1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-19 11:02:59 +02:00

Revert rL349136: [llvm-exegesis] Optimize ToProcess in dbScan

Summary:
Use `vector<char> Added + vector<size_t> ToProcess` to replace `SetVector ToProcess`

We also check `Added[P]` to enqueueing a point more than once, which
also saves us a `ClusterIdForPoint_[Q].isUndef()` check.

Reviewers: courbet, RKSimon, gchatelet, john.brawn, lebedev.ri

Subscribers: tschuett, llvm-commits

Differential Revision: https://reviews.llvm.org/D54442
........
Patch wasn't approved and breaks buildbots

llvm-svn: 349139
This commit is contained in:
Simon Pilgrim 2018-12-14 09:25:08 +00:00
parent 486c1ccebe
commit 0777513533

View File

@ -8,6 +8,7 @@
//===----------------------------------------------------------------------===// //===----------------------------------------------------------------------===//
#include "Clustering.h" #include "Clustering.h"
#include "llvm/ADT/SetVector.h"
#include "llvm/ADT/SmallVector.h" #include "llvm/ADT/SmallVector.h"
#include <string> #include <string>
@ -91,14 +92,8 @@ llvm::Error InstructionBenchmarkClustering::validateAndSetup() {
} }
void InstructionBenchmarkClustering::dbScan(const size_t MinPts) { void InstructionBenchmarkClustering::dbScan(const size_t MinPts) {
const size_t NumPoints = Points_.size(); std::vector<size_t> Neighbors; // Persistent buffer to avoid allocs.
for (size_t P = 0, NumPoints = Points_.size(); P < NumPoints; ++P) {
// Persistent buffers to avoid allocs.
std::vector<size_t> Neighbors;
std::vector<size_t> ToProcess(NumPoints);
std::vector<char> Added(NumPoints);
for (size_t P = 0; P < NumPoints; ++P) {
if (!ClusterIdForPoint_[P].isUndef()) if (!ClusterIdForPoint_[P].isUndef())
continue; // Previously processed in inner loop. continue; // Previously processed in inner loop.
rangeQuery(P, Neighbors); rangeQuery(P, Neighbors);
@ -114,18 +109,14 @@ void InstructionBenchmarkClustering::dbScan(const size_t MinPts) {
Cluster &CurrentCluster = Clusters_.back(); Cluster &CurrentCluster = Clusters_.back();
ClusterIdForPoint_[P] = CurrentCluster.Id; /* Label initial point */ ClusterIdForPoint_[P] = CurrentCluster.Id; /* Label initial point */
CurrentCluster.PointIndices.push_back(P); CurrentCluster.PointIndices.push_back(P);
Added[P] = 1;
// Process P's neighbors. // Process P's neighbors.
size_t Tail = 0; llvm::SetVector<size_t, std::deque<size_t>> ToProcess;
for (size_t Q : Neighbors) ToProcess.insert(Neighbors.begin(), Neighbors.end());
if (!Added[Q]) { while (!ToProcess.empty()) {
ToProcess[Tail++] = P;
Added[Q] = 1;
}
for (size_t Head = 0; Head < Tail; ++Head) {
// Retrieve a point from the set. // Retrieve a point from the set.
size_t Q = ToProcess[Head]; const size_t Q = *ToProcess.begin();
ToProcess.erase(ToProcess.begin());
if (ClusterIdForPoint_[Q].isNoise()) { if (ClusterIdForPoint_[Q].isNoise()) {
// Change noise point to border point. // Change noise point to border point.
@ -133,18 +124,17 @@ void InstructionBenchmarkClustering::dbScan(const size_t MinPts) {
CurrentCluster.PointIndices.push_back(Q); CurrentCluster.PointIndices.push_back(Q);
continue; continue;
} }
assert(ClusterIdForPoint_[Q].isUndef()); if (!ClusterIdForPoint_[Q].isUndef()) {
continue; // Previously processed.
}
// Add Q to the current custer. // Add Q to the current custer.
ClusterIdForPoint_[Q] = CurrentCluster.Id; ClusterIdForPoint_[Q] = CurrentCluster.Id;
CurrentCluster.PointIndices.push_back(Q); CurrentCluster.PointIndices.push_back(Q);
// And extend to the neighbors of Q if the region is dense enough. // And extend to the neighbors of Q if the region is dense enough.
rangeQuery(Q, Neighbors); rangeQuery(Q, Neighbors);
if (Neighbors.size() + 1 >= MinPts) if (Neighbors.size() + 1 >= MinPts) {
for (size_t P : Neighbors) ToProcess.insert(Neighbors.begin(), Neighbors.end());
if (!Added[P]) { }
ToProcess[Tail++] = P;
Added[P] = 1;
}
} }
} }
// assert(Neighbors.capacity() == (Points_.size() - 1)); // assert(Neighbors.capacity() == (Points_.size() - 1));