[AutoFDO] Use getHeadSamplesEstimate instead of getTotalSamples to compute profile...

Fix two issues for profile staleness report.

1) It should be more accurate to use the sum of all entry count(`getHeadSamplesEstimate`) for the callsite samples than the total samples, since even the top-level callsite is mismatched, it does affect the inlining but it can still be merged into base profile and used later.

2) I accidentally missed to persist the num of mismatched callsite into binary.

Also added the asm testing to test the decoding of the section.

Reviewed By: hoy, wenlei

Differential Revision: https://reviews.llvm.org/D140063

diff --git a/llvm/lib/Transforms/IPO/SampleProfile.cpp b/llvm/lib/Transforms/IPO/SampleProfile.cpp
index df5f91b..2c18b26 100644 (file)
--- a/llvm/lib/Transforms/IPO/SampleProfile.cpp
+++ b/llvm/lib/Transforms/IPO/SampleProfile.cpp
@@ -430,8 +430,8 @@ class SampleProfileMatcher {
   const PseudoProbeManager *ProbeManager;
 
   // Profile mismatching statstics.
-  uint64_t TotalProfiledCallsite = 0;
-  uint64_t NumMismatchedCallsite = 0;
+  uint64_t TotalProfiledCallsites = 0;
+  uint64_t NumMismatchedCallsites = 0;
   uint64_t MismatchedCallsiteSamples = 0;
   uint64_t TotalCallsiteSamples = 0;
   uint64_t TotalProfiledFunc = 0;
@@ -2119,10 +2119,10 @@ void SampleProfileMatcher::detectProfileMismatch(const Function &F,
     uint64_t Count = I.second.getSamples();
     if (!I.second.getCallTargets().empty()) {
       TotalCallsiteSamples += Count;
-      TotalProfiledCallsite++;
+      TotalProfiledCallsites++;
       if (!MatchedCallsiteLocs.count(Loc)) {
         MismatchedCallsiteSamples += Count;
-        NumMismatchedCallsite++;
+        NumMismatchedCallsites++;
       }
     }
   }
@@ -2134,13 +2134,13 @@ void SampleProfileMatcher::detectProfileMismatch(const Function &F,
 
     uint64_t Count = 0;
     for (auto &FM : I.second) {
-      Count += FM.second.getTotalSamples();
+      Count += FM.second.getHeadSamplesEstimate();
     }
     TotalCallsiteSamples += Count;
-    TotalProfiledCallsite++;
+    TotalProfiledCallsites++;
     if (!MatchedCallsiteLocs.count(Loc)) {
       MismatchedCallsiteSamples += Count;
-      NumMismatchedCallsite++;
+      NumMismatchedCallsites++;
     }
   }
 }
@@ -2163,7 +2163,7 @@ void SampleProfileMatcher::detectProfileMismatch() {
              << ")"
              << " of samples are discarded due to function hash mismatch.\n";
     }
-    errs() << "(" << NumMismatchedCallsite << "/" << TotalProfiledCallsite
+    errs() << "(" << NumMismatchedCallsites << "/" << TotalProfiledCallsites
            << ")"
            << " of callsites' profile are invalid and "
            << "(" << MismatchedCallsiteSamples << "/" << TotalCallsiteSamples
@@ -2183,6 +2183,9 @@ void SampleProfileMatcher::detectProfileMismatch() {
                                 MismatchedFuncHashSamples);
       ProfStatsVec.emplace_back("TotalFuncHashSamples", TotalFuncHashSamples);
     }
+
+    ProfStatsVec.emplace_back("NumMismatchedCallsites", NumMismatchedCallsites);
+    ProfStatsVec.emplace_back("TotalProfiledCallsites", TotalProfiledCallsites);
     ProfStatsVec.emplace_back("MismatchedCallsiteSamples",
                               MismatchedCallsiteSamples);
     ProfStatsVec.emplace_back("TotalCallsiteSamples", TotalCallsiteSamples);

diff --git a/llvm/test/Transforms/SampleProfile/profile-mismatch.ll b/llvm/test/Transforms/SampleProfile/profile-mismatch.ll
index 8d6d13d..cf07974 100644 (file)
--- a/llvm/test/Transforms/SampleProfile/profile-mismatch.ll
+++ b/llvm/test/Transforms/SampleProfile/profile-mismatch.ll
@@ -4,13 +4,32 @@
 ; RUN: FileCheck %s --input-file %t.ll -check-prefix=CHECK-MD
 ; RUN: llc < %t.ll -filetype=obj -o %t.obj
 ; RUN: llvm-objdump --section-headers %t.obj | FileCheck %s --check-prefix=CHECK-OBJ
+; RUN: llc < %t.ll -filetype=asm -o - | FileCheck %s --check-prefix=CHECK-ASM
 
-; CHECK: (2/3) of callsites' profile are invalid and (20/30) of samples are discarded due to callsite location mismatch.
+; CHECK: (2/3) of callsites' profile are invalid and (15/25) of samples are discarded due to callsite location mismatch.
 
-; CHECK-MD: ![[#]] = !{!"MismatchedCallsiteSamples", i64 20, !"TotalCallsiteSamples", i64 30}
+; CHECK-MD: ![[#]] = !{!"NumMismatchedCallsites", i64 2, !"TotalProfiledCallsites", i64 3, !"MismatchedCallsiteSamples", i64 15, !"TotalCallsiteSamples", i64 25}
 
 ; CHECK-OBJ: .llvm_stats
 
+; CHECK-ASM: .section  .llvm_stats,"",@progbits
+; CHECK-ASM: .byte 22
+; CHECK-ASM: .ascii  "NumMismatchedCallsites"
+; CHECK-ASM: .byte 4
+; CHECK-ASM: .ascii  "Mg=="
+; CHECK-ASM: .byte 22
+; CHECK-ASM: .ascii  "TotalProfiledCallsites"
+; CHECK-ASM: .byte 4
+; CHECK-ASM: .ascii  "Mw=="
+; CHECK-ASM: .byte 25
+; CHECK-ASM: .ascii  "MismatchedCallsiteSamples"
+; CHECK-ASM: .byte 4
+; CHECK-ASM: .ascii  "MTU="
+; CHECK-ASM: .byte 20
+; CHECK-ASM: .ascii  "TotalCallsiteSamples"
+; CHECK-ASM: .byte 4
+; CHECK-ASM: .ascii  "MjU="
+
 target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"
 

diff --git a/llvm/test/Transforms/SampleProfile/pseudo-probe-profile-mismatch.ll b/llvm/test/Transforms/SampleProfile/pseudo-probe-profile-mismatch.ll
index ad88fa0..ee492b8 100644 (file)
--- a/llvm/test/Transforms/SampleProfile/pseudo-probe-profile-mismatch.ll
+++ b/llvm/test/Transforms/SampleProfile/pseudo-probe-profile-mismatch.ll
@@ -4,14 +4,49 @@
 ; RUN: FileCheck %s --input-file %t.ll -check-prefix=CHECK-MD
 ; RUN: llc < %t.ll -filetype=obj -o %t.obj
 ; RUN: llvm-objdump --section-headers %t.obj | FileCheck %s --check-prefix=CHECK-OBJ
+; RUN: llc < %t.ll -filetype=asm -o - | FileCheck %s --check-prefix=CHECK-ASM
 
 ; CHECK: (1/3) of functions' profile are invalid and (10/50) of samples are discarded due to function hash mismatch.
 ; CHECK: (2/3) of callsites' profile are invalid and (20/30) of samples are discarded due to callsite location mismatch.
 
-; CHECK-MD: ![[#]] = !{!"NumMismatchedFuncHash", i64 1, !"TotalProfiledFunc", i64 3, !"MismatchedFuncHashSamples", i64 10, !"TotalFuncHashSamples", i64 50, !"MismatchedCallsiteSamples", i64 20, !"TotalCallsiteSamples", i64 30}
+; CHECK-MD: ![[#]] = !{!"NumMismatchedFuncHash", i64 1, !"TotalProfiledFunc", i64 3, !"MismatchedFuncHashSamples", i64 10, !"TotalFuncHashSamples", i64 50, !"NumMismatchedCallsites", i64 2, !"TotalProfiledCallsites", i64 3, !"MismatchedCallsiteSamples", i64 20, !"TotalCallsiteSamples", i64 30}
 
 ; CHECK-OBJ: .llvm_stats
 
+; CHECK-ASM: .section  .llvm_stats,"",@progbits
+; CHECK-ASM: .byte 21
+; CHECK-ASM: .ascii  "NumMismatchedFuncHash"
+; CHECK-ASM: .byte 4
+; CHECK-ASM: .ascii  "MQ=="
+; CHECK-ASM: .byte 17
+; CHECK-ASM: .ascii  "TotalProfiledFunc"
+; CHECK-ASM: .byte 4
+; CHECK-ASM: .ascii  "Mw=="
+; CHECK-ASM: .byte 25
+; CHECK-ASM: .ascii  "MismatchedFuncHashSamples"
+; CHECK-ASM: .byte 4
+; CHECK-ASM: .ascii  "MTA="
+; CHECK-ASM: .byte 20
+; CHECK-ASM: .ascii  "TotalFuncHashSamples"
+; CHECK-ASM: .byte 4
+; CHECK-ASM: .ascii  "NTA="
+; CHECK-ASM: .byte 22
+; CHECK-ASM: .ascii  "NumMismatchedCallsites"
+; CHECK-ASM: .byte 4
+; CHECK-ASM: .ascii  "Mg=="
+; CHECK-ASM: .byte 22
+; CHECK-ASM: .ascii  "TotalProfiledCallsites"
+; CHECK-ASM: .byte 4
+; CHECK-ASM: .ascii  "Mw=="
+; CHECK-ASM: .byte 25
+; CHECK-ASM: .ascii  "MismatchedCallsiteSamples"
+; CHECK-ASM: .byte 4
+; CHECK-ASM: .ascii  "MjA="
+; CHECK-ASM: .byte 20
+; CHECK-ASM: .ascii  "TotalCallsiteSamples"
+; CHECK-ASM: .byte 4
+; CHECK-ASM: .ascii  "MzA="
+
 target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-linux-gnu"