mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-26 12:43:36 +01:00
[SCCP] Use conditional info with AND/OR branch conditions.
Currently SCCP does not combine the information of conditions joined by AND in the true branch or OR in the false branch. For branches on AND, 2 copies will be inserted for the true branch, with one being the operand of the other as in the code below. We can combine the information using intersection. Note that for the OR case, the copies are inserted in the false branch, where using intersection is safe as well. define void @foo(i32 %a) { entry: %lt = icmp ult i32 %a, 100 %gt = icmp ugt i32 %a, 20 %and = and i1 %lt, %gt ; Has predicate info ; branch predicate info { TrueEdge: 1 Comparison: %lt = icmp ult i32 %a, 100 Edge: [label %entry,label %true] } %a.0 = call i32 @llvm.ssa.copy.140247425954880(i32 %a) ; Has predicate info ; branch predicate info { TrueEdge: 1 Comparison: %gt = icmp ugt i32 %a, 20 Edge: [label %entry,label %false] } %a.1 = call i32 @llvm.ssa.copy.140247425954880(i32 %a.0) br i1 %and, label %true, label %false true: ; preds = %entry call void @use(i32 %a.1) %true.1 = icmp ne i32 %a.1, 20 call void @use.i1(i1 %true.1) ret void false: ; preds = %entry call void @use(i32 %a.1) ret void } Reviewers: efriedma, davide, mssimpso, nikic Reviewed By: nikic Differential Revision: https://reviews.llvm.org/D77808
This commit is contained in:
parent
996e94e98e
commit
6574ec1d01
@ -1258,7 +1258,7 @@ void SCCPSolver::handleCallResult(CallBase &CB) {
|
||||
return;
|
||||
|
||||
Value *CopyOf = CB.getOperand(0);
|
||||
ValueLatticeElement OriginalVal = getValueState(CopyOf);
|
||||
ValueLatticeElement CopyOfVal = getValueState(CopyOf);
|
||||
auto *PI = getPredicateInfoFor(&CB);
|
||||
assert(PI && "Missing predicate info for ssa.copy");
|
||||
|
||||
@ -1271,25 +1271,27 @@ void SCCPSolver::handleCallResult(CallBase &CB) {
|
||||
Cmp = dyn_cast<CmpInst>(PAssume->Condition);
|
||||
TrueEdge = true;
|
||||
} else {
|
||||
mergeInValue(ValueState[&CB], &CB, OriginalVal);
|
||||
mergeInValue(ValueState[&CB], &CB, CopyOfVal);
|
||||
return;
|
||||
}
|
||||
|
||||
// Everything below relies on the condition being a comparison.
|
||||
if (!Cmp) {
|
||||
mergeInValue(ValueState[&CB], &CB, OriginalVal);
|
||||
mergeInValue(ValueState[&CB], &CB, CopyOfVal);
|
||||
return;
|
||||
}
|
||||
|
||||
Value *RenamedOp = PI->RenamedOp;
|
||||
Value *CmpOp0 = Cmp->getOperand(0);
|
||||
Value *CmpOp1 = Cmp->getOperand(1);
|
||||
if (CopyOf != CmpOp0 && CopyOf != CmpOp1) {
|
||||
mergeInValue(ValueState[&CB], &CB, OriginalVal);
|
||||
// Bail out if neither of the operands matches RenamedOp.
|
||||
if (CmpOp0 != RenamedOp && CmpOp1 != RenamedOp) {
|
||||
mergeInValue(ValueState[&CB], &CB, getValueState(CopyOf));
|
||||
return;
|
||||
}
|
||||
|
||||
auto Pred = Cmp->getPredicate();
|
||||
if (CmpOp0 != CopyOf) {
|
||||
if (CmpOp1 == RenamedOp) {
|
||||
std::swap(CmpOp0, CmpOp1);
|
||||
Pred = Cmp->getSwappedPredicate();
|
||||
}
|
||||
@ -1300,27 +1302,37 @@ void SCCPSolver::handleCallResult(CallBase &CB) {
|
||||
return;
|
||||
}
|
||||
|
||||
// The code below relies on PredicateInfo only inserting copies for the
|
||||
// true branch when the branch condition is an AND and only inserting
|
||||
// copies for the false branch when the branch condition is an OR. This
|
||||
// ensures we can intersect the range from the condition with the range of
|
||||
// CopyOf.
|
||||
if (!TrueEdge)
|
||||
Pred = CmpInst::getInversePredicate(Pred);
|
||||
|
||||
ValueLatticeElement CondVal = getValueState(CmpOp1);
|
||||
ValueLatticeElement &IV = ValueState[&CB];
|
||||
if (CondVal.isConstantRange() || OriginalVal.isConstantRange()) {
|
||||
auto NewCR =
|
||||
if (CondVal.isConstantRange() || CopyOfVal.isConstantRange()) {
|
||||
auto ImposedCR =
|
||||
ConstantRange::getFull(DL.getTypeSizeInBits(CopyOf->getType()));
|
||||
|
||||
// Get the range imposed by the condition.
|
||||
if (CondVal.isConstantRange())
|
||||
NewCR = ConstantRange::makeAllowedICmpRegion(
|
||||
ImposedCR = ConstantRange::makeAllowedICmpRegion(
|
||||
Pred, CondVal.getConstantRange());
|
||||
|
||||
// Combine range info for the original value with the new range from the
|
||||
// condition.
|
||||
auto OriginalCR = OriginalVal.isConstantRange()
|
||||
? OriginalVal.getConstantRange()
|
||||
: ConstantRange::getFull(
|
||||
DL.getTypeSizeInBits(CopyOf->getType()));
|
||||
NewCR = NewCR.intersectWith(OriginalCR);
|
||||
auto CopyOfCR = CopyOfVal.isConstantRange()
|
||||
? CopyOfVal.getConstantRange()
|
||||
: ConstantRange::getFull(
|
||||
DL.getTypeSizeInBits(CopyOf->getType()));
|
||||
auto NewCR = ImposedCR.intersectWith(CopyOfCR);
|
||||
// If the existing information is != x, do not use the information from
|
||||
// a chained predicate, as the != x information is more likely to be
|
||||
// helpful in practice.
|
||||
if (!CopyOfCR.contains(NewCR) && CopyOfCR.getSingleMissingElement())
|
||||
NewCR = CopyOfCR;
|
||||
|
||||
addAdditionalUser(CmpOp1, &CB);
|
||||
// TODO: Actually filp MayIncludeUndef for the created range to false,
|
||||
@ -1344,7 +1356,7 @@ void SCCPSolver::handleCallResult(CallBase &CB) {
|
||||
return;
|
||||
}
|
||||
|
||||
return (void)mergeInValue(IV, &CB, OriginalVal);
|
||||
return (void)mergeInValue(IV, &CB, CopyOfVal);
|
||||
}
|
||||
}
|
||||
|
||||
|
@ -814,14 +814,11 @@ define void @f16_conditions_and(i32 %a, i32 %b) {
|
||||
; CHECK-NEXT: [[BC:%.*]] = and i1 [[LT]], [[GT]]
|
||||
; CHECK-NEXT: br i1 [[BC]], label [[TRUE:%.*]], label [[FALSE:%.*]]
|
||||
; CHECK: true:
|
||||
; CHECK-NEXT: [[F_1:%.*]] = icmp eq i32 [[A]], 0
|
||||
; CHECK-NEXT: call void @use(i1 [[F_1]])
|
||||
; CHECK-NEXT: [[F_2:%.*]] = icmp eq i32 [[A]], 20
|
||||
; CHECK-NEXT: call void @use(i1 [[F_2]])
|
||||
; CHECK-NEXT: call void @use(i1 false)
|
||||
; CHECK-NEXT: call void @use(i1 false)
|
||||
; CHECK-NEXT: call void @use(i1 false)
|
||||
; CHECK-NEXT: call void @use(i1 true)
|
||||
; CHECK-NEXT: [[T_2:%.*]] = icmp ne i32 [[A]], 20
|
||||
; CHECK-NEXT: call void @use(i1 [[T_2]])
|
||||
; CHECK-NEXT: call void @use(i1 true)
|
||||
; CHECK-NEXT: [[C_1:%.*]] = icmp eq i32 [[A]], 21
|
||||
; CHECK-NEXT: call void @use(i1 [[C_1]])
|
||||
; CHECK-NEXT: [[C_2:%.*]] = icmp ugt i32 [[A]], 21
|
||||
@ -899,10 +896,8 @@ define void @f17_conditions_or(i32 %a, i32 %b) {
|
||||
; CHECK: false:
|
||||
; CHECK-NEXT: call void @use(i1 false)
|
||||
; CHECK-NEXT: call void @use(i1 false)
|
||||
; CHECK-NEXT: [[F_3:%.*]] = icmp ugt i32 [[A]], 100
|
||||
; CHECK-NEXT: call void @use(i1 [[F_3]])
|
||||
; CHECK-NEXT: [[T_1:%.*]] = icmp ult i32 [[A]], 100
|
||||
; CHECK-NEXT: call void @use(i1 [[T_1]])
|
||||
; CHECK-NEXT: call void @use(i1 false)
|
||||
; CHECK-NEXT: call void @use(i1 true)
|
||||
; CHECK-NEXT: call void @use(i1 true)
|
||||
; CHECK-NEXT: [[C_1:%.*]] = icmp eq i32 [[A]], 21
|
||||
; CHECK-NEXT: call void @use(i1 [[C_1]])
|
||||
|
Loading…
Reference in New Issue
Block a user