[llvm-exegesis] InstructionBenchmarkClustering::rangeQuery(): write into llvm::SmallVectorImpl& output parameter

Summary:
I do believe this is the correct fix.
We call `rangeQuery()` *very* often. And many times it's output vector is large (tens of thousands entries), so small-size-opt won't help.

Old: (D54389)
```
 Performance counter stats for './bin/llvm-exegesis -mode=analysis -analysis-epsilon=100000 -benchmarks-file=/tmp/benchmarks.yaml -analysis-inconsistencies-output-file=/tmp/clusters.html' (10 runs):

       7934.528363      task-clock (msec)         #    1.000 CPUs utilized            ( +-  0.19% )
...
            7.9354 +- 0.0148 seconds time elapsed  ( +-  0.19% )
```
New:
```
 Performance counter stats for './bin/llvm-exegesis -mode=analysis -analysis-epsilon=100000 -benchmarks-file=/tmp/benchmarks.yaml -analysis-inconsistencies-output-file=/tmp/clusters.html' (10 runs):

       7383.793440      task-clock (msec)         #    1.000 CPUs utilized            ( +-  0.47% )
...
            7.3868 +- 0.0340 seconds time elapsed  ( +-  0.46% )
```
And another -7%. And that isn't even the good bit yet.

Old:
* calls to allocation functions: 2081419
* temporary allocations: 219658 (10.55%)
* bytes allocated in total (ignoring deallocations): 4.31 GB

New:
* calls to allocation functions: 1880295 (-10%)
* temporary allocations: 18758 (1%) (-91% *sic*)
* bytes allocated in total (ignoring deallocations): 545.15 MB (-88% *sic*)

Reviewers: courbet, MaskRay, RKSimon, gchatelet, john.brawn

Reviewed By: courbet, MaskRay

Subscribers: tschuett, llvm-commits

Differential Revision: https://reviews.llvm.org/D54390

llvm-svn: 347202

2 files changed, 7 insertions, 7 deletions

diff --git a/llvm/tools/llvm-exegesis/lib/Clustering.cpp b/llvm/tools/llvm-exegesis/lib/Clustering.cpp
index 8a42e0b28db..df45de31990 100644
--- a/llvm/tools/llvm-exegesis/lib/Clustering.cpp
+++ b/llvm/tools/llvm-exegesis/lib/Clustering.cpp
@@ -33,9 +33,9 @@ namespace exegesis {
 
 // Finds the points at distance less than sqrt(EpsilonSquared) of Q (not
 // including Q).
-llvm::SmallVector<size_t, 0>
-InstructionBenchmarkClustering::rangeQuery(const size_t Q) const {
-  llvm::SmallVector<size_t, 0> Neighbors;
+void InstructionBenchmarkClustering::rangeQuery(
+    const size_t Q, llvm::SmallVectorImpl<size_t> &Neighbors) const {
+  Neighbors.clear();
   const auto &QMeasurements = Points_[Q].Measurements;
   for (size_t P = 0, NumPoints = Points_.size(); P < NumPoints; ++P) {
     if (P == Q)
@@ -47,7 +47,6 @@ InstructionBenchmarkClustering::rangeQuery(const size_t Q) const {
       Neighbors.push_back(P);
     }
   }
-  return Neighbors;
 }
 
 bool InstructionBenchmarkClustering::isNeighbour(
@@ -103,10 +102,11 @@ llvm::Error InstructionBenchmarkClustering::validateAndSetup() {
 }
 
 void InstructionBenchmarkClustering::dbScan(const size_t MinPts) {
+  llvm::SmallVector<size_t, 0> Neighbors; // Persistent buffer to avoid allocs.
   for (size_t P = 0, NumPoints = Points_.size(); P < NumPoints; ++P) {
     if (!ClusterIdForPoint_[P].isUndef())
       continue; // Previously processed in inner loop.
-    const auto Neighbors = rangeQuery(P);
+    rangeQuery(P, Neighbors);
     if (Neighbors.size() + 1 < MinPts) { // Density check.
       // The region around P is not dense enough to create a new cluster, mark
       // as noise for now.
@@ -141,7 +141,7 @@ void InstructionBenchmarkClustering::dbScan(const size_t MinPts) {
       ClusterIdForPoint_[Q] = CurrentCluster.Id;
       CurrentCluster.PointIndices.push_back(Q);
       // And extend to the neighbors of Q if the region is dense enough.
-      const auto Neighbors = rangeQuery(Q);
+      rangeQuery(Q, Neighbors);
       if (Neighbors.size() + 1 >= MinPts) {
         ToProcess.insert(Neighbors.begin(), Neighbors.end());
       }
diff --git a/llvm/tools/llvm-exegesis/lib/Clustering.h b/llvm/tools/llvm-exegesis/lib/Clustering.h
index 0d8a463371a..e746e4ba41d 100644
--- a/llvm/tools/llvm-exegesis/lib/Clustering.h
+++ b/llvm/tools/llvm-exegesis/lib/Clustering.h
@@ -97,7 +97,7 @@ private:
       const std::vector<InstructionBenchmark> &Points, double EpsilonSquared);
   llvm::Error validateAndSetup();
   void dbScan(size_t MinPts);
-  llvm::SmallVector<size_t, 0> rangeQuery(size_t Q) const;
+  void rangeQuery(size_t Q, llvm::SmallVectorImpl<size_t> &Scratchpad) const;
 
   const std::vector<InstructionBenchmark> &Points_;
   const double EpsilonSquared_;