Make ICP uses PSI to check for hotness.

Summary: Currently, ICP checks the count against a fixed value to see if it is hot enough to be promoted. This does not work for SamplePGO because sampled count may be much smaller. This patch uses PSI to check if the count is hot enough to be promoted.

Reviewers: davidxl, tejohnson, eraman

Reviewed By: davidxl

Subscribers: sanjoy, llvm-commits, mehdi_amini

Differential Revision: https://reviews.llvm.org/D36341

llvm-svn: 310416

diff --git a/llvm/lib/Analysis/IndirectCallPromotionAnalysis.cpp b/llvm/lib/Analysis/IndirectCallPromotionAnalysis.cpp
index 62db61b..8f483df 100644 (file)
--- a/llvm/lib/Analysis/IndirectCallPromotionAnalysis.cpp
+++ b/llvm/lib/Analysis/IndirectCallPromotionAnalysis.cpp
@@ -32,14 +32,6 @@ using namespace llvm;
 
 #define DEBUG_TYPE "pgo-icall-prom-analysis"
 
-// The minimum call count for the direct-call target to be considered as the
-// promotion candidate.
-static cl::opt<unsigned>
-    ICPCountThreshold("icp-count-threshold", cl::Hidden, cl::ZeroOrMore,
-                      cl::init(1000),
-                      cl::desc("The minimum count to the direct call target "
-                               "for the promotion"));
-
 // The percent threshold for the direct-call target (this call site vs the
 // remaining call count) for it to be considered as the promotion target.
 static cl::opt<unsigned> ICPRemainingPercentThreshold(
@@ -69,8 +61,7 @@ ICallPromotionAnalysis::ICallPromotionAnalysis() {
 bool ICallPromotionAnalysis::isPromotionProfitable(uint64_t Count,
                                                    uint64_t TotalCount,
                                                    uint64_t RemainingCount) {
-  return Count >= ICPCountThreshold &&
-         Count * 100 >= ICPRemainingPercentThreshold * RemainingCount &&
+  return Count * 100 >= ICPRemainingPercentThreshold * RemainingCount &&
          Count * 100 >= ICPTotalPercentThreshold * TotalCount;
 }
 

diff --git a/llvm/lib/Transforms/Instrumentation/IndirectCallPromotion.cpp b/llvm/lib/Transforms/Instrumentation/IndirectCallPromotion.cpp
index abce36d..47e21bd 100644 (file)
--- a/llvm/lib/Transforms/Instrumentation/IndirectCallPromotion.cpp
+++ b/llvm/lib/Transforms/Instrumentation/IndirectCallPromotion.cpp
@@ -22,6 +22,7 @@
 #include "llvm/Analysis/IndirectCallPromotionAnalysis.h"
 #include "llvm/Analysis/IndirectCallSiteVisitor.h"
 #include "llvm/Analysis/OptimizationDiagnosticInfo.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
 #include "llvm/IR/BasicBlock.h"
 #include "llvm/IR/CallSite.h"
 #include "llvm/IR/DerivedTypes.h"
@@ -121,6 +122,10 @@ public:
         *PassRegistry::getPassRegistry());
   }
 
+  void getAnalysisUsage(AnalysisUsage &AU) const override {
+    AU.addRequired<ProfileSummaryInfoWrapperPass>();
+  }
+
   StringRef getPassName() const override { return "PGOIndirectCallPromotion"; }
 
 private:
@@ -194,7 +199,7 @@ public:
                      bool SamplePGO, OptimizationRemarkEmitter &ORE)
       : F(Func), M(Modu), Symtab(Symtab), SamplePGO(SamplePGO), ORE(ORE) {}
 
-  bool processFunction();
+  bool processFunction(ProfileSummaryInfo *PSI);
 };
 } // end anonymous namespace
 
@@ -613,7 +618,7 @@ uint32_t ICallPromotionFunc::tryToPromote(
 
 // Traverse all the indirect-call callsite and get the value profile
 // annotation to perform indirect-call promotion.
-bool ICallPromotionFunc::processFunction() {
+bool ICallPromotionFunc::processFunction(ProfileSummaryInfo *PSI) {
   bool Changed = false;
   ICallPromotionAnalysis ICallAnalysis;
   for (auto &I : findIndirectCallSites(F)) {
@@ -621,7 +626,8 @@ bool ICallPromotionFunc::processFunction() {
     uint64_t TotalCount;
     auto ICallProfDataRef = ICallAnalysis.getPromotionCandidatesForInstruction(
         I, NumVals, TotalCount, NumCandidates);
-    if (!NumCandidates)
+    if (!NumCandidates ||
+        (PSI && PSI->hasProfileSummary() && !PSI->isHotCount(TotalCount)))
       continue;
     auto PromotionCandidates = getPromotionCandidatesForCallSite(
         I, ICallProfDataRef, TotalCount, NumCandidates);
@@ -643,7 +649,8 @@ bool ICallPromotionFunc::processFunction() {
 }
 
 // A wrapper function that does the actual work.
-static bool promoteIndirectCalls(Module &M, bool InLTO, bool SamplePGO,
+static bool promoteIndirectCalls(Module &M, ProfileSummaryInfo *PSI,
+                                 bool InLTO, bool SamplePGO,
                                  ModuleAnalysisManager *AM = nullptr) {
   if (DisableICP)
     return false;
@@ -673,7 +680,7 @@ static bool promoteIndirectCalls(Module &M, bool InLTO, bool SamplePGO,
     }
 
     ICallPromotionFunc ICallPromotion(F, &M, &Symtab, SamplePGO, *ORE);
-    bool FuncChanged = ICallPromotion.processFunction();
+    bool FuncChanged = ICallPromotion.processFunction(PSI);
     if (ICPDUMPAFTER && FuncChanged) {
       DEBUG(dbgs() << "\n== IR Dump After =="; F.print(dbgs()));
       DEBUG(dbgs() << "\n");
@@ -688,15 +695,20 @@ static bool promoteIndirectCalls(Module &M, bool InLTO, bool SamplePGO,
 }
 
 bool PGOIndirectCallPromotionLegacyPass::runOnModule(Module &M) {
+  ProfileSummaryInfo *PSI =
+      getAnalysis<ProfileSummaryInfoWrapperPass>().getPSI();
+
   // Command-line option has the priority for InLTO.
-  return promoteIndirectCalls(M, InLTO | ICPLTOMode,
+  return promoteIndirectCalls(M, PSI, InLTO | ICPLTOMode,
                               SamplePGO | ICPSamplePGOMode);
 }
 
 PreservedAnalyses PGOIndirectCallPromotion::run(Module &M,
                                                 ModuleAnalysisManager &AM) {
-  if (!promoteIndirectCalls(M, InLTO | ICPLTOMode, SamplePGO | ICPSamplePGOMode,
-                            &AM))
+  ProfileSummaryInfo *PSI = &AM.getResult<ProfileSummaryAnalysis>(M);
+
+  if (!promoteIndirectCalls(M, PSI, InLTO | ICPLTOMode,
+                            SamplePGO | ICPSamplePGOMode, &AM))
     return PreservedAnalyses::all();
 
   return PreservedAnalyses::none();

diff --git a/llvm/test/Other/new-pm-lto-defaults.ll b/llvm/test/Other/new-pm-lto-defaults.ll
index a474559..e450a8e 100644 (file)
--- a/llvm/test/Other/new-pm-lto-defaults.ll
+++ b/llvm/test/Other/new-pm-lto-defaults.ll
@@ -30,6 +30,7 @@
 ; CHECK-O-NEXT: Running pass: InferFunctionAttrsPass
 ; CHECK-O-NEXT: Running analysis: TargetLibraryAnalysis
 ; CHECK-O2-NEXT: PGOIndirectCallPromotion
+; CHECK-O2-NEXT: Running analysis: ProfileSummaryAnalysis
 ; CHECK-O2-NEXT: Running analysis: InnerAnalysisManagerProxy<{{.*}}Function
 ; CHECK-O2-NEXT: Running analysis: OptimizationRemarkEmitterAnalysis
 ; CHECK-O2-NEXT: Running pass: IPSCCPPass

diff --git a/llvm/test/Transforms/PGOProfile/icp_invoke.ll b/llvm/test/Transforms/PGOProfile/icp_invoke.ll
index a6bf5a8..2ec5646 100644 (file)
--- a/llvm/test/Transforms/PGOProfile/icp_invoke.ll
+++ b/llvm/test/Transforms/PGOProfile/icp_invoke.ll
@@ -1,5 +1,5 @@
-; RUN: opt < %s -icp-lto -pgo-icall-prom -S -icp-count-threshold=0 | FileCheck %s --check-prefix=ICP
-; RUN: opt < %s -icp-lto -passes=pgo-icall-prom -S -icp-count-threshold=0 | FileCheck %s --check-prefix=ICP
+; RUN: opt < %s -icp-lto -pgo-icall-prom -S | FileCheck %s --check-prefix=ICP
+; RUN: opt < %s -icp-lto -passes=pgo-icall-prom -S | FileCheck %s --check-prefix=ICP
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 

diff --git a/llvm/test/Transforms/PGOProfile/indirect_call_promotion.ll b/llvm/test/Transforms/PGOProfile/indirect_call_promotion.ll
index 3a8206e..6832fec 100644 (file)
--- a/llvm/test/Transforms/PGOProfile/indirect_call_promotion.ll
+++ b/llvm/test/Transforms/PGOProfile/indirect_call_promotion.ll
@@ -1,10 +1,9 @@
-; RUN: opt < %s -pgo-icall-prom -S | FileCheck %s --check-prefix=ICALL-PROM
-; RUN: opt < %s -pgo-icall-prom -S -icp-samplepgo | FileCheck %s --check-prefix=ICALL-PROM
-; RUN: opt < %s -pgo-icall-prom -S -icp-samplepgo | FileCheck %s --check-prefix=ICALL-PROM-SAMPLEPGO
-; RUN: opt < %s -passes=pgo-icall-prom -S | FileCheck %s --check-prefix=ICALL-PROM
-; RUN: opt < %s -pgo-icall-prom -S -pass-remarks=pgo-icall-prom -icp-count-threshold=0 -icp-remaining-percent-threshold=0 -icp-total-percent-threshold=0 -icp-max-prom=4 2>&1 | FileCheck %s --check-prefix=PASS-REMARK
-; RUN: opt < %s -passes=pgo-icall-prom -S -pass-remarks=pgo-icall-prom -icp-count-threshold=0 -icp-remaining-percent-threshold=0 -icp-total-percent-threshold=0 -icp-max-prom=4 2>&1 | FileCheck %s --check-prefix=PASS-REMARK
-; RUN: opt < %s -passes=pgo-icall-prom -S -pass-remarks=pgo-icall-prom -icp-count-threshold=0 -icp-remaining-percent-threshold=0 -icp-total-percent-threshold=20 -icp-max-prom=4 2>&1 | FileCheck %s --check-prefix=PASS2-REMARK
+; RUN: opt < %s -pgo-icall-prom -S -icp-total-percent-threshold=50 | FileCheck %s --check-prefix=ICALL-PROM
+; RUN: opt < %s -pgo-icall-prom -S -icp-samplepgo -icp-total-percent-threshold=50 | FileCheck %s --check-prefix=ICALL-PROM
+; RUN: opt < %s -passes=pgo-icall-prom -S -icp-total-percent-threshold=50 | FileCheck %s --check-prefix=ICALL-PROM
+; RUN: opt < %s -pgo-icall-prom -S -pass-remarks=pgo-icall-prom -icp-remaining-percent-threshold=0 -icp-total-percent-threshold=0 -icp-max-prom=4 2>&1 | FileCheck %s --check-prefix=PASS-REMARK
+; RUN: opt < %s -passes=pgo-icall-prom -S -pass-remarks=pgo-icall-prom -icp-remaining-percent-threshold=0 -icp-total-percent-threshold=0 -icp-max-prom=4 2>&1 | FileCheck %s --check-prefix=PASS-REMARK
+; RUN: opt < %s -passes=pgo-icall-prom -S -pass-remarks=pgo-icall-prom -icp-remaining-percent-threshold=0 -icp-total-percent-threshold=20 -icp-max-prom=4 2>&1 | FileCheck %s --check-prefix=PASS2-REMARK
 
 ; PASS-REMARK: remark: <unknown>:0:0: Promote indirect call to func4 with count 1030 out of 1600
 ; PASS-REMARK: remark: <unknown>:0:0: Promote indirect call to func2 with count 410 out of 570

diff --git a/llvm/test/Transforms/PGOProfile/thinlto_indirect_call_promotion.ll b/llvm/test/Transforms/PGOProfile/thinlto_indirect_call_promotion.ll
index 01f458a..6d928ea 100644 (file)
--- a/llvm/test/Transforms/PGOProfile/thinlto_indirect_call_promotion.ll
+++ b/llvm/test/Transforms/PGOProfile/thinlto_indirect_call_promotion.ll
@@ -7,8 +7,8 @@
 ; IMPORTS-DAG: Import a
 ; IMPORTS-DAG: Import c
 
-; RUN: opt %t4.bc -icp-lto -pgo-icall-prom -S -icp-count-threshold=1 | FileCheck %s --check-prefix=ICALL-PROM
-; RUN: opt %t4.bc -icp-lto -pgo-icall-prom -S -pass-remarks=pgo-icall-prom -icp-count-threshold=1 2>&1 | FileCheck %s --check-prefix=PASS-REMARK
+; RUN: opt %t4.bc -icp-lto -pgo-icall-prom -S | FileCheck %s --check-prefix=ICALL-PROM
+; RUN: opt %t4.bc -icp-lto -pgo-icall-prom -S -pass-remarks=pgo-icall-prom 2>&1 | FileCheck %s --check-prefix=PASS-REMARK
 ; PASS-REMARK: Promote indirect call to a with count 1 out of 1
 ; PASS-REMARK: Promote indirect call to c.llvm.0 with count 1 out of 1
 

diff --git a/llvm/test/Transforms/PGOProfile/thinlto_samplepgo_icp.ll b/llvm/test/Transforms/PGOProfile/thinlto_samplepgo_icp.ll
index dfb6816..b6b668d 100644 (file)
--- a/llvm/test/Transforms/PGOProfile/thinlto_samplepgo_icp.ll
+++ b/llvm/test/Transforms/PGOProfile/thinlto_samplepgo_icp.ll
@@ -7,7 +7,7 @@
 ; by ICP. Note that the GUID in the profile is from the oroginal name.
 ; RUN: opt -function-import -summary-file %t3.thinlto.bc %t.bc -o %t4.bc -print-imports 2>&1 | FileCheck %s --check-prefix=IMPORTS
 ; IMPORTS: Import _ZL3foov.llvm.0
-; RUN: opt %t4.bc -icp-lto -pgo-icall-prom -S -icp-count-threshold=1 | FileCheck %s --check-prefix=ICALL-PROM
+; RUN: opt %t4.bc -icp-lto -pgo-icall-prom -S | FileCheck %s --check-prefix=ICALL-PROM
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"