[BOLT] Report input staleness (#79496)

It's beneficial to have uniform reporting in both `infer-stale-profile`
on and off cases, primarily for logging purposes.

Without this change, BOLT would report "input" staleness in
`infer-stale-profile=0` case (without matching), and "output" staleness
in `infer-stale-profile=1` case (after matching).

This change makes BOLT report "input" staleness in both cases. "Output"
staleness information is printed separately with "BOLT-INFO: inferred
profile..."

Author: aaupov

bolt/lib/Passes/BinaryPasses.cpp

@@ -1417,26 +1417,28 @@ void PrintProgramStats::runOnFunctions(BinaryContext &BC) {
            << (NumNonSimpleProfiledFunctions == 1 ? "" : "s")
            << " with profile could not be optimized\n";
   }
-  if (NumStaleProfileFunctions) {
+  if (NumAllStaleFunctions) {
     const float PctStale =
-        NumStaleProfileFunctions / (float)NumAllProfiledFunctions * 100.0f;
+        NumAllStaleFunctions / (float)NumAllProfiledFunctions * 100.0f;
     auto printErrorOrWarning = [&]() {
       if (PctStale > opts::StaleThreshold)
         errs() << "BOLT-ERROR: ";
       else
         errs() << "BOLT-WARNING: ";
     };
     printErrorOrWarning();
-    errs() << NumStaleProfileFunctions
+    errs() << NumAllStaleFunctions
            << format(" (%.1f%% of all profiled)", PctStale) << " function"
-           << (NumStaleProfileFunctions == 1 ? "" : "s")
+           << (NumAllStaleFunctions == 1 ? "" : "s")
            << " have invalid (possibly stale) profile."
               " Use -report-stale to see the list.\n";
     if (TotalSampleCount > 0) {
       printErrorOrWarning();
-      errs() << StaleSampleCount << " out of " << TotalSampleCount
-             << " samples in the binary ("
-             << format("%.1f", ((100.0f * StaleSampleCount) / TotalSampleCount))
+      errs() << (StaleSampleCount + InferredSampleCount) << " out of "
+             << TotalSampleCount << " samples in the binary ("
+             << format("%.1f",
+                       ((100.0f * (StaleSampleCount + InferredSampleCount)) /
+                        TotalSampleCount))
              << "%) belong to functions with invalid"
                 " (possibly stale) profile.\n";
     }

bolt/test/X86/reader-stale-yaml.test

@@ -3,6 +3,9 @@
 
 REQUIRES: asserts
 RUN: yaml2obj %p/Inputs/blarge.yaml &> %t.exe
+RUN: llvm-bolt %t.exe -o %t.null --b %p/Inputs/blarge_profile_stale.yaml \
+RUN:   --infer-stale-profile=0 --profile-ignore-hash=1 --profile-use-dfs=0 \
+RUN:   2>&1 | FileCheck %s -check-prefix=CHECK0
 # Testing "usqrt"
 RUN: llvm-bolt %t.exe -o %t.null --b %p/Inputs/blarge_profile_stale.yaml \
 RUN:   --print-cfg --print-only=usqrt --infer-stale-profile=1 \
@@ -12,6 +15,10 @@ RUN: llvm-bolt %t.exe -o %t.null --b %p/Inputs/blarge_profile_stale.yaml \
 RUN:   --print-cfg --print-only=SolveCubic --infer-stale-profile=1 \
 RUN:   --profile-ignore-hash=1 --profile-use-dfs=0 --debug-only=bolt-prof 2>&1 | FileCheck %s -check-prefix=CHECK2
 
+CHECK0: BOLT-INFO: 2 out of 7 functions in the binary (28.6%) have non-empty execution profile
+CHECK0: BOLT-WARNING: 2 (100.0% of all profiled) functions have invalid (possibly stale) profile
+CHECK0: BOLT-WARNING: 1192 out of 1192 samples in the binary (100.0%) belong to functions with invalid (possibly stale) profile
+
 # Function "usqrt" has stale profile, since the number of blocks in the profile
 # (nblocks=6) does not match the size of the CFG in the binary. The entry
 # block (bid=0) has an incorrect (missing) count, which should be inferred by
@@ -51,6 +58,8 @@ CHECK1:      Successors: .Ltmp[[#BB13:]] (mispreds: 0, count: 300), .LFT[[#BB1:]
 CHECK1:    .LFT[[#BB1:]] (2 instructions, align : 1)
 # Check the overall inference stats.
 CHECK1:  2 out of 7 functions in the binary (28.6%) have non-empty execution profile
+CHECK1:  BOLT-WARNING: 2 (100.0% of all profiled) functions have invalid (possibly stale) profile
+CHECK1:  BOLT-WARNING: 1192 out of 1192 samples in the binary (100.0%) belong to functions with invalid (possibly stale) profile
 CHECK1:  inferred profile for 2 (100.00% of profiled, 100.00% of stale) functions responsible for {{.*}} samples ({{.*}} out of {{.*}})