Skip to content

Commit

Permalink
[IndVars] Widen more comparisons for non-negative induction vars
Browse files Browse the repository at this point in the history 
Summary:
If an induction variable is provably non-negative, its sign extension is
equal to its zero extension.  This means narrow uses like

  icmp slt iNarrow %indvar, %rhs

can be widened into

  icmp slt iWide zext(%indvar), sext(%rhs)

Reviewers: atrick, mcrosier, hfinkel

Subscribers: hfinkel, reames, llvm-commits

Differential Revision: http://reviews.llvm.org/D12745

llvm-svn: 248045
  • Loading branch information
@sanjoy
sanjoy committed Sep 18, 2015
1 parent e8d1c59 commit f69d0e3
Show file tree
Hide file tree
Showing 2 changed files with 154 additions and 3 deletions.
29 changes: 26 additions & 3 deletions llvm/lib/Transforms/Scalar/IndVarSimplify.cpp
View file
Expand Up @@ -849,6 +849,11 @@ class WidenIV {
Type *WideType;
bool IsSigned;

// True if the narrow induction variable is never negative. Tracking this
// information lets us use a sign extension instead of a zero extension or
// vice versa, when profitable and legal.
bool NeverNegative;

// Context
LoopInfo *LI;
Loop *L;
Expand All @@ -871,6 +876,7 @@ class WidenIV {
OrigPhi(WI.NarrowIV),
WideType(WI.WidestNativeType),
IsSigned(WI.IsSigned),
NeverNegative(false),
LI(LInfo),
L(LI->getLoopFor(OrigPhi->getParent())),
SE(SEv),
Expand Down Expand Up @@ -1082,8 +1088,22 @@ bool WidenIV::WidenLoopCompare(NarrowIVDefUse DU) {
if (!Cmp)
return false;

// Sign of IV user and compare must match.
if (IsSigned != CmpInst::isSigned(Cmp->getPredicate()))
// We can legally widen the comparison in the following two cases:
//
// - The signedness of the IV extension and comparison match
//
// - The narrow IV is always positive (and thus its sign extension is equal
// to its zero extension). For instance, let's say we're zero extending
// %narrow for the following use
//
// icmp slt i32 %narrow, %val ... (A)
//
// and %narrow is always positive. Then
//
// (A) == icmp slt i32 sext(%narrow), sext(%val)
// == icmp slt i32 zext(%narrow), sext(%val)

if (!(NeverNegative || IsSigned == Cmp->isSigned()))
return false;

Value *Op = Cmp->getOperand(Cmp->getOperand(0) == DU.NarrowDef ? 1 : 0);
Expand All @@ -1097,7 +1117,7 @@ bool WidenIV::WidenLoopCompare(NarrowIVDefUse DU) {

// Widen the other operand of the compare, if necessary.
if (CastWidth < IVWidth) {
Value *ExtOp = getExtend(Op, WideType, IsSigned, Cmp);
Value *ExtOp = getExtend(Op, WideType, Cmp->isSigned(), Cmp);
DU.NarrowUse->replaceUsesOfWith(Op, ExtOp);
}
return true;
Expand Down Expand Up @@ -1247,6 +1267,9 @@ PHINode *WidenIV::CreateWideIV(SCEVExpander &Rewriter) {
if (!AddRec)
return nullptr;

NeverNegative = SE->isKnownPredicate(ICmpInst::ICMP_SGE, AddRec,
SE->getConstant(AddRec->getType(), 0));

// Widen the induction variable expression.
const SCEV *WideIVExpr = IsSigned ?
SE->getSignExtendExpr(AddRec, WideType) :
Expand Down
128 changes: 128 additions & 0 deletions llvm/test/Transforms/IndVarSimplify/widen-loop-comp.ll
View file
Expand Up @@ -193,3 +193,131 @@ for.body:
for.end:
ret i32 %sum.0
}

define i32 @test6(i32* %a, i32 %b) {
; CHECK-LABEL: @test6(
; CHECK: [[B_SEXT:%[a-z0-9]+]] = sext i32 %b to i64
; CHECK: for.cond:
; CHECK: icmp sle i64 %indvars.iv, [[B_SEXT]]

entry:
br label %for.cond

for.cond:
%sum.0 = phi i32 [ 0, %entry ], [ %add, %for.body ]
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%cmp = icmp sle i32 %i.0, %b
br i1 %cmp, label %for.body, label %for.end

for.body:
%idxprom = zext i32 %i.0 to i64
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4
%add = add nsw i32 %sum.0, %0
%inc = add nsw i32 %i.0, 1
br label %for.cond

for.end:
ret i32 %sum.0
}

define i32 @test7(i32* %a, i32 %b) {
; CHECK-LABEL: @test7(
; CHECK: [[B_ZEXT:%[a-z0-9]+]] = zext i32 %b to i64
; CHECK: [[B_SEXT:%[a-z0-9]+]] = sext i32 %b to i64
; CHECK: for.cond:
; CHECK: icmp ule i64 %indvars.iv, [[B_ZEXT]]
; CHECK: for.body:
; CHECK: icmp sle i64 %indvars.iv, [[B_SEXT]]

entry:
br label %for.cond

for.cond:
%sum.0 = phi i32 [ 0, %entry ], [ %add, %for.body ]
%i.0 = phi i32 [ 0, %entry ], [ %inc, %for.body ]
%cmp = icmp ule i32 %i.0, %b
br i1 %cmp, label %for.body, label %for.end

for.body:
%idxprom = sext i32 %i.0 to i64
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4
%add = add nsw i32 %sum.0, %0
%inc = add nsw i32 %i.0, 1
%cmp2 = icmp sle i32 %i.0, %b
br i1 %cmp2, label %for.cond, label %for.end

for.end:
ret i32 %sum.0
}

define i32 @test8(i32* %a, i32 %b, i32 %init) {
; CHECK-LABEL: @test8(
; CHECK: [[INIT_SEXT:%[a-z0-9]+]] = sext i32 %init to i64
; CHECK: [[B_ZEXT:%[a-z0-9]+]] = zext i32 %b to i64
; CHECK: for.cond:
; Note: %indvars.iv is the sign extension of %i.0
; CHECK: %indvars.iv = phi i64 [ [[INIT_SEXT]], %for.cond.preheader ], [ %indvars.iv.next, %for.body ]
; CHECK: icmp ule i64 %indvars.iv, [[B_ZEXT]]

entry:
%e = icmp sgt i32 %init, 0
br i1 %e, label %for.cond, label %leave

for.cond:
%sum.0 = phi i32 [ 0, %entry ], [ %add, %for.body ]
%i.0 = phi i32 [ %init, %entry ], [ %inc, %for.body ]
%cmp = icmp ule i32 %i.0, %b
br i1 %cmp, label %for.body, label %for.end

for.body:
%idxprom = sext i32 %i.0 to i64
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4
%add = add nsw i32 %sum.0, %0
%inc = add nsw i32 %i.0, 1
%cmp2 = icmp slt i32 0, %inc
br i1 %cmp2, label %for.cond, label %for.end

for.end:
ret i32 %sum.0

leave:
ret i32 0
}

define i32 @test9(i32* %a, i32 %b, i32 %init) {
; CHECK-LABEL: @test9(
; CHECK: [[INIT_ZEXT:%[a-z0-9]+]] = zext i32 %init to i64
; CHECK: [[B_SEXT:%[a-z0-9]+]] = sext i32 %b to i64
; CHECK: for.cond:
; Note: %indvars.iv is the zero extension of %i.0
; CHECK: %indvars.iv = phi i64 [ [[INIT_ZEXT]], %for.cond.preheader ], [ %indvars.iv.next, %for.body ]
; CHECK: icmp slt i64 %indvars.iv, [[B_SEXT]]

entry:
%e = icmp sgt i32 %init, 0
br i1 %e, label %for.cond, label %leave

for.cond:
%sum.0 = phi i32 [ 0, %entry ], [ %add, %for.body ]
%i.0 = phi i32 [ %init, %entry ], [ %inc, %for.body ]
%cmp = icmp slt i32 %i.0, %b
br i1 %cmp, label %for.body, label %for.end

for.body:
%idxprom = zext i32 %i.0 to i64
%arrayidx = getelementptr inbounds i32, i32* %a, i64 %idxprom
%0 = load i32, i32* %arrayidx, align 4
%add = add nsw i32 %sum.0, %0
%inc = add nsw i32 %i.0, 1
%cmp2 = icmp slt i32 0, %inc
br i1 %cmp2, label %for.cond, label %for.end

for.end:
ret i32 %sum.0

leave:
ret i32 0
}

0 comments on commit f69d0e3

Please sign in to comment.