forked from OSchip/llvm-project
[SCEV][IndVars] Always provide insertion point to the SCEVExpander::isHighCostExpansion()
Summary: This addresses the `llvm/test/Transforms/IndVarSimplify/elim-extend.ll` `@nestedIV` regression from D73728 Reviewers: reames, mkazantsev, wmi, sanjoy Reviewed By: mkazantsev Subscribers: hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D73777
This commit is contained in:
parent
44edc6fd2c
commit
400ceda425
|
@ -176,18 +176,19 @@ namespace llvm {
|
|||
/// Return true for expressions that can't be evaluated at runtime
|
||||
/// within given \b Budget.
|
||||
///
|
||||
/// At is an optional parameter which specifies point in code where user is
|
||||
/// going to expand this expression. Sometimes this knowledge can lead to a
|
||||
/// more accurate cost estimation.
|
||||
/// At is a parameter which specifies point in code where user is going to
|
||||
/// expand this expression. Sometimes this knowledge can lead to
|
||||
/// a less pessimistic cost estimation.
|
||||
bool isHighCostExpansion(const SCEV *Expr, Loop *L, unsigned Budget,
|
||||
const TargetTransformInfo *TTI,
|
||||
const Instruction *At = nullptr) {
|
||||
const Instruction *At) {
|
||||
assert(TTI && "This function requires TTI to be provided.");
|
||||
assert(At && "This function requires At instruction to be provided.");
|
||||
if (!TTI) // In assert-less builds, avoid crashing
|
||||
return true; // by always claiming to be high-cost.
|
||||
SmallPtrSet<const SCEV *, 8> Processed;
|
||||
int BudgetRemaining = Budget * TargetTransformInfo::TCC_Basic;
|
||||
return isHighCostExpansionHelper(Expr, L, At, BudgetRemaining, *TTI,
|
||||
return isHighCostExpansionHelper(Expr, L, *At, BudgetRemaining, *TTI,
|
||||
Processed);
|
||||
}
|
||||
|
||||
|
@ -331,7 +332,7 @@ namespace llvm {
|
|||
|
||||
/// Recursive helper function for isHighCostExpansion.
|
||||
bool isHighCostExpansionHelper(const SCEV *S, Loop *L,
|
||||
const Instruction *At, int &BudgetRemaining,
|
||||
const Instruction &At, int &BudgetRemaining,
|
||||
const TargetTransformInfo &TTI,
|
||||
SmallPtrSetImpl<const SCEV *> &Processed);
|
||||
|
||||
|
|
|
@ -2136,7 +2136,7 @@ SCEVExpander::getRelatedExistingExpansion(const SCEV *S, const Instruction *At,
|
|||
}
|
||||
|
||||
bool SCEVExpander::isHighCostExpansionHelper(
|
||||
const SCEV *S, Loop *L, const Instruction *At, int &BudgetRemaining,
|
||||
const SCEV *S, Loop *L, const Instruction &At, int &BudgetRemaining,
|
||||
const TargetTransformInfo &TTI, SmallPtrSetImpl<const SCEV *> &Processed) {
|
||||
if (BudgetRemaining < 0)
|
||||
return true; // Already run out of budget, give up.
|
||||
|
@ -2147,7 +2147,7 @@ bool SCEVExpander::isHighCostExpansionHelper(
|
|||
|
||||
// If we can find an existing value for this scev available at the point "At"
|
||||
// then consider the expression cheap.
|
||||
if (At && getRelatedExistingExpansion(S, At, L))
|
||||
if (getRelatedExistingExpansion(S, &At, L))
|
||||
return false; // Consider the expression to be free.
|
||||
|
||||
switch (S->getSCEVType()) {
|
||||
|
@ -2198,18 +2198,12 @@ bool SCEVExpander::isHighCostExpansionHelper(
|
|||
// UDiv from the user's code. If we can't find a UDiv in the code with some
|
||||
// simple searching, we need to account for it's cost.
|
||||
|
||||
BasicBlock *ExitingBB = L->getExitingBlock();
|
||||
if (At || ExitingBB) {
|
||||
if (!At)
|
||||
At = &ExitingBB->back();
|
||||
|
||||
// At the beginning of this function we already tried to find existing
|
||||
// value for plain 'S'. Now try to lookup 'S + 1' since it is common
|
||||
// pattern involving division. This is just a simple search heuristic.
|
||||
if (getRelatedExistingExpansion(
|
||||
SE.getAddExpr(S, SE.getConstant(S->getType(), 1)), At, L))
|
||||
return false; // Consider it to be free.
|
||||
}
|
||||
// At the beginning of this function we already tried to find existing
|
||||
// value for plain 'S'. Now try to lookup 'S + 1' since it is common
|
||||
// pattern involving division. This is just a simple search heuristic.
|
||||
if (getRelatedExistingExpansion(
|
||||
SE.getAddExpr(S, SE.getConstant(S->getType(), 1)), &At, L))
|
||||
return false; // Consider it to be free.
|
||||
|
||||
// Need to count the cost of this UDiv.
|
||||
BudgetRemaining -= TTI.getOperationCost(Instruction::UDiv, S->getType());
|
||||
|
|
|
@ -2726,6 +2726,9 @@ bool IndVarSimplify::run(Loop *L) {
|
|||
// If we have a trip count expression, rewrite the loop's exit condition
|
||||
// using it.
|
||||
if (!DisableLFTR) {
|
||||
BasicBlock *PreHeader = L->getLoopPreheader();
|
||||
BranchInst *PreHeaderBR = cast<BranchInst>(PreHeader->getTerminator());
|
||||
|
||||
SmallVector<BasicBlock*, 16> ExitingBlocks;
|
||||
L->getExitingBlocks(ExitingBlocks);
|
||||
for (BasicBlock *ExitingBB : ExitingBlocks) {
|
||||
|
@ -2760,7 +2763,7 @@ bool IndVarSimplify::run(Loop *L) {
|
|||
// Avoid high cost expansions. Note: This heuristic is questionable in
|
||||
// that our definition of "high cost" is not exactly principled.
|
||||
if (Rewriter.isHighCostExpansion(ExitCount, L, SCEVCheapExpansionBudget,
|
||||
TTI))
|
||||
TTI, PreHeaderBR))
|
||||
continue;
|
||||
|
||||
// Check preconditions for proper SCEVExpander operation. SCEV does not
|
||||
|
|
|
@ -140,8 +140,8 @@ define void @nestedIV(i8* %address, i32 %limit) nounwind {
|
|||
; CHECK-NEXT: store i8 0, i8* [[ADR2]]
|
||||
; CHECK-NEXT: [[ADR3:%.*]] = getelementptr i8, i8* [[ADDRESS]], i64 [[INDVARS_IV_NEXT]]
|
||||
; CHECK-NEXT: store i8 0, i8* [[ADR3]]
|
||||
; CHECK-NEXT: [[INNERCMP:%.*]] = icmp sgt i64 [[TMP0]], [[INDVARS_IV_NEXT]]
|
||||
; CHECK-NEXT: br i1 [[INNERCMP]], label [[INNERLOOP]], label [[INNEREXIT:%.*]]
|
||||
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT]], [[TMP0]]
|
||||
; CHECK-NEXT: br i1 [[EXITCOND]], label [[INNERLOOP]], label [[INNEREXIT:%.*]]
|
||||
; CHECK: innerexit:
|
||||
; CHECK-NEXT: [[TMP4:%.*]] = trunc i64 [[TMP0]] to i32
|
||||
; CHECK-NEXT: br label [[OUTERMERGE]]
|
||||
|
@ -153,8 +153,8 @@ define void @nestedIV(i8* %address, i32 %limit) nounwind {
|
|||
; CHECK-NEXT: [[ADR5:%.*]] = getelementptr i8, i8* [[ADDRESS]], i64 [[OFS5]]
|
||||
; CHECK-NEXT: store i8 0, i8* [[ADR5]]
|
||||
; CHECK-NEXT: [[INDVARS_IV_NEXT2]] = add nuw nsw i64 [[INDVARS_IV1]], 1
|
||||
; CHECK-NEXT: [[EXITCOND:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT2]], [[WIDE_TRIP_COUNT]]
|
||||
; CHECK-NEXT: br i1 [[EXITCOND]], label [[OUTERLOOP]], label [[RETURN:%.*]]
|
||||
; CHECK-NEXT: [[EXITCOND4:%.*]] = icmp ne i64 [[INDVARS_IV_NEXT2]], [[WIDE_TRIP_COUNT]]
|
||||
; CHECK-NEXT: br i1 [[EXITCOND4]], label [[OUTERLOOP]], label [[RETURN:%.*]]
|
||||
; CHECK: return:
|
||||
; CHECK-NEXT: ret void
|
||||
;
|
||||
|
|
Loading…
Reference in New Issue