forked from OSchip/llvm-project
[Inlining] Teach shouldBeDeferred to take the total cost into account
Summary: This patch teaches shouldBeDeferred to take into account the total cost of inlining. Suppose we have a call hierarchy {A1,A2,A3,...}->B->C. (Each of A1, A2, A3, ... calls B, which in turn calls C.) Without this patch, shouldBeDeferred essentially returns true if TotalSecondaryCost < IC.getCost() where TotalSecondaryCost is the total cost of inlining B into As. This means that if B is a small wraper function, for example, it would get inlined into all of As. In turn, C gets inlined into all of As. In other words, shouldBeDeferred ignores the cost of inlining C into each of As. This patch adds an option, inline-deferral-scale, to replace the expression above with: TotalCost < Allowance where - TotalCost is TotalSecondaryCost + IC.getCost() * # of As, and - Allowance is IC.getCost() * Scale For now, the new option defaults to -1, disabling the new scheme. Reviewers: davidxl Subscribers: eraman, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D79138
This commit is contained in:
parent
61d5b0e663
commit
e8984fe65b
|
@ -93,6 +93,13 @@ static cl::opt<bool>
|
|||
DisableInlinedAllocaMerging("disable-inlined-alloca-merging",
|
||||
cl::init(false), cl::Hidden);
|
||||
|
||||
// An integer used to limit the cost of inline deferral. The default negative
|
||||
// number tells shouldBeDeferred to only take the secondary cost into account.
|
||||
static cl::opt<int>
|
||||
InlineDeferralScale("inline-deferral-scale",
|
||||
cl::desc("Scale to limit the cost of inline deferral"),
|
||||
cl::init(-1), cl::Hidden);
|
||||
|
||||
namespace {
|
||||
|
||||
enum class InlinerFunctionImportStatsOpts {
|
||||
|
@ -338,12 +345,8 @@ shouldBeDeferred(Function *Caller, InlineCost IC, int &TotalSecondaryCost,
|
|||
bool ApplyLastCallBonus = Caller->hasLocalLinkage() && !Caller->hasOneUse();
|
||||
// This bool tracks what happens if we DO inline C into B.
|
||||
bool InliningPreventsSomeOuterInline = false;
|
||||
unsigned NumCallerUsers = 0;
|
||||
for (User *U : Caller->users()) {
|
||||
// If the caller will not be removed (either because it does not have a
|
||||
// local linkage or because the LastCallToStaticBonus has been already
|
||||
// applied), then we can exit the loop early.
|
||||
if (!ApplyLastCallBonus && TotalSecondaryCost >= IC.getCost())
|
||||
return false;
|
||||
CallBase *CS2 = dyn_cast<CallBase>(U);
|
||||
|
||||
// If this isn't a call to Caller (it could be some other sort
|
||||
|
@ -369,8 +372,13 @@ shouldBeDeferred(Function *Caller, InlineCost IC, int &TotalSecondaryCost,
|
|||
if (IC2.getCostDelta() <= CandidateCost) {
|
||||
InliningPreventsSomeOuterInline = true;
|
||||
TotalSecondaryCost += IC2.getCost();
|
||||
NumCallerUsers++;
|
||||
}
|
||||
}
|
||||
|
||||
if (!InliningPreventsSomeOuterInline)
|
||||
return false;
|
||||
|
||||
// If all outer calls to Caller would get inlined, the cost for the last
|
||||
// one is set very low by getInlineCost, in anticipation that Caller will
|
||||
// be removed entirely. We did not account for this above unless there
|
||||
|
@ -378,7 +386,14 @@ shouldBeDeferred(Function *Caller, InlineCost IC, int &TotalSecondaryCost,
|
|||
if (ApplyLastCallBonus)
|
||||
TotalSecondaryCost -= InlineConstants::LastCallToStaticBonus;
|
||||
|
||||
return InliningPreventsSomeOuterInline && TotalSecondaryCost < IC.getCost();
|
||||
// If InlineDeferralScale is negative, then ignore the cost of primary
|
||||
// inlining -- IC.getCost() multiplied by the number of callers to Caller.
|
||||
if (InlineDeferralScale < 0)
|
||||
return TotalSecondaryCost < IC.getCost();
|
||||
|
||||
int TotalCost = TotalSecondaryCost + IC.getCost() * NumCallerUsers;
|
||||
int Allowance = IC.getCost() * InlineDeferralScale;
|
||||
return TotalCost < Allowance;
|
||||
}
|
||||
|
||||
static std::basic_ostream<char> &operator<<(std::basic_ostream<char> &R,
|
||||
|
|
Loading…
Reference in New Issue