[llvm] [BOLT][heatmap] Produce zoomed-out heatmaps (PR #140153)

[via llvm-commits]

llvmbot wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-bolt

Author: Amir Ayupov (aaupov)

<details>
<summary>Changes</summary>

Add an option `--heatmap-zoom-out=bucket_size1,bucket_size2,...` to
print additional heatmaps with coarser granularity. This makes it easier
to navigate the heatmap, compared to the default setting of 64B buckets
that could be too fine-grained.

The option rescales an existing heatmap, so the provided bucket sizes
should be multiples of the original bucket size (`--block-size`), and be
provided in ascending order. If rescaling is impossible, no heatmap is
produced.

Suggested values to use: 4096 (default page size), 16384 (16k page),
1048576 (1MB for XL workloads).

Test Plan: updated heatmap-preagg.test


---
Full diff: https://github.com/llvm/llvm-project/pull/140153.diff


4 Files Affected:

- (modified) bolt/include/bolt/Profile/Heatmap.h (+3) 
- (modified) bolt/lib/Profile/DataAggregator.cpp (+15) 
- (modified) bolt/lib/Profile/Heatmap.cpp (+14-1) 
- (modified) bolt/test/X86/heatmap-preagg.test (+13-1) 


``````````diff
diff --git a/bolt/include/bolt/Profile/Heatmap.h b/bolt/include/bolt/Profile/Heatmap.h
index 9813e7fed486d..bf3d1c91c0aa5 100644
--- a/bolt/include/bolt/Profile/Heatmap.h
+++ b/bolt/include/bolt/Profile/Heatmap.h
@@ -85,6 +85,9 @@ class Heatmap {
   void printSectionHotness(raw_ostream &OS) const;
 
   size_t size() const { return Map.size(); }
+
+  /// Increase bucket size to \p TargetSize, recomputing the heatmap.
+  bool resizeBucket(uint64_t TargetSize);
 };
 
 } // namespace bolt
diff --git a/bolt/lib/Profile/DataAggregator.cpp b/bolt/lib/Profile/DataAggregator.cpp
index 6beb60741406e..aa681e633c0d8 100644
--- a/bolt/lib/Profile/DataAggregator.cpp
+++ b/bolt/lib/Profile/DataAggregator.cpp
@@ -68,6 +68,12 @@ FilterPID("pid",
   cl::Optional,
   cl::cat(AggregatorCategory));
 
+static cl::list<uint64_t>
+    HeatmapZoomOut("heatmap-zoom-out", cl::CommaSeparated,
+                   cl::desc("print secondary heatmaps with given bucket sizes"),
+                   cl::value_desc("bucket_size"), cl::Optional,
+                   cl::cat(HeatmapCategory));
+
 static cl::opt<bool>
 IgnoreBuildID("ignore-build-id",
   cl::desc("continue even if build-ids in input binary and perf.data mismatch"),
@@ -1365,6 +1371,15 @@ std::error_code DataAggregator::printLBRHeatMap() {
     HM.printCDF(opts::HeatmapOutput + ".csv");
     HM.printSectionHotness(opts::HeatmapOutput + "-section-hotness.csv");
   }
+  // Provide coarse-grained heatmap if requested via --heatmap-zoom-out
+  for (const uint64_t NewBucketSize : opts::HeatmapZoomOut) {
+    if (!HM.resizeBucket(NewBucketSize))
+      break;
+    if (opts::HeatmapOutput == "-")
+      HM.print(opts::HeatmapOutput);
+    else
+      HM.print(formatv("{0}-{1}", opts::HeatmapOutput, NewBucketSize).str());
+  }
 
   return std::error_code();
 }
diff --git a/bolt/lib/Profile/Heatmap.cpp b/bolt/lib/Profile/Heatmap.cpp
index c66c2e5487613..4aaf6dc344a85 100644
--- a/bolt/lib/Profile/Heatmap.cpp
+++ b/bolt/lib/Profile/Heatmap.cpp
@@ -81,7 +81,7 @@ void Heatmap::print(raw_ostream &OS) const {
   // the Address.
   auto startLine = [&](uint64_t Address, bool Empty = false) {
     changeColor(DefaultColor);
-    const uint64_t LineAddress = Address / BytesPerLine * BytesPerLine;
+    const uint64_t LineAddress = alignTo(Address, BytesPerLine);
 
     if (MaxAddress > 0xffffffff)
       OS << format("0x%016" PRIx64 ": ", LineAddress);
@@ -364,5 +364,18 @@ void Heatmap::printSectionHotness(raw_ostream &OS) const {
     OS << formatv("[unmapped], 0x0, 0x0, {0:f4}, 0, 0\n",
                   100.0 * UnmappedHotness / NumTotalCounts);
 }
+
+bool Heatmap::resizeBucket(uint64_t TargetSize) {
+  if (TargetSize <= BucketSize)
+    return false;
+  std::map<uint64_t, uint64_t> NewMap;
+  for (const auto [Bucket, Count] : Map) {
+    const uint64_t Address = Bucket * BucketSize;
+    NewMap[Address / TargetSize] += Count;
+  }
+  Map = NewMap;
+  BucketSize = TargetSize;
+  return true;
+}
 } // namespace bolt
 } // namespace llvm
diff --git a/bolt/test/X86/heatmap-preagg.test b/bolt/test/X86/heatmap-preagg.test
index 306e74800a353..9539269ff0d47 100644
--- a/bolt/test/X86/heatmap-preagg.test
+++ b/bolt/test/X86/heatmap-preagg.test
@@ -3,8 +3,11 @@
 RUN: yaml2obj %p/Inputs/blarge_new.yaml &> %t.exe
 ## Non-BOLTed input binary
 RUN: llvm-bolt-heatmap %t.exe -o %t --pa -p %p/Inputs/blarge_new.preagg.txt \
-RUN:   2>&1 | FileCheck --check-prefix CHECK-HEATMAP %s
+RUN:   --heatmap-zoom-out 128,1024 2>&1 | FileCheck --check-prefix CHECK-HEATMAP %s
 RUN: FileCheck %s --check-prefix CHECK-SEC-HOT --input-file %t-section-hotness.csv
+RUN: FileCheck %s --check-prefix CHECK-HM-64 --input-file %t
+RUN: FileCheck %s --check-prefix CHECK-HM-128 --input-file %t-128
+RUN: FileCheck %s --check-prefix CHECK-HM-1024 --input-file %t-1024
 
 ## BOLTed input binary
 RUN: llvm-bolt %t.exe -o %t.out --pa -p %p/Inputs/blarge_new.preagg.txt \
@@ -24,6 +27,15 @@ CHECK-SEC-HOT-NEXT: .plt, 0x401020, 0x4010b0, 4.7583, 66.6667, 0.0317
 CHECK-SEC-HOT-NEXT: .text, 0x4010b0, 0x401c25, 78.3872, 85.1064, 0.6671
 CHECK-SEC-HOT-NEXT: .fini, 0x401c28, 0x401c35, 0.0000, 0.0000, 0.0000
 
+# Only check start addresses – can't check colors, and FileCheck doesn't strip
+# color codes by default. Reference output:
+# HM-64:   0x00404000: ABBcccccccccccccccCCCCCCCCCccccCCCCCCCCcc....CC
+# HM-128:  0x00408000: ABCCCCCCCCCCCCCCCCCCc.CC
+# HM-1024: 0x00440000: ACC
+CHECK-HM-64:   0x00404000:
+CHECK-HM-128:  0x00408000:
+CHECK-HM-1024: 0x00440000:
+
 CHECK-HEATMAP-BAT: PERF2BOLT: read 79 aggregated LBR entries
 CHECK-HEATMAP-BAT: HEATMAP: invalid traces: 2
 

``````````

</details>


https://github.com/llvm/llvm-project/pull/140153