[llvm] r309994 - [Inliner] Increase threshold for hot callsites without PGO.
Easwaran Raman via llvm-commits
llvm-commits at lists.llvm.org
Thu Aug 3 15:23:33 PDT 2017
Author: eraman
Date: Thu Aug 3 15:23:33 2017
New Revision: 309994
URL: http://llvm.org/viewvc/llvm-project?rev=309994&view=rev
Log:
[Inliner] Increase threshold for hot callsites without PGO.
Summary:
This increases the inlining threshold for hot callsites. Hotness is
defined in terms of block frequency of the callsite relative to the
caller's entry block's frequency. Since this requires BFI in the
inliner, this only affects the new PM pipeline. This is enabled by
default at -O3.
This improves the performance of some internal benchmarks. Notably, an
internal benchmark for Gipfeli compression
(https://github.com/google/gipfeli) improves by ~7%. Povray in SPEC2006
improves by ~2.5%. I am running more experiments and will update the
thread if other benchmarks show improvement/regression.
In terms of text size, LLVM test-suite shows an 1.22% text size
increase. Diving into the results, 13 of the benchmarks in the
test-suite increases by > 10%. Most of these are small, but
Adobe-C++/loop_unroll (17.6% increases) and tramp3d(20.7% size increase)
have >250K text size. On a large application, the text size increases by
2%
Reviewers: chandlerc, davidxl
Subscribers: llvm-commits
Differential Revision: https://reviews.llvm.org/D36199
Modified:
llvm/trunk/include/llvm/Analysis/InlineCost.h
llvm/trunk/lib/Analysis/InlineCost.cpp
Modified: llvm/trunk/include/llvm/Analysis/InlineCost.h
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/include/llvm/Analysis/InlineCost.h?rev=309994&r1=309993&r2=309994&view=diff
==============================================================================
--- llvm/trunk/include/llvm/Analysis/InlineCost.h (original)
+++ llvm/trunk/include/llvm/Analysis/InlineCost.h Thu Aug 3 15:23:33 2017
@@ -139,6 +139,10 @@ struct InlineParams {
/// Threshold to use when the callsite is considered hot.
Optional<int> HotCallSiteThreshold;
+ /// Threshold to use when the callsite is considered hot relative to function
+ /// entry.
+ Optional<int> LocallyHotCallSiteThreshold;
+
/// Threshold to use when the callsite is considered cold.
Optional<int> ColdCallSiteThreshold;
};
Modified: llvm/trunk/lib/Analysis/InlineCost.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Analysis/InlineCost.cpp?rev=309994&r1=309993&r2=309994&view=diff
==============================================================================
--- llvm/trunk/lib/Analysis/InlineCost.cpp (original)
+++ llvm/trunk/lib/Analysis/InlineCost.cpp Thu Aug 3 15:23:33 2017
@@ -66,12 +66,22 @@ static cl::opt<int>
cl::ZeroOrMore,
cl::desc("Threshold for hot callsites "));
+static cl::opt<int> LocallyHotCallSiteThreshold(
+ "locally-hot-callsite-threshold", cl::Hidden, cl::init(525), cl::ZeroOrMore,
+ cl::desc("Threshold for locally hot callsites "));
+
static cl::opt<int> ColdCallSiteRelFreq(
"cold-callsite-rel-freq", cl::Hidden, cl::init(2), cl::ZeroOrMore,
cl::desc("Maxmimum block frequency, expressed as a percentage of caller's "
"entry frequency, for a callsite to be cold in the absence of "
"profile information."));
+static cl::opt<int> HotCallSiteRelFreq(
+ "hot-callsite-rel-freq", cl::Hidden, cl::init(60), cl::ZeroOrMore,
+ cl::desc("Maxmimum block frequency, expressed as a multiple of caller's "
+ "entry frequency, for a callsite to be hot in the absence of "
+ "profile information."));
+
namespace {
class CallAnalyzer : public InstVisitor<CallAnalyzer, bool> {
@@ -182,6 +192,10 @@ class CallAnalyzer : public InstVisitor<
/// Return true if \p CS is a cold callsite.
bool isColdCallSite(CallSite CS, BlockFrequencyInfo *CallerBFI);
+ /// Return a higher threshold if \p CS is a hot callsite.
+ Optional<int> getHotCallSiteThreshold(CallSite CS,
+ BlockFrequencyInfo *CallerBFI);
+
// Custom analysis routines.
bool analyzeBlock(BasicBlock *BB, SmallPtrSetImpl<const Value *> &EphValues);
@@ -662,6 +676,34 @@ bool CallAnalyzer::isColdCallSite(CallSi
return CallSiteFreq < CallerEntryFreq * ColdProb;
}
+Optional<int>
+CallAnalyzer::getHotCallSiteThreshold(CallSite CS,
+ BlockFrequencyInfo *CallerBFI) {
+ // If global profile summary is available, then callsite's hotness is
+ // determined based on that.
+
+ auto HotCallSiteThreshold = Params.HotCallSiteThreshold;
+ if (PSI->hasProfileSummary() && PSI->isHotCallSite(CS, CallerBFI))
+ return HotCallSiteThreshold;
+ if (!CallerBFI)
+ return None;
+
+ HotCallSiteThreshold = Params.LocallyHotCallSiteThreshold;
+ if (!HotCallSiteThreshold)
+ return None;
+
+ // In the absence of global profile summary, determine if the callsite is hot
+ // relative to caller's entry. We could potentially cache the computation of
+ // scaled entry frequency, but the added complexity is not worth it unless
+ // this scaling shows up high in the profiles.
+ auto CallSiteBB = CS.getInstruction()->getParent();
+ auto CallSiteFreq = CallerBFI->getBlockFreq(CallSiteBB).getFrequency();
+ auto CallerEntryFreq = CallerBFI->getEntryFreq();
+ if (CallSiteFreq >= CallerEntryFreq * HotCallSiteRelFreq)
+ return HotCallSiteThreshold;
+ return None;
+}
+
void CallAnalyzer::updateThreshold(CallSite CS, Function &Callee) {
// If no size growth is allowed for this inlining, set Threshold to 0.
if (!allowSizeGrowth(CS)) {
@@ -742,9 +784,14 @@ void CallAnalyzer::updateThreshold(CallS
// sample profile is used (which adds hotness metadata to calls) or if
// caller's BlockFrequencyInfo is available.
if (CallerBFI || PSI->hasSampleProfile()) {
- if (PSI->isHotCallSite(CS, CallerBFI)) {
+ auto HotCallSiteThreshold = getHotCallSiteThreshold(CS, CallerBFI);
+ if (!Caller->optForSize() && HotCallSiteThreshold) {
DEBUG(dbgs() << "Hot callsite.\n");
- Threshold = Params.HotCallSiteThreshold.getValue();
+ // FIXME: This should update the threshold only if it exceeds the
+ // current threshold, but AutoFDO + ThinLTO currently relies on this
+ // behavior to prevent inlining of hot callsites during ThinLTO
+ // compile phase.
+ Threshold = HotCallSiteThreshold.getValue();
} else if (isColdCallSite(CS, CallerBFI)) {
DEBUG(dbgs() << "Cold callsite.\n");
// Do not apply bonuses for a cold callsite including the
@@ -1729,6 +1776,16 @@ InlineParams llvm::getInlineParams(int T
// Set the HotCallSiteThreshold knob from the -hot-callsite-threshold.
Params.HotCallSiteThreshold = HotCallSiteThreshold;
+ // If the -locally-hot-callsite-threshold is explicitly specified, use it to
+ // populate LocallyHotCallSiteThreshold. Later, we populate
+ // Params.LocallyHotCallSiteThreshold from -locally-hot-callsite-threshold if
+ // we know that optimization level is O3 (in the getInlineParams variant that
+ // takes the opt and size levels).
+ // FIXME: Remove this check (and make the assignment unconditional) after
+ // addressing size regression issues at O2.
+ if (LocallyHotCallSiteThreshold.getNumOccurrences() > 0)
+ Params.LocallyHotCallSiteThreshold = LocallyHotCallSiteThreshold;
+
// Set the ColdCallSiteThreshold knob from the -inline-cold-callsite-threshold.
Params.ColdCallSiteThreshold = ColdCallSiteThreshold;
@@ -1768,5 +1825,12 @@ static int computeThresholdFromOptLevels
}
InlineParams llvm::getInlineParams(unsigned OptLevel, unsigned SizeOptLevel) {
- return getInlineParams(computeThresholdFromOptLevels(OptLevel, SizeOptLevel));
+ auto Params =
+ getInlineParams(computeThresholdFromOptLevels(OptLevel, SizeOptLevel));
+ // At O3, use the value of -locally-hot-callsite-threshold option to populate
+ // Params.LocallyHotCallSiteThreshold. Below O3, this flag has effect only
+ // when it is specified explicitly.
+ if (OptLevel > 2)
+ Params.LocallyHotCallSiteThreshold = LocallyHotCallSiteThreshold;
+ return Params;
}
More information about the llvm-commits
mailing list