[llvm-profgen] Update total samples by accumulating all its body samples

[wlei]

Summary

Like probe-based profile, the total samples is the sum of all its body samples. This patch fix it by a post-processing update for the line-number based profile. Tested it on our internal services, results showed no performance change.

[wenlei]

lgtm, except a nit. thanks.

llvm/include/llvm/ProfileData/SampleProf.h

735

nit: inferTotalSamples->updateTotalSamples, same for ProfileGenerator.

[wlei]

rename inferTotalSamples->updateTotalSamples

[wlei]

clean up all the redundant "addTotalSamples"

[hoy]

LGTM, thanks.

[wlei]

rebase

llvm/include/llvm/ProfileData/SampleProf.h

public:
 
   sampleprof_error addBodySamplesForProbe(uint32_t Index, uint64_t Num,
                                           uint64_t Weight = 1) {
     SampleRecord S;
     S.addSamples(Num, Weight);
     return BodySamples[LineLocation(Index, 0)].merge(S, Weight);
   }
 
+  // Accumulate all body samples to set total samples.
+  void updateTotalSamples() {
+    setTotalSamples(0);
+    for (const auto &I : BodySamples)
+      addTotalSamples(I.second.getSamples());
+
+    for (auto &I : CallsiteSamples) {
+      for (auto &CS : I.second) {
+        CS.second.updateTotalSamples();
+        addTotalSamples(CS.second.getTotalSamples());
+      }
+    }
+  }
+
   /// Return the number of samples collected at the given location.
   /// Each location is specified by \p LineOffset and \p Discriminator.
   /// If the location is not found in profile, return error.
   ErrorOr<uint64_t> findSamplesAt(uint32_t LineOffset,
                                   uint32_t Discriminator) const {
     const auto &ret = BodySamples.find(LineLocation(LineOffset, Discriminator));
     if (ret == BodySamples.end())
       return std::error_code();

llvm/test/tools/llvm-profgen/coroutine.test

 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/coroutine.perfscript --binary=%S/Inputs/coroutine.perfbin --output=%t
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK
 
 ; Check that the head sample count for ticker is 0.
-; CHECK: _Z6tickeri:353:0
+; CHECK: _Z6tickeri:67:0
 ; CHECK-NOT: _Z6tickeri.resume
 
 
 /*
  * Inputs/coroutine.perfbin is generated by compiling the following source code:
  * clang++ coroutine.cpp -std=c++2a -g2 -o coroutine
  */
 

llvm/test/tools/llvm-profgen/cs-interrupt.test

 ;; The test fails on Windows. Fix it before removing the following requirement.
 ; REQUIRES: x86_64-linux
 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/cs-interrupt.perfscript --binary=%S/Inputs/noinline-cs-noprobe.perfbin --output=%t --skip-symbolization --profile-summary-cold-count=0
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-UNWINDER
 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/cs-interrupt.perfscript --binary=%S/Inputs/noinline-cs-noprobe.perfbin --output=%t --profile-summary-cold-count=0
 >>>>>>> 02ea7084c370 ([llvm-profgen] Support LBR only perf script)
 ; RUN: FileCheck %s --input-file %t
 
-; CHECK:[main:1 @ foo]:88:0
-; CHECK: 2: 5
-; CHECK: 3: 5 bar:5
-; CHECK:[main:1 @ foo:3 @ bar]:74:5
+; CHECK:[main:1 @ foo:3 @ bar]:17:5
 ; CHECK: 0: 5
 ; CHECK: 1: 5
 ; CHECK: 2: 3
 ; CHECK: 5: 4
+; CHECK:[main:1 @ foo]:10:0
+; CHECK: 2: 5
+; CHECK: 3: 5 bar:5
 
 ; CHECK-UNWINDER:      [main:1 @ foo]
 ; CHECK-UNWINDER-NEXT:   3
 ; CHECK-UNWINDER-NEXT:   5ff-62f:5
 ; CHECK-UNWINDER-NEXT:   634-637:4
 ; CHECK-UNWINDER-NEXT:   645-645:5
 ; CHECK-UNWINDER-NEXT:   3
 ; CHECK-UNWINDER-NEXT:   62f->5b0:5

llvm/test/tools/llvm-profgen/cs-preinline.test

 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/inline-cs-noprobe.perfscript --binary=%S/Inputs/inline-cs-noprobe.perfbin --output=%t --csspgo-preinliner=1  -sample-profile-cold-inline-threshold=0
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-NO-PREINL
 
 ; Test cold profile trimming. Only base profiles should be dropped.
 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/inline-cs-noprobe.perfscript --binary=%S/Inputs/inline-cs-noprobe.perfbin --output=%t --csspgo-preinliner=1  --csprof-trim-cold-context=1 --profile-summary-hot-count=250
 
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-TRIM
 
-; CHECK-DEFAULT:     [main:1 @ foo]:225:0
+; CHECK-DEFAULT:     [main:1 @ foo]:44:0
 ; CHECK-DEFAULT-NEXT: 2.1: 14
 ; CHECK-DEFAULT-NEXT: 3: 15
 ; CHECK-DEFAULT-NEXT: 3.1: 14 bar:14
 ; CHECK-DEFAULT-NEXT: 3.2: 1
 ; CHECK-DEFAULT-NEXT: !Attributes: 1
-; CHECK-DEFAULT-NEXT:[main:1 @ foo:3.1 @ bar]:84:0
+; CHECK-DEFAULT-NEXT:[main:1 @ foo:3.1 @ bar]:14:0
 ; CHECK-DEFAULT-NEXT: 1: 14
 ; CHECK-DEFAULT-NEXT: !Attributes: 1
 
-; CHECK-PREINL:     [foo]:225:0
+; CHECK-PREINL:     [foo]:44:0
 ; CHECK-PREINL-NEXT: 2.1: 14
 ; CHECK-PREINL-NEXT: 3: 15
 ; CHECK-PREINL-NEXT: 3.1: 14 bar:14
 ; CHECK-PREINL-NEXT: 3.2: 1
 ; CHECK-PREINL-NEXT: !Attributes: 1
-; CHECK-PREINL-NEXT:[foo:3.1 @ bar]:84:0
+; CHECK-PREINL-NEXT:[foo:3.1 @ bar]:14:0
 ; CHECK-PREINL-NEXT: 1: 14
 ; CHECK-PREINL-NEXT: !Attributes: 3
 
-; CHECK-NO-PREINL:     [foo]:225:0
+; CHECK-NO-PREINL:     [foo]:44:0
 ; CHECK-NO-PREINL-NEXT: 2.1: 14
 ; CHECK-NO-PREINL-NEXT: 3: 15
 ; CHECK-NO-PREINL-NEXT: 3.1: 14 bar:14
 ; CHECK-NO-PREINL-NEXT: 3.2: 1
 ; CHECK-NO-PREINL-NEXT: !Attributes: 1
-; CHECK-NO-PREINL-NEXT:[bar]:84:0
+; CHECK-NO-PREINL-NEXT:[bar]:14:0
 ; CHECK-NO-PREINL-NEXT: 1: 14
 ; CHECK-NO-PREINL-NEXT: !Attributes: 1
 
-; CHECK-TRIM-NOT: [foo]:225:0
-; CHECK-TRIM:[foo:3.1 @ bar]:84:0
+; CHECK-TRIM-NOT: [foo]
+; CHECK-TRIM:[foo:3.1 @ bar]:14:0
 ; CHECK-TRIM-NEXT: 1: 14
 ; CHECK-TRIM-NEXT: !Attributes: 3

llvm/test/tools/llvm-profgen/fname-canonicalization.test

 ; Test unique linkage name decoding and canonicalization from dwarf debug info
 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/unique-linkage-name-dwarf.perfscript --binary=%S/Inputs/unique-linkage-name-dwarf.perfbin --output=%t --profile-summary-cold-count=0
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-DWARF-FNAME
 
-; CHECK-DWARF-FNAME:[main:1 @ foo]:225:0
+; CHECK-DWARF-FNAME:[main:1 @ foo]:43:0
 ; CHECK-DWARF-FNAME: 2: 14
 ; CHECK-DWARF-FNAME: 3: 29 bar.__uniq.26267048767521081047744692097241227776:14
-; CHECK-DWARF-FNAME:[main:1 @ foo:3 @ bar.__uniq.26267048767521081047744692097241227776]:84:0
+; CHECK-DWARF-FNAME:[main:1 @ foo:3 @ bar.__uniq.26267048767521081047744692097241227776]:14:0
 ; CHECK-DWARF-FNAME: 1: 14
 
 
 ; Test unique linkage name decoding and canonicalization from pseudo probe info
 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/unique-linkage-name-probe.perfscript --binary=%S/Inputs/unique-linkage-name-probe.perfbin --output=%t --profile-summary-cold-count=0
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-PROBE-FNAME
 
 ; CHECK-PROBE-FNAME:[main:2 @ foo]:75:0

llvm/test/tools/llvm-profgen/func-split.test

 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/func-split.perfscript --binary=%S/Inputs/func-split.perfbin --output=%t
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK
 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/func-split.perfscript --binary=%S/Inputs/func-split.perfbin --output=%t --ignore-stack-samples
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-STRIP-CTX
 
-;CHECK: [foo]:408:0
+;CHECK: [foo]:82:0
 ;CHECK:  2.1: 27
 ;CHECK:  3: 27
 ;CHECK:  3.1: 2 bar:2
 ;CHECK:  3.2: 26
-;CHECK: [foo:3.1 @ bar]:8:0
+;CHECK: [foo:3.1 @ bar]:2:0
 ;CHECK:  1: 1
 ;CHECK:  5: 1
 ;CHECK: [bar]:0:1
 
 ;CHECK-NOT: foo.cold
 
-;CHECK-STRIP-CTX: foo:408:0
+;CHECK-STRIP-CTX: foo:81:0
 ;CHECK-STRIP-CTX:  0: 0
 ;CHECK-STRIP-CTX:  2.1: 27
 ;CHECK-STRIP-CTX:  3: 27
 ;CHECK-STRIP-CTX:  3.1: 1 bar:1
 ;CHECK-STRIP-CTX:  3.2: 26
 ;CHECK-STRIP-CTX:  4: 0
-;CHECK-STRIP-CTX: bar:8:1
+;CHECK-STRIP-CTX: bar:2:1
 ;CHECK-STRIP-CTX:  1: 1
 ;CHECK-STRIP-CTX:  5: 1
 
 ;CHECK-STRIP-CTX-NOT: foo.cold
 
 
 ; clang -g -O3 -fdebug-info-for-profiling func-split.c -mllvm -mfs-count-threshold=0
 ; -fprofile-sample-use=profile.txt -fno-inline -mllvm --enable-split-machine-functions=1

llvm/test/tools/llvm-profgen/inline-cs-noprobe.test

 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/inline-cs-noprobe.perfscript --binary=%S/Inputs/inline-cs-noprobe.perfbin --output=%t --skip-symbolization --profile-summary-cold-count=0
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-UNWINDER
 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/inline-cs-noprobe.perfscript --binary=%S/Inputs/inline-cs-noprobe.perfbin --output=%t --profile-summary-cold-count=0
 ; RUN: FileCheck %s --input-file %t
 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/inline-cs-noprobe.perfscript --binary=%S/Inputs/inline-cs-noprobe.perfbin --output=%t --profile-summary-cold-count=0 --ignore-stack-samples
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-STRIP-CTX
 
 ; RUN: llvm-profgen --format=extbinary --perfscript=%S/Inputs/inline-cs-noprobe.perfscript --binary=%S/Inputs/inline-cs-noprobe.perfbin --output=%t --profile-summary-cold-count=0 --populate-profile-symbol-list=1
 ; RUN: llvm-profdata show -show-prof-sym-list -sample %t | FileCheck %s --check-prefix=CHECK-SYM-LIST
 
 ; CHECK-SYM-LIST: Dump profile symbol list
 ; CHECK-SYM-LIST: bar
 ; CHECK-SYM-LIST: foo
 ; CHECK-SYM-LIST: main
 
-; CHECK:[main:1 @ foo]:225:0
+; CHECK:[main:1 @ foo]:44:0
 ; CHECK: 2.1: 14
 ; CHECK: 3: 15
 ; CHECK: 3.1: 14 bar:14
 ; CHECK: 3.2: 1
-; CHECK:[main:1 @ foo:3.1 @ bar]:84:0
+; CHECK:[main:1 @ foo:3.1 @ bar]:14:0
 ; CHECK: 1: 14
 
 ; CHECK-UNWINDER: [main:1 @ foo]
 ; CHECK-UNWINDER:   3
 ; CHECK-UNWINDER:   670-69b:1
 ; CHECK-UNWINDER:   67e-69b:14
 ; CHECK-UNWINDER:   6bf-6c8:14
 ; CHECK-UNWINDER:   2
 ; CHECK-UNWINDER:   69b->670:1
 ; CHECK-UNWINDER:   6c8->67e:15
 ; CHECK-UNWINDER: [main:1 @ foo:3.1 @ bar]
 ; CHECK-UNWINDER:   1
 ; CHECK-UNWINDER:   6af-6bb:14
 ; CHECK-UNWINDER:   0
 
-; CHECK-STRIP-CTX: main:295:0
+; CHECK-STRIP-CTX: main:44:0
 ; CHECK-STRIP-CTX:  0: 0
 ; CHECK-STRIP-CTX:  2: 0
-; CHECK-STRIP-CTX:  1: foo:295
+; CHECK-STRIP-CTX:  1: foo:44
 ; CHECK-STRIP-CTX:   2.1: 14
 ; CHECK-STRIP-CTX:   3: 15
 ; CHECK-STRIP-CTX:   3.2: 1
 ; CHECK-STRIP-CTX:   4: 0
 ; CHECK-STRIP-CTX:   7: 0
-; CHECK-STRIP-CTX:   3.1: bar:84
+; CHECK-STRIP-CTX:   3.1: bar:14
 ; CHECK-STRIP-CTX:    1: 14
 
 ; original code:
 ; clang -O3 -g test.c -o a.out
 #include <stdio.h>
 
 int bar(int x, int y) {
   if (x % 3) {

llvm/test/tools/llvm-profgen/inline-force-dwarf.test

 ; RUN: llvm-profgen --format=text --ignore-stack-samples --use-dwarf-correlation --perfscript=%S/Inputs/inline-cs-pseudoprobe.perfscript --binary=%S/Inputs/inline-cs-pseudoprobe.perfbin --output=%t --profile-summary-cold-count=0
 ; RUN: FileCheck %s --input-file %t
 
-; CHECK:     main:295:0
+; CHECK:     main:43:0
 ; CHECK-NEXT: 0: 0
 ; CHECK-NEXT: 2: 0
-; CHECK-NEXT: 1: foo:295
+; CHECK-NEXT: 1: foo:43
 ; CHECK-NEXT:  2: 14
 ; CHECK-NEXT:  3: 15
 ; CHECK-NEXT:  4: 0
-; CHECK-NEXT:  3: bar:84
+; CHECK-NEXT:  3: bar:14
 ; CHECK-NEXT:   1: 14
 
 
 ; clang -O3 -fexperimental-new-pass-manager -fuse-ld=lld -fpseudo-probe-for-profiling
 ; -fno-omit-frame-pointer -mno-omit-leaf-frame-pointer -Xclang -mdisable-tail-calls
 ; -g test.c  -o a.out
 
 #include <stdio.h>

llvm/test/tools/llvm-profgen/inline-noprobe.test

 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/inline-noprobe.perfscript --binary=%S/Inputs/inline-noprobe.perfbin --output=%t --skip-symbolization
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-RAW-PROFILE
 ; RUN: llvm-profgen --format=text --use-dwarf-correlation --perfscript=%S/Inputs/inline-noprobe.perfscript --binary=%S/Inputs/inline-noprobe.perfbin --output=%t --skip-symbolization
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-RAW-PROFILE
 ; RUN: llvm-profgen --format=text --unsymbolized-profile=%t --binary=%S/Inputs/inline-noprobe.perfbin --output=%t1
 ; RUN: FileCheck %s --input-file %t1 --check-prefix=CHECK
 ; RUN: llvm-profgen --format=text --use-dwarf-correlation --perfscript=%S/Inputs/inline-noprobe.perfscript --binary=%S/Inputs/inline-noprobe.perfbin --output=%t
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK
 
-CHECK: main:669:0
+CHECK: main:188:0
 CHECK:  0: 0
 CHECK:  2: 0
-CHECK:  1: foo:669
+CHECK:  1: foo:188
 CHECK:   2.1: 42
 CHECK:   3: 62
 CHECK:   3.2: 21
 CHECK:   4: 0
-CHECK:   3.1: bar:210
+CHECK:   3.1: bar:42
 CHECK:    1: 42
-CHECK:   3.2: bar:63
+CHECK:   3.2: bar:21
 CHECK:    1: 21
 
 CHECK-RAW-PROFILE:      3
 CHECK-RAW-PROFILE-NEXT: 650-691:21
 CHECK-RAW-PROFILE-NEXT: 669-677:20
 CHECK-RAW-PROFILE-NEXT: 669-691:21
 CHECK-RAW-PROFILE-NEXT: 2
 CHECK-RAW-PROFILE-NEXT: 677->650:21

llvm/test/tools/llvm-profgen/inline-noprobe2.test

 ; CHECK-SYM-LIST: partition_pivot_last
 ; CHECK-SYM-LIST: quick_sort
 ; CHECK-SYM-LIST: swap
 
 
 ;CHECK-RAW-PROFILE-NOT: 7f7448e889e4
 ;CHECK-RAW-PROFILE-NOT: 7f7448e88826
 
-;CHECK:       partition_pivot_first:1045:5
+;CHECK:       partition_pivot_first:367:5
 ;CHECK-NEXT:  0: 5
 ;CHECK-NEXT:  1: 5
 ;CHECK-NEXT:  2: 5
 ;CHECK-NEXT:  3: 5
 ;CHECK-NEXT:  3.1: 83
 ;CHECK-NEXT:  4: 82
 ;CHECK-NEXT:  4.1: 26
 ;CHECK-NEXT:  4.2: 25
 ;CHECK-NEXT:  4.3: 26
 ;CHECK-NEXT:  5: 6
 ;CHECK-NEXT:  6: 6
-;CHECK-NEXT:  4.2: swap:100
+;CHECK-NEXT:  4.2: swap:75
 ;CHECK-NEXT:   1: 25
 ;CHECK-NEXT:   2: 25
 ;CHECK-NEXT:   3: 25
-;CHECK-NEXT:  5: swap:24
+;CHECK-NEXT:  5: swap:18
 ;CHECK-NEXT:   1: 6
 ;CHECK-NEXT:   2: 6
 ;CHECK-NEXT:   3: 6
-;CHECK-NEXT: partition_pivot_last:389:7
+;CHECK-NEXT: partition_pivot_last:225:7
 ;CHECK-NEXT:  1: 6
 ;CHECK-NEXT:  2: 6
 ;CHECK-NEXT:  3: 6
 
 ;w/o duplication factor :  3.1: 18
 ;w/o duplication factor :  3.3: 18
 ;w/o duplication factor :  4: 19
 ;w/o duplication factor :  5: 9
 ;CHECK-NEXT:  3.1: 36
 ;CHECK-NEXT:  3.3: 36
 ;CHECK-NEXT:  4: 38
 ;CHECK-NEXT:  5: 18
 
 ;CHECK-NEXT:  6: 5
 ;CHECK-NEXT:  7: 5
-;CHECK-NEXT:  5: swap:61
+;CHECK-NEXT:  5: swap:54
 
 ;w/o duplication factor :  1: 9
 ;w/o duplication factor :  2: 9
 ;w/o duplication factor :  3: 9
 ;CHECK-NEXT:   1: 18
 ;CHECK-NEXT:   2: 18
 ;CHECK-NEXT:   3: 18
 
-;CHECK-NEXT:  6: swap:20
+;CHECK-NEXT:  6: swap:15
 ;CHECK-NEXT:   1: 5
 ;CHECK-NEXT:   2: 5
 ;CHECK-NEXT:   3: 5
-;CHECK-NEXT: quick_sort:318:25
+;CHECK-NEXT: quick_sort:83:25
 ;CHECK-NEXT:  1: 24
 ;CHECK-NEXT:  2: 12 partition_pivot_last:7 partition_pivot_first:5
 ;CHECK-NEXT:  3: 11 quick_sort:12
 ;CHECK-NEXT:  4: 12 quick_sort:12
 ;CHECK-NEXT:  6: 24
-;CHECK-NEXT: main:213:0
+;CHECK-NEXT: main:52:0
 ;CHECK-NEXT:  0: 0
 ;CHECK-NEXT:  3: 0
 ;CHECK-NEXT:  4.1: 0
 ;CHECK-NEXT:  4.3: 0
 ;CHECK-NEXT:  5.1: 10
 ;CHECK-NEXT:  5.3: 10
 ;CHECK-NEXT:  6: 10
 ;CHECK-NEXT:  6.1: 12

llvm/test/tools/llvm-profgen/multi-load-segs.test

 ; RUN: llvm-profgen --perfscript=%S/Inputs/multi-load-segs.perfscript --binary=%S/Inputs/multi-load-segs.perfbin --output=%t --format=text
 ; RUN: FileCheck %s --input-file %t
 
 ;;  %S/Inputs/multi-load-segs.perfbin is an ELF image with two executable load segments.
 ; running llvm-readelf -l %S/Inputs/multi-load-segs.perfbin gives:
 ;;  LOAD           0x000000 0x0000000000200000 0x0000000000200000 0x00075c 0x00075c R   0x1000
 ;;  LOAD           0x000760 0x0000000000201760 0x0000000000201760 0x0004c0 0x0004c0 R E 0x1000
 ;;  LOAD           0x000c20 0x0000000000202c20 0x0000000000202c20 0x0001f0 0x0001f0 RW  0x1000
 ;;  LOAD           0x000e10 0x0000000000203e10 0x0000000000203e10 0x000040 0x000058 RW  0x1000
 ;;  LOAD           0x200000 0x0000000000400000 0x0000000000400000 0x0005e8 0x0005e8 R E 0x200000
 
-; CHECK:      [main:2 @ _Z10sort_arrayv:6 @ _Z11bubble_sortPii]:434:0
+; CHECK:      [main:2 @ _Z10sort_arrayv:6 @ _Z11bubble_sortPii]:124:0
 ; CHECK-NEXT:  4: 31
 ; CHECK-NEXT:  5: 31
 ; CHECK-NEXT:  7: 31
 ; CHECK-NEXT:  8: 31
 ; CHECK-NEXT:    !Attributes: 1

llvm/test/tools/llvm-profgen/noinline-cs-noprobe.test

 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/noinline-cs-noprobe.perfscript --binary=%S/Inputs/noinline-cs-noprobe.perfbin --output=%t1 --profile-summary-cold-count=0
 ; RUN: llvm-profgen --format=extbinary --perfscript=%S/Inputs/noinline-cs-noprobe.perfscript --binary=%S/Inputs/noinline-cs-noprobe.perfbin --output=%t2 --profile-summary-cold-count=0 -use-md5
 ; RUN: llvm-profdata show --sample -show-sec-info-only %t2 | FileCheck %s --check-prefix=CHECK-MD5
 ; RUN: llvm-profdata show --sample -detailed-summary --function=dummy %t1 > %t.summary
 ; RUN: llvm-profdata show --sample -detailed-summary --function=dummy %t2 > %t2.summary
 ; RUN: diff -b %t.summary %t2.summary
 
 
-; CHECK-AGG:[main:1 @ foo]:108:0
-; CHECK-AGG: 2: 6
-; CHECK-AGG: 3: 6 bar:6
-; CHECK-AGG:[main:1 @ foo:3 @ bar]:100:6
+; CHECK-AGG:[main:1 @ foo:3 @ bar]:24:6
 ; CHECK-AGG: 0: 6
 ; CHECK-AGG: 1: 6
 ; CHECK-AGG: 2: 4
 ; CHECK-AGG: 4: 2
 ; CHECK-AGG: 5: 6
+; CHECK-AGG:[main:1 @ foo]:12:0
+; CHECK-AGG: 2: 6
+; CHECK-AGG: 3: 6 bar:6
+
 
 ; CHECK-AGG-UNWINDER:      [main:1 @ foo]
 ; CHECK-AGG-UNWINDER-NEXT:   3
 ; CHECK-AGG-UNWINDER-NEXT:   5ff-62f:6
 ; CHECK-AGG-UNWINDER-NEXT:   634-637:6
 ; CHECK-AGG-UNWINDER-NEXT:   645-645:6
 ; CHECK-AGG-UNWINDER-NEXT:   3
 ; CHECK-AGG-UNWINDER-NEXT:   62f->5b0:6
 ; CHECK-AGG-UNWINDER-NEXT:   637->645:6
 ; CHECK-AGG-UNWINDER-NEXT:   645->5ff:6
 ; CHECK-AGG-UNWINDER-NEXT: [main:1 @ foo:3 @ bar]
 ; CHECK-AGG-UNWINDER-NEXT:   4
 ; CHECK-AGG-UNWINDER-NEXT:   5b0-5c8:2
 ; CHECK-AGG-UNWINDER-NEXT:   5b0-5d7:4
 ; CHECK-AGG-UNWINDER-NEXT:   5dc-5e9:2
 ; CHECK-AGG-UNWINDER-NEXT:   5e5-5e9:4
 ; CHECK-AGG-UNWINDER-NEXT:   3
 ; CHECK-AGG-UNWINDER-NEXT:   5c8->5dc:4
 ; CHECK-AGG-UNWINDER-NEXT:   5d7->5e5:4
 ; CHECK-AGG-UNWINDER-NEXT:   5e9->634:6
 
 
-; CHECK:[main:1 @ foo]:54:0
-; CHECK: 2: 3
-; CHECK: 3: 3 bar:3
-; CHECK:[main:1 @ foo:3 @ bar]:50:3
+; CHECK:[main:1 @ foo:3 @ bar]:12:3
 ; CHECK: 0: 3
 ; CHECK: 1: 3
 ; CHECK: 2: 2
 ; CHECK: 4: 1
 ; CHECK: 5: 3
+; CHECK:[main:1 @ foo]:6:0
+; CHECK: 2: 3
+; CHECK: 3: 3 bar:3
 
-; CHECK-STRIP-CTX: foo:57:0
+; CHECK-STRIP-CTX: bar:12:3
+; CHECK-STRIP-CTX:  0: 3
+; CHECK-STRIP-CTX:  1: 3
+; CHECK-STRIP-CTX:  2: 2
+; CHECK-STRIP-CTX:  4: 1
+; CHECK-STRIP-CTX:  5: 3
+; CHECK-STRIP-CTX: foo:6:0
 ; CHECK-STRIP-CTX:  0: 0
 ; CHECK-STRIP-CTX:  1: 0
 ; CHECK-STRIP-CTX:  2: 3
 ; CHECK-STRIP-CTX:  3: 3 bar:3
 ; CHECK-STRIP-CTX:  4: 0
 ; CHECK-STRIP-CTX:  5: 0
-; CHECK-STRIP-CTX: bar:50:3
-; CHECK-STRIP-CTX:  0: 3
-; CHECK-STRIP-CTX:  1: 3
-; CHECK-STRIP-CTX:  2: 2
-; CHECK-STRIP-CTX:  4: 1
-; CHECK-STRIP-CTX:  5: 3
 
 ; CHECK-UNWINDER:      [main:1 @ foo]
 ; CHECK-UNWINDER-NEXT:   3
 ; CHECK-UNWINDER-NEXT:   5ff-62f:3
 ; CHECK-UNWINDER-NEXT:   634-637:3
 ; CHECK-UNWINDER-NEXT:   645-645:3
 ; CHECK-UNWINDER-NEXT:   3
 ; CHECK-UNWINDER-NEXT:   62f->5b0:3

llvm/test/tools/llvm-profgen/noinline-noprobe.test

 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/noprobe.perfscript --binary=%S/Inputs/noprobe.perfbin --output=%t --skip-symbolization
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-RAW-PROFILE
 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/noprobe.mmap.perfscript --binary=%S/Inputs/noprobe.perfbin --output=%t --skip-symbolization
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-RAW-PROFILE
 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/noprobe.aggperfscript --binary=%S/Inputs/noprobe.perfbin --output=%t --skip-symbolization
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK-RAW-PROFILE-AGG
 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/noprobe.perfscript --binary=%S/Inputs/noprobe.perfbin --output=%t
 ; RUN: FileCheck %s --input-file %t --check-prefix=CHECK
 
-CHECK: foo:360:0
-CHECK:  2: 19
-CHECK:  3: 19 bar:21
-CHECK: bar:324:21
+CHECK: bar:77:21
 CHECK:  0: 20
 CHECK:  1: 20
 CHECK:  2: 13
 CHECK:  4: 6
 CHECK:  5: 18
+CHECK: foo:38:0
+CHECK:  0: 0
+CHECK:  1: 0
+CHECK:  2: 19
+CHECK:  3: 19 bar:21
+CHECK:  4: 0
+CHECK:  5: 0
 
 CHECK-RAW-PROFILE:      7
 CHECK-RAW-PROFILE-NEXT: 5b0-5c8:7
 CHECK-RAW-PROFILE-NEXT: 5b0-5d7:13
 CHECK-RAW-PROFILE-NEXT: 5dc-5e9:6
 CHECK-RAW-PROFILE-NEXT: 5e5-5e9:12
 CHECK-RAW-PROFILE-NEXT: 5ff-62f:19
 CHECK-RAW-PROFILE-NEXT: 634-637:18

llvm/test/tools/llvm-profgen/recursion-compression-noprobe.test

 ; Firstly test uncompression(--compress-recursion=0)
 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/recursion-compression-noprobe.perfscript --binary=%S/Inputs/recursion-compression-noprobe.perfbin --output=%t --compress-recursion=0 --profile-summary-cold-count=0
 ; RUN: FileCheck %s --input-file %t -check-prefix=CHECK-UNCOMPRESS
 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/recursion-compression-noprobe.perfscript --binary=%S/Inputs/recursion-compression-noprobe.perfbin --output=%t --profile-summary-cold-count=0
 ; RUN: FileCheck %s --input-file %t
 ; RUN: llvm-profgen --format=text --perfscript=%S/Inputs/recursion-compression-noprobe.perfscript --binary=%S/Inputs/recursion-compression-noprobe.perfbin --output=%t --compress-recursion=0 --profile-summary-cold-count=0 --csprof-max-context-depth=2
 ; RUN: FileCheck %s --input-file %t -check-prefix=CHECK-MAX-CTX-DEPTH
 
-; CHECK-UNCOMPRESS:[main:1 @ foo:3 @ fa:2 @ fb]:37:0
-; CHECK-UNCOMPRESS: 1: 11
-; CHECK-UNCOMPRESS: 2: 1 fa:1
-; CHECK-UNCOMPRESS:[main:1 @ foo:3 @ fa]:21:0
+; CHECK-UNCOMPRESS:[main:1 @ foo:3 @ fa]:14:0
 ; CHECK-UNCOMPRESS: 1: 1
 ; CHECK-UNCOMPRESS: 2: 13 fb:11
-; CHECK-UNCOMPRESS:[main:1 @ foo]:7:0
+; CHECK-UNCOMPRESS:[main:1 @ foo:3 @ fa:2 @ fb]:12:0
+; CHECK-UNCOMPRESS: 1: 11
+; CHECK-UNCOMPRESS: 2: 1 fa:1
+; CHECK-UNCOMPRESS:[main:1 @ foo]:3:0
 ; CHECK-UNCOMPRESS: 2: 1
 ; CHECK-UNCOMPRESS: 3: 2 fa:1
-; CHECK-UNCOMPRESS:[main:1 @ foo:3 @ fa:2 @ fb:2 @ fa]:6:0
+; CHECK-UNCOMPRESS:[main:1 @ foo:3 @ fa:2 @ fb:2 @ fa]:2:0
 ; CHECK-UNCOMPRESS: 1: 1
 ; CHECK-UNCOMPRESS: 2: 1
-; CHECK-UNCOMPRESS:[main:1 @ foo:3 @ fa:2 @ fb:2 @ fa:2 @ fb:2 @ fa]:2:0
+; CHECK-UNCOMPRESS:[main:1 @ foo:3 @ fa:2 @ fb:2 @ fa:2 @ fb:2 @ fa]:1:0
 ; CHECK-UNCOMPRESS: 4: 1
 
-; CHECK-MAX-CTX-DEPTH:[foo:3 @ fa:2 @ fb]:36:0
+; CHECK-MAX-CTX-DEPTH:[foo:3 @ fa:2 @ fb]:11:0
 ; CHECK-MAX-CTX-DEPTH: 1: 11
-; CHECK-MAX-CTX-DEPTH:[main:1 @ foo:3 @ fa]:10:0
-; CHECK-MAX-CTX-DEPTH: 1: 1
-; CHECK-MAX-CTX-DEPTH: 2: 2
-; CHECK-MAX-CTX-DEPTH:[fa:2 @ fb:2 @ fa]:8:0
+; CHECK-MAX-CTX-DEPTH:[fa:2 @ fb:2 @ fa]:3:0
 ; CHECK-MAX-CTX-DEPTH: 1: 1
 ; CHECK-MAX-CTX-DEPTH: 2: 1
 ; CHECK-MAX-CTX-DEPTH: 4: 1
-; CHECK-MAX-CTX-DEPTH:[main:1 @ foo]:7:0
+; CHECK-MAX-CTX-DEPTH:[main:1 @ foo]:3:0
 ; CHECK-MAX-CTX-DEPTH: 2: 1
 ; CHECK-MAX-CTX-DEPTH: 3: 2 fa:1
+; CHECK-MAX-CTX-DEPTH:[main:1 @ foo:3 @ fa]:3:0
+; CHECK-MAX-CTX-DEPTH: 1: 1
+; CHECK-MAX-CTX-DEPTH: 2: 2
 
 
-; CHECK: [main:1 @ foo:3 @ fa:2 @ fb]:37:0
-; CHECK:  1: 11
-; CHECK:  2: 1 fa:1
-; CHECK: [main:1 @ foo:3 @ fa]:21:0
+
+
+; CHECK: [main:1 @ foo:3 @ fa]:14:0
 ; CHECK:  1: 1
 ; CHECK:  2: 13 fb:11
-; CHECK: [main:1 @ foo:3 @ fa:2 @ fb:2 @ fa]:8:0
+; CHECK: [main:1 @ foo:3 @ fa:2 @ fb]:12:0
+; CHECK:  1: 11
+; CHECK:  2: 1 fa:1
+; CHECK: [main:1 @ foo]:3:0
+; CHECK:  2: 1
+; CHECK:  3: 2 fa:1
+; CHECK: [main:1 @ foo:3 @ fa:2 @ fb:2 @ fa]:3:0
 ; CHECK:  1: 1
 ; CHECK:  2: 1
 ; CHECK:  4: 1
-; CHECK: [main:1 @ foo]:7:0
-; CHECK:  2: 1
-; CHECK:  3: 2 fa:1
+
 
 ; original code:
 ; clang -O3 -g test.c -o a.out
 #include <stdio.h>
 
 int fb(int n) {
   if(n > 10) return fb(n / 2);
   return fa(n - 1);

llvm/tools/llvm-profgen/ProfileGenerator.h

protected:
   */
   void findDisjointRanges(RangeSample &DisjointRanges,
                           const RangeSample &Ranges);
   // Helper function for updating body sample for a leaf location in
   // FunctionProfile
   void updateBodySamplesforFunctionProfile(FunctionSamples &FunctionProfile,
                                            const SampleContextFrame &LeafLoc,
                                            uint64_t Count);
+  void updateTotalSamples();
   StringRef getCalleeNameForOffset(uint64_t TargetOffset);
   // Used by SampleProfileWriter
   SampleProfileMap ProfileMap;
 
   ProfiledBinary *Binary = nullptr;
 
   const ContextSampleCounterMap &SampleCounters;
 };

 private:
   void generateLineNumBasedProfile();
   RangeSample preprocessRangeCounter(const RangeSample &RangeCounter);
   FunctionSamples &getTopLevelFunctionProfile(StringRef FuncName);
   // Helper function to get the leaf frame's FunctionProfile by traversing the
   // inline stack and meanwhile it adds the total samples for each frame's
   // function profile.
   FunctionSamples &
-  getLeafProfileAndAddTotalSamples(const SampleContextFrameVector &FrameVec,
-                                   uint64_t Count);
+  getLeafFrameProfile(const SampleContextFrameVector &FrameVec);
   void populateBodySamplesForAllFunctions(const RangeSample &RangeCounter);
   void
   populateBoundarySamplesForAllFunctions(const BranchSample &BranchCounters);
 };
 
 using ProbeCounterMap =
     std::unordered_map<const MCDecodedPseudoProbe *, uint64_t>;
 

llvm/tools/llvm-profgen/ProfileGenerator.cpp

void ProfileGeneratorBase::updateBodySamplesforFunctionProfile(
 
   uint64_t PreviousCount = R ? R.get() : 0;
   if (PreviousCount <= Count) {
     FunctionProfile.addBodySamples(LeafLoc.Location.LineOffset, Discriminator,
                                    Count - PreviousCount);
   }
 }
 
+void ProfileGeneratorBase::updateTotalSamples() {
+  for (auto &Item : ProfileMap) {
+    FunctionSamples &FunctionProfile = Item.second;
+    FunctionProfile.updateTotalSamples();
+  }
+}
+
 FunctionSamples &
 ProfileGenerator::getTopLevelFunctionProfile(StringRef FuncName) {
   SampleContext Context(FuncName);
   auto Ret = ProfileMap.emplace(Context, FunctionSamples());
   if (Ret.second) {
     FunctionSamples &FProfile = Ret.first->second;
     FProfile.setContext(Context);
   }

 void ProfileGenerator::generateLineNumBasedProfile() {
   assert(SampleCounters.size() == 1 &&
          "Must have one entry for profile generation.");
   const SampleCounter &SC = SampleCounters.begin()->second;
   // Fill in function body samples
   populateBodySamplesForAllFunctions(SC.RangeCounter);
   // Fill in boundary sample counts as well as call site samples for calls
   populateBoundarySamplesForAllFunctions(SC.BranchCounter);
+
+  updateTotalSamples();
 }
 
-FunctionSamples &ProfileGenerator::getLeafProfileAndAddTotalSamples(
-    const SampleContextFrameVector &FrameVec, uint64_t Count) {
+FunctionSamples &ProfileGenerator::getLeafFrameProfile(
+    const SampleContextFrameVector &FrameVec) {
   // Get top level profile
   FunctionSamples *FunctionProfile =
       &getTopLevelFunctionProfile(FrameVec[0].FuncName);
-  FunctionProfile->addTotalSamples(Count);
 
   for (size_t I = 1; I < FrameVec.size(); I++) {
     LineLocation Callsite(
         FrameVec[I - 1].Location.LineOffset,
         getBaseDiscriminator(FrameVec[I - 1].Location.Discriminator));
     FunctionSamplesMap &SamplesMap =
         FunctionProfile->functionSamplesAt(Callsite);
     auto Ret =
         SamplesMap.emplace(FrameVec[I].FuncName.str(), FunctionSamples());
     if (Ret.second) {
       SampleContext Context(FrameVec[I].FuncName);
       Ret.first->second.setContext(Context);
     }
     FunctionProfile = &Ret.first->second;
-    FunctionProfile->addTotalSamples(Count);
   }
 
   return *FunctionProfile;
 }
 
 RangeSample
 ProfileGenerator::preprocessRangeCounter(const RangeSample &RangeCounter) {
   RangeSample Ranges(RangeCounter.begin(), RangeCounter.end());
for (auto Range : preprocessRangeCounter(RangeCounter)) {
     // Disjoint ranges may have range in the middle of two instr,
     // e.g. If Instr1 at Addr1, and Instr2 at Addr2, disjoint range
     // can be Addr1+1 to Addr2-1. We should ignore such range.
     while (IP.Address <= RangeEnd) {
       uint64_t Offset = Binary->virtualAddrToOffset(IP.Address);
       const SampleContextFrameVector &FrameVec =
           Binary->getFrameLocationStack(Offset);
       if (!FrameVec.empty()) {
-        FunctionSamples &FunctionProfile =
-            getLeafProfileAndAddTotalSamples(FrameVec, Count);
+        FunctionSamples &FunctionProfile = getLeafFrameProfile(FrameVec);
         updateBodySamplesforFunctionProfile(FunctionProfile, FrameVec.back(),
                                             Count);
       }
       // Move to next IP within the range.
       IP.advance();
     }
   }
 }
for (auto Entry : BranchCounters) {
 
     StringRef CalleeName = getCalleeNameForOffset(TargetOffset);
     if (CalleeName.size() == 0)
       continue;
     // Record called target sample and its count.
     const SampleContextFrameVector &FrameVec =
         Binary->getFrameLocationStack(SourceOffset);
     if (!FrameVec.empty()) {
-      FunctionSamples &FunctionProfile =
-          getLeafProfileAndAddTotalSamples(FrameVec, Count);
+      FunctionSamples &FunctionProfile = getLeafFrameProfile(FrameVec);
       FunctionProfile.addCalledTargetSamples(
           FrameVec.back().Location.LineOffset,
           getBaseDiscriminator(FrameVec.back().Location.Discriminator),
           CalleeName, Count);
     }
     // Add head samples for callee.
     FunctionSamples &CalleeProfile = getTopLevelFunctionProfile(CalleeName);
     CalleeProfile.addHeadSamples(Count);
for (const auto &CI : SampleCounters) {
     populateBoundarySamplesForFunction(CtxKey->Context, FunctionProfile,
                                        CI.second.BranchCounter);
   }
   // Fill in call site value sample for inlined calls and also use context to
   // infer missing samples. Since we don't have call count for inlined
   // functions, we estimate it from inlinee's profile using the entry of the
   // body sample.
   populateInferredFunctionSamples();
+
+  updateTotalSamples();
 }
 
 void CSProfileGenerator::populateBodySamplesForFunction(
     FunctionSamples &FunctionProfile, const RangeSample &RangeCounter) {
   // Compute disjoint ranges first, so we can use MAX
   // for calculating count for each location.
   RangeSample Ranges;
   findDisjointRanges(Ranges, RangeCounter);
for (auto Range : Ranges) {
     // e.g. If Instr1 at Addr1, and Instr2 at Addr2, disjoint range
     // can be Addr1+1 to Addr2-1. We should ignore such range.
     while (IP.Address <= RangeEnd) {
       uint64_t Offset = Binary->virtualAddrToOffset(IP.Address);
       auto LeafLoc = Binary->getInlineLeafFrameLoc(Offset);
       if (LeafLoc.hasValue()) {
         // Recording body sample for this specific context
         updateBodySamplesforFunctionProfile(FunctionProfile, *LeafLoc, Count);
-        FunctionProfile.addTotalSamples(Count);
       }
 
       // Move to next IP within the range
       IP.advance();
     }
   }
 }
 
if (!EstimatedCallCount && !CalleeProfile.getBodySamples().size())
       EstimatedCallCount = 1;
     CallerProfile.addCalledTargetSamples(
         CallerLeafFrameLoc.Location.LineOffset,
         CallerLeafFrameLoc.Location.Discriminator,
         CalleeProfile.getContext().getName(), EstimatedCallCount);
     CallerProfile.addBodySamples(CallerLeafFrameLoc.Location.LineOffset,
                                  CallerLeafFrameLoc.Location.Discriminator,
                                  EstimatedCallCount);
-    CallerProfile.addTotalSamples(EstimatedCallCount);
   }
 }
 
 void CSProfileGenerator::postProcessProfiles() {
   // Compute hot/cold threshold based on profile. This will be used for cold
   // context profile merging/trimming.
   computeSummaryAndThreshold();
 

llvm/tools/llvm-profgen/ProfiledBinary.cpp

 //===-- ProfiledBinary.cpp - Binary decoder ---------------------*- C++ -*-===//
 //
 // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
 // See https://llvm.org/LICENSE.txt for license information.
 // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
 //
 //===----------------------------------------------------------------------===//
 
 #include "ProfiledBinary.h"
 #include "ErrorHandling.h"
 #include "ProfileGenerator.h"
 #include "llvm/ADT/Triple.h"
-#include "llvm/DebugInfo/DWARF/DWARFContext.h"
 #include "llvm/Demangle/Demangle.h"
 #include "llvm/IR/DebugInfoMetadata.h"
 #include "llvm/MC/TargetRegistry.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Format.h"
 #include "llvm/Support/TargetSelect.h"
 
 #define DEBUG_TYPE "load-binary"