunc i64 %N to i32 %TruncN = trunc i64 %N to i32
br label %for.body br label %for.body
▲ Show 20 Lines • Show All 49 Lines • ▼ Show 20 Lines
; LV-NEXT: [[TMP6:%.*]] = select i1 false, i1 [[TMP4]], i1 [[TMP5]] ; LV-NEXT: [[TMP6:%.*]] = select i1 false, i1 [[TMP4]], i1 [[TMP5]]
; LV-NEXT: [[TMP7:%.*]] = icmp ugt i64 [[TMP0]], 4294967295 ; LV-NEXT: [[TMP7:%.*]] = icmp ugt i64 [[TMP0]], 4294967295
; LV-NEXT: [[TMP8:%.*]] = or i1 [[TMP6]], [[TMP7]] ; LV-NEXT: [[TMP8:%.*]] = or i1 [[TMP6]], [[TMP7]]
; LV-NEXT: [[TMP9:%.*]] = or i1 [[TMP8]], [[MUL_OVERFLOW]] ; LV-NEXT: [[TMP9:%.*]] = or i1 [[TMP8]], [[MUL_OVERFLOW]]
; LV-NEXT: [[TMP10:%.*]] = or i1 false, [[TMP9]] ; LV-NEXT: [[TMP10:%.*]] = or i1 false, [[TMP9]]
; LV-NEXT: [[MUL2:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 4, i64 [[TMP0]]) ; 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_RESULT3:%.*]] = extractvalue { i64, i1 } [[MUL2]], 0
; LV-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1 ; LV-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1
; LV-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, i8* [[A5]], i64 [[MUL_RESULT3]] ; LV-NEXT: [[TMP11:%.*]] = sub i64 0, [[MUL_RESULT3]]
; LV-NEXT: [[TMP11:%.*]] = bitcast i8* [[UGLYGEP]] to i16* ; LV-NEXT: [[TMP12:%.*]] = getelementptr i8, i8* [[A5]], i64 [[MUL_RESULT3]]
; LV-NEXT: [[TMP12:%.*]] = sub i64 [[MUL_RESULT3]], -4 ; LV-NEXT: [[TMP13:%.*]] = getelementptr i8, i8* [[A5]], i64 [[TMP11]]
; LV-NEXT: [[TMP13:%.*]] = sub i64 4, [[TMP12]] ; LV-NEXT: [[TMP14:%.*]] = icmp ugt i8* [[TMP13]], [[A5]]
; LV-NEXT: [[UGLYGEP6:%.*]] = getelementptr i8, i8* [[A5]], i64 [[TMP13]] ; LV-NEXT: [[TMP15:%.*]] = icmp ult i8* [[TMP12]], [[A5]]
; LV-NEXT: [[TMP14:%.*]] = bitcast i8* [[UGLYGEP6]] to i16* ; LV-NEXT: [[TMP16:%.*]] = select i1 false, i1 [[TMP14]], i1 [[TMP15]]
; LV-NEXT: [[TMP15:%.*]] = icmp ugt i16* [[TMP14]], [[A]] ; LV-NEXT: [[TMP17:%.*]] = or i1 [[TMP16]], [[MUL_OVERFLOW4]]
; LV-NEXT: [[TMP16:%.*]] = icmp ult i16* [[TMP11]], [[A]] ; LV-NEXT: [[TMP18:%.*]] = or i1 [[TMP10]], [[TMP17]]
; LV-NEXT: [[TMP17:%.*]] = select i1 false, i1 [[TMP15]], i1 [[TMP16]] ; LV-NEXT: br i1 [[TMP18]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH:%.*]]
; 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: for.body.ph.lver.orig: ; LV: for.body.ph.lver.orig:
; LV-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]] ; LV-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]]
; LV: for.body.lver.orig: ; LV: for.body.lver.orig:
; LV-NEXT: [[IND_LVER_ORIG:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ] ; LV-NEXT: [[IND_LVER_ORIG:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; LV-NEXT: [[IND1_LVER_ORIG:%.*]] = phi i32 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC1_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ] ; LV-NEXT: [[IND1_LVER_ORIG:%.*]] = phi i32 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC1_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; LV-NEXT: [[MUL_LVER_ORIG:%.*]] = mul i32 [[IND1_LVER_ORIG]], 2 ; LV-NEXT: [[MUL_LVER_ORIG:%.*]] = mul i32 [[IND1_LVER_ORIG]], 2
; LV-NEXT: [[MUL_EXT_LVER_ORIG:%.*]] = sext i32 [[MUL_LVER_ORIG]] to i64 ; LV-NEXT: [[MUL_EXT_LVER_ORIG:%.*]] = sext i32 [[MUL_LVER_ORIG]] to i64
; LV-NEXT: [[ARRAYIDXA_LVER_ORIG:%.*]] = getelementptr i16, i16* [[A]], i64 [[MUL_EXT_LVER_ORIG]] ; LV-NEXT: [[ARRAYIDXA_LVER_ORIG:%.*]] = getelementptr i16, i16* [[A]], i64 [[MUL_EXT_LVER_ORIG]]
Show All 17 Lines
; LV-NEXT: [[LOADA:%.*]] = load i16, i16* [[ARRAYIDXA]], align 2 ; LV-NEXT: [[LOADA:%.*]] = load i16, i16* [[ARRAYIDXA]], align 2
; LV-NEXT: [[ARRAYIDXB:%.*]] = getelementptr i16, i16* [[B]], i64 [[IND]] ; LV-NEXT: [[ARRAYIDXB:%.*]] = getelementptr i16, i16* [[B]], i64 [[IND]]
; LV-NEXT: [[LOADB:%.*]] = load i16, i16* [[ARRAYIDXB]], align 2 ; LV-NEXT: [[LOADB:%.*]] = load i16, i16* [[ARRAYIDXB]], align 2
; LV-NEXT: [[ADD:%.*]] = mul i16 [[LOADA]], [[LOADB]] ; LV-NEXT: [[ADD:%.*]] = mul i16 [[LOADA]], [[LOADB]]
; LV-NEXT: store i16 [[ADD]], i16* [[ARRAYIDXA]], align 2 ; LV-NEXT: store i16 [[ADD]], i16* [[ARRAYIDXA]], align 2
; LV-NEXT: [[INC]] = add nuw nsw i64 [[IND]], 1 ; LV-NEXT: [[INC]] = add nuw nsw i64 [[IND]], 1
; LV-NEXT: [[INC1]] = add i32 [[IND1]], 1 ; LV-NEXT: [[INC1]] = add i32 [[IND1]], 1
; LV-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INC]], [[N]] ; 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: for.end.loopexit:
; LV-NEXT: br label [[FOR_END:%.*]] ; LV-NEXT: br label [[FOR_END:%.*]]
; LV: for.end.loopexit7: ; LV: for.end.loopexit6:
; LV-NEXT: br label [[FOR_END]] ; LV-NEXT: br label [[FOR_END]]
; LV: for.end: ; LV: for.end:
; LV-NEXT: ret void ; LV-NEXT: ret void
; ;
i16* noalias %b, i64 %N) { i16* noalias %b, i64 %N) {
entry: entry:
br label %for.body br label %for.body
▲ Show 20 Lines • Show All 44 Lines • ▼ Show 20 Lines
; LV-NEXT: [[TMP10:%.*]] = or i1 [[TMP9]], [[MUL_OVERFLOW]] ; LV-NEXT: [[TMP10:%.*]] = or i1 [[TMP9]], [[MUL_OVERFLOW]]
; LV-NEXT: [[TMP11:%.*]] = or i1 false, [[TMP10]] ; LV-NEXT: [[TMP11:%.*]] = or i1 false, [[TMP10]]
; LV-NEXT: [[TMP12:%.*]] = sext i32 [[TMP1]] to i64 ; LV-NEXT: [[TMP12:%.*]] = sext i32 [[TMP1]] to i64
; LV-NEXT: [[SCEVGEP:%.*]] = getelementptr i16, i16* [[A:%.*]], i64 [[TMP12]] ; LV-NEXT: [[SCEVGEP:%.*]] = getelementptr i16, i16* [[A:%.*]], i64 [[TMP12]]
; LV-NEXT: [[MUL2:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 4, i64 [[TMP0]]) ; 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_RESULT3:%.*]] = extractvalue { i64, i1 } [[MUL2]], 0
; LV-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1 ; LV-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1
; LV-NEXT: [[SCEVGEP5:%.*]] = bitcast i16* [[SCEVGEP]] to i8* ; LV-NEXT: [[SCEVGEP5:%.*]] = bitcast i16* [[SCEVGEP]] to i8*
; LV-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[MUL_RESULT3]] ; LV-NEXT: [[TMP13:%.*]] = sub i64 0, [[MUL_RESULT3]]
; LV-NEXT: [[TMP13:%.*]] = bitcast i8* [[UGLYGEP]] to i16* ; LV-NEXT: [[TMP14:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[MUL_RESULT3]]
; LV-NEXT: [[TMP14:%.*]] = sub i64 [[MUL_RESULT3]], -4 ; LV-NEXT: [[TMP15:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[TMP13]]
; LV-NEXT: [[TMP15:%.*]] = sub i64 4, [[TMP14]] ; LV-NEXT: [[TMP16:%.*]] = icmp ugt i8* [[TMP15]], [[SCEVGEP5]]
; LV-NEXT: [[UGLYGEP6:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[TMP15]] ; LV-NEXT: [[TMP17:%.*]] = icmp ult i8* [[TMP14]], [[SCEVGEP5]]
; LV-NEXT: [[TMP16:%.*]] = bitcast i8* [[UGLYGEP6]] to i16* ; LV-NEXT: [[TMP18:%.*]] = select i1 true, i1 [[TMP16]], i1 [[TMP17]]
; LV-NEXT: [[TMP17:%.*]] = icmp ugt i16* [[TMP16]], [[SCEVGEP]] ; LV-NEXT: [[TMP19:%.*]] = or i1 [[TMP18]], [[MUL_OVERFLOW4]]
; LV-NEXT: [[TMP18:%.*]] = icmp ult i16* [[TMP13]], [[SCEVGEP]] ; LV-NEXT: [[TMP20:%.*]] = or i1 [[TMP11]], [[TMP19]]
; LV-NEXT: [[TMP19:%.*]] = select i1 true, i1 [[TMP17]], i1 [[TMP18]] ; LV-NEXT: br i1 [[TMP20]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH:%.*]]
; 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: for.body.ph.lver.orig: ; LV: for.body.ph.lver.orig:
; LV-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]] ; LV-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]]
; LV: for.body.lver.orig: ; LV: for.body.lver.orig:
; LV-NEXT: [[IND_LVER_ORIG:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ] ; LV-NEXT: [[IND_LVER_ORIG:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; LV-NEXT: [[IND1_LVER_ORIG:%.*]] = phi i32 [ [[TRUNCN]], [[FOR_BODY_PH_LVER_ORIG]] ], [ [[DEC_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ] ; LV-NEXT: [[IND1_LVER_ORIG:%.*]] = phi i32 [ [[TRUNCN]], [[FOR_BODY_PH_LVER_ORIG]] ], [ [[DEC_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; LV-NEXT: [[MUL_LVER_ORIG:%.*]] = mul i32 [[IND1_LVER_ORIG]], 2 ; LV-NEXT: [[MUL_LVER_ORIG:%.*]] = mul i32 [[IND1_LVER_ORIG]], 2
; LV-NEXT: [[MUL_EXT_LVER_ORIG:%.*]] = sext i32 [[MUL_LVER_ORIG]] to i64 ; LV-NEXT: [[MUL_EXT_LVER_ORIG:%.*]] = sext i32 [[MUL_LVER_ORIG]] to i64
; LV-NEXT: [[ARRAYIDXA_LVER_ORIG:%.*]] = getelementptr i16, i16* [[A]], i64 [[MUL_EXT_LVER_ORIG]] ; LV-NEXT: [[ARRAYIDXA_LVER_ORIG:%.*]] = getelementptr i16, i16* [[A]], i64 [[MUL_EXT_LVER_ORIG]]
Show All 17 Lines
; LV-NEXT: [[LOADA:%.*]] = load i16, i16* [[ARRAYIDXA]], align 2 ; LV-NEXT: [[LOADA:%.*]] = load i16, i16* [[ARRAYIDXA]], align 2
; LV-NEXT: [[ARRAYIDXB:%.*]] = getelementptr i16, i16* [[B]], i64 [[IND]] ; LV-NEXT: [[ARRAYIDXB:%.*]] = getelementptr i16, i16* [[B]], i64 [[IND]]
; LV-NEXT: [[LOADB:%.*]] = load i16, i16* [[ARRAYIDXB]], align 2 ; LV-NEXT: [[LOADB:%.*]] = load i16, i16* [[ARRAYIDXB]], align 2
; LV-NEXT: [[ADD:%.*]] = mul i16 [[LOADA]], [[LOADB]] ; LV-NEXT: [[ADD:%.*]] = mul i16 [[LOADA]], [[LOADB]]
; LV-NEXT: store i16 [[ADD]], i16* [[ARRAYIDXA]], align 2 ; LV-NEXT: store i16 [[ADD]], i16* [[ARRAYIDXA]], align 2
; LV-NEXT: [[INC]] = add nuw nsw i64 [[IND]], 1 ; LV-NEXT: [[INC]] = add nuw nsw i64 [[IND]], 1
; LV-NEXT: [[DEC]] = sub i32 [[IND1]], 1 ; LV-NEXT: [[DEC]] = sub i32 [[IND1]], 1
; LV-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INC]], [[N]] ; 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: for.end.loopexit:
; LV-NEXT: br label [[FOR_END:%.*]] ; LV-NEXT: br label [[FOR_END:%.*]]
; LV: for.end.loopexit7: ; LV: for.end.loopexit6:
; LV-NEXT: br label [[FOR_END]] ; LV-NEXT: br label [[FOR_END]]
; LV: for.end: ; LV: for.end:
; LV-NEXT: ret void ; LV-NEXT: ret void
; ;
i16* noalias %b, i64 %N) { i16* noalias %b, i64 %N) {
entry: entry:
%TruncN = trunc i64 %N to i32 %TruncN = trunc i64 %N to i32
br label %for.body br label %for.body
▲ Show 20 Lines • Show All 52 Lines • ▼ Show 20 Lines
; LV-NEXT: [[TMP10:%.*]] = or i1 [[TMP9]], [[MUL_OVERFLOW]] ; LV-NEXT: [[TMP10:%.*]] = or i1 [[TMP9]], [[MUL_OVERFLOW]]
; LV-NEXT: [[TMP11:%.*]] = or i1 false, [[TMP10]] ; LV-NEXT: [[TMP11:%.*]] = or i1 false, [[TMP10]]
; LV-NEXT: [[TMP12:%.*]] = sext i32 [[TMP1]] to i64 ; LV-NEXT: [[TMP12:%.*]] = sext i32 [[TMP1]] to i64
; LV-NEXT: [[SCEVGEP:%.*]] = getelementptr i16, i16* [[A:%.*]], i64 [[TMP12]] ; LV-NEXT: [[SCEVGEP:%.*]] = getelementptr i16, i16* [[A:%.*]], i64 [[TMP12]]
; LV-NEXT: [[MUL2:%.*]] = call { i64, i1 } @llvm.umul.with.overflow.i64(i64 4, i64 [[TMP0]]) ; 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_RESULT3:%.*]] = extractvalue { i64, i1 } [[MUL2]], 0
; LV-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1 ; LV-NEXT: [[MUL_OVERFLOW4:%.*]] = extractvalue { i64, i1 } [[MUL2]], 1
; LV-NEXT: [[SCEVGEP5:%.*]] = bitcast i16* [[SCEVGEP]] to i8* ; LV-NEXT: [[SCEVGEP5:%.*]] = bitcast i16* [[SCEVGEP]] to i8*
; LV-NEXT: [[UGLYGEP:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[MUL_RESULT3]] ; LV-NEXT: [[TMP13:%.*]] = sub i64 0, [[MUL_RESULT3]]
; LV-NEXT: [[TMP13:%.*]] = bitcast i8* [[UGLYGEP]] to i16* ; LV-NEXT: [[TMP14:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[MUL_RESULT3]]
; LV-NEXT: [[TMP14:%.*]] = sub i64 [[MUL_RESULT3]], -4 ; LV-NEXT: [[TMP15:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[TMP13]]
; LV-NEXT: [[TMP15:%.*]] = sub i64 4, [[TMP14]] ; LV-NEXT: [[TMP16:%.*]] = icmp ugt i8* [[TMP15]], [[SCEVGEP5]]
; LV-NEXT: [[UGLYGEP6:%.*]] = getelementptr i8, i8* [[SCEVGEP5]], i64 [[TMP15]] ; LV-NEXT: [[TMP17:%.*]] = icmp ult i8* [[TMP14]], [[SCEVGEP5]]
; LV-NEXT: [[TMP16:%.*]] = bitcast i8* [[UGLYGEP6]] to i16* ; LV-NEXT: [[TMP18:%.*]] = select i1 true, i1 [[TMP16]], i1 [[TMP17]]
; LV-NEXT: [[TMP17:%.*]] = icmp ugt i16* [[TMP16]], [[SCEVGEP]] ; LV-NEXT: [[TMP19:%.*]] = or i1 [[TMP18]], [[MUL_OVERFLOW4]]
; LV-NEXT: [[TMP18:%.*]] = icmp ult i16* [[TMP13]], [[SCEVGEP]] ; LV-NEXT: [[TMP20:%.*]] = or i1 [[TMP11]], [[TMP19]]
; LV-NEXT: [[TMP19:%.*]] = select i1 true, i1 [[TMP17]], i1 [[TMP18]] ; LV-NEXT: br i1 [[TMP20]], label [[FOR_BODY_PH_LVER_ORIG:%.*]], label [[FOR_BODY_PH:%.*]]
; 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: for.body.ph.lver.orig: ; LV: for.body.ph.lver.orig:
; LV-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]] ; LV-NEXT: br label [[FOR_BODY_LVER_ORIG:%.*]]
; LV: for.body.lver.orig: ; LV: for.body.lver.orig:
; LV-NEXT: [[IND_LVER_ORIG:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ] ; LV-NEXT: [[IND_LVER_ORIG:%.*]] = phi i64 [ 0, [[FOR_BODY_PH_LVER_ORIG]] ], [ [[INC_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; LV-NEXT: [[IND1_LVER_ORIG:%.*]] = phi i32 [ [[TRUNCN]], [[FOR_BODY_PH_LVER_ORIG]] ], [ [[DEC_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ] ; LV-NEXT: [[IND1_LVER_ORIG:%.*]] = phi i32 [ [[TRUNCN]], [[FOR_BODY_PH_LVER_ORIG]] ], [ [[DEC_LVER_ORIG:%.*]], [[FOR_BODY_LVER_ORIG]] ]
; LV-NEXT: [[MUL_LVER_ORIG:%.*]] = mul i32 [[IND1_LVER_ORIG]], 2 ; LV-NEXT: [[MUL_LVER_ORIG:%.*]] = mul i32 [[IND1_LVER_ORIG]], 2
; LV-NEXT: [[ARRAYIDXA_LVER_ORIG:%.*]] = getelementptr inbounds i16, i16* [[A]], i32 [[MUL_LVER_ORIG]] ; LV-NEXT: [[ARRAYIDXA_LVER_ORIG:%.*]] = getelementptr inbounds i16, i16* [[A]], i32 [[MUL_LVER_ORIG]]
; LV-NEXT: [[LOADA_LVER_ORIG:%.*]] = load i16, i16* [[ARRAYIDXA_LVER_ORIG]], align 2 ; LV-NEXT: [[LOADA_LVER_ORIG:%.*]] = load i16, i16* [[ARRAYIDXA_LVER_ORIG]], align 2
Show All 15 Lines
; LV-NEXT: [[LOADA:%.*]] = load i16, i16* [[ARRAYIDXA]], align 2 ; LV-NEXT: [[LOADA:%.*]] = load i16, i16* [[ARRAYIDXA]], align 2
; LV-NEXT: [[ARRAYIDXB:%.*]] = getelementptr inbounds i16, i16* [[B]], i64 [[IND]] ; LV-NEXT: [[ARRAYIDXB:%.*]] = getelementptr inbounds i16, i16* [[B]], i64 [[IND]]
; LV-NEXT: [[LOADB:%.*]] = load i16, i16* [[ARRAYIDXB]], align 2 ; LV-NEXT: [[LOADB:%.*]] = load i16, i16* [[ARRAYIDXB]], align 2
; LV-NEXT: [[ADD:%.*]] = mul i16 [[LOADA]], [[LOADB]] ; LV-NEXT: [[ADD:%.*]] = mul i16 [[LOADA]], [[LOADB]]
; LV-NEXT: store i16 [[ADD]], i16* [[ARRAYIDXA]], align 2 ; LV-NEXT: store i16 [[ADD]], i16* [[ARRAYIDXA]], align 2
; LV-NEXT: [[INC]] = add nuw nsw i64 [[IND]], 1 ; LV-NEXT: [[INC]] = add nuw nsw i64 [[IND]], 1
; LV-NEXT: [[DEC]] = sub i32 [[IND1]], 1 ; LV-NEXT: [[DEC]] = sub i32 [[IND1]], 1
; LV-NEXT: [[EXITCOND:%.*]] = icmp eq i64 [[INC]], [[N]] ; 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: for.end.loopexit:
; LV-NEXT: br label [[FOR_END:%.*]] ; LV-NEXT: br label [[FOR_END:%.*]]
; LV: for.end.loopexit7: ; LV: for.end.loopexit6:
; LV-NEXT: br label [[FOR_END]] ; LV-NEXT: br label [[FOR_END]]
; LV: for.end: ; LV: for.end:
; LV-NEXT: ret void ; LV-NEXT: ret void
; ;
i16* noalias %b, i64 %N) { i16* noalias %b, i64 %N) {
entry: entry:
%TruncN = trunc i64 %N to i32 %TruncN = trunc i64 %N to i32
br label %for.body br label %for.body
Show All 26 Lines