mirror of
https://github.com/RPCS3/llvm.git
synced 2024-11-27 21:50:29 +00:00
[llvm-exegesis] Split Epsilon param into two (PR40787)
Summary:
This eps param is used for two distinct things:
* initial point clusterization
* checking clusters against the llvm values
What if one wants to only look at highly different clusters, without changing
the clustering itself? In particular, this helps to weed out noisy measurements
(since the clusterization epsilon is still small, so there is a better chance
that noisy measurements from the same opcode will go into different clusters)
By splitting it into two params it is now possible.
This is nearly-free performance-wise:
Old:
```
$ perf stat -r 25 ./bin/llvm-exegesis -mode=analysis -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-latency-1.yaml -analysis-inconsistencies-output-file=/tmp/clusters-old.html
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 10099 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-old.html'
...
Performance counter stats for './bin/llvm-exegesis -mode=analysis -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-latency-1.yaml -analysis-inconsistencies-output-file=/tmp/clusters-old.html' (25 runs):
390.01 msec task-clock # 0.998 CPUs utilized ( +- 0.25% )
12 context-switches # 31.735 M/sec ( +- 27.38% )
0 cpu-migrations # 0.000 K/sec
4745 page-faults # 12183.732 M/sec ( +- 0.54% )
1562711900 cycles # 4012303.327 GHz ( +- 0.24% ) (82.90%)
185567822 stalled-cycles-frontend # 11.87% frontend cycles idle ( +- 0.52% ) (83.30%)
392106234 stalled-cycles-backend # 25.09% backend cycles idle ( +- 1.31% ) (33.79%)
1839236666 instructions # 1.18 insn per cycle
# 0.21 stalled cycles per insn ( +- 0.15% ) (50.37%)
407035764 branches # 1045074878.710 M/sec ( +- 0.12% ) (66.80%)
10896459 branch-misses # 2.68% of all branches ( +- 0.17% ) (83.20%)
0.390629 +- 0.000972 seconds time elapsed ( +- 0.25% )
```
```
$ perf stat -r 9 ./bin/llvm-exegesis -mode=analysis -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-latency.yml -analysis-inconsistencies-output-file=/tmp/clusters-old.html
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 50572 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-old.html'
...
Performance counter stats for './bin/llvm-exegesis -mode=analysis -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-latency.yml -analysis-inconsistencies-output-file=/tmp/clusters-old.html' (9 runs):
6803.36 msec task-clock # 0.999 CPUs utilized ( +- 0.96% )
262 context-switches # 38.546 M/sec ( +- 23.06% )
0 cpu-migrations # 0.065 M/sec ( +- 76.03% )
13287 page-faults # 1953.206 M/sec ( +- 0.32% )
27252537904 cycles # 4006024.257 GHz ( +- 0.95% ) (83.31%)
1496314935 stalled-cycles-frontend # 5.49% frontend cycles idle ( +- 0.97% ) (83.32%)
16128404524 stalled-cycles-backend # 59.18% backend cycles idle ( +- 0.30% ) (33.37%)
17611143370 instructions # 0.65 insn per cycle
# 0.92 stalled cycles per insn ( +- 0.05% ) (50.04%)
3894906599 branches # 572537147.437 M/sec ( +- 0.03% ) (66.69%)
116314514 branch-misses # 2.99% of all branches ( +- 0.20% ) (83.35%)
6.8118 +- 0.0689 seconds time elapsed ( +- 1.01%)
```
New:
```
$ perf stat -r 25 ./bin/llvm-exegesis -mode=analysis -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-latency-1.yaml -analysis-inconsistencies-output-file=/tmp/clusters-new.html
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 10099 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-new.html'
...
Performance counter stats for './bin/llvm-exegesis -mode=analysis -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-latency-1.yaml -analysis-inconsistencies-output-file=/tmp/clusters-new.html' (25 runs):
400.14 msec task-clock # 0.998 CPUs utilized ( +- 0.66% )
12 context-switches # 29.429 M/sec ( +- 25.95% )
0 cpu-migrations # 0.100 M/sec ( +-100.00% )
4714 page-faults # 11796.496 M/sec ( +- 0.55% )
1603131306 cycles # 4011840.105 GHz ( +- 0.66% ) (82.85%)
199538509 stalled-cycles-frontend # 12.45% frontend cycles idle ( +- 2.40% ) (83.10%)
402249109 stalled-cycles-backend # 25.09% backend cycles idle ( +- 1.19% ) (34.05%)
1847783963 instructions # 1.15 insn per cycle
# 0.22 stalled cycles per insn ( +- 0.18% ) (50.64%)
407162722 branches # 1018925730.631 M/sec ( +- 0.12% ) (67.02%)
10932779 branch-misses # 2.69% of all branches ( +- 0.51% ) (83.28%)
0.40077 +- 0.00267 seconds time elapsed ( +- 0.67% )
lebedevri@pini-pini:/build/llvm-build-Clang-release$ perf stat -r 9 ./bin/llvm-exegesis -mode=analysis -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-latency.yml -analysis-inconsistencies-output-file=/tmp/clusters-new.html
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 50572 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-new.html'
...
Performance counter stats for './bin/llvm-exegesis -mode=analysis -benchmarks-file=/home/lebedevri/PileDriver-Sched/benchmarks-latency.yml -analysis-inconsistencies-output-file=/tmp/clusters-new.html' (9 runs):
6947.79 msec task-clock # 1.000 CPUs utilized ( +- 0.90% )
217 context-switches # 31.236 M/sec ( +- 36.16% )
1 cpu-migrations # 0.096 M/sec ( +- 50.00% )
13258 page-faults # 1908.389 M/sec ( +- 0.34% )
27830796523 cycles # 4006032.286 GHz ( +- 0.89% ) (83.30%)
1504554006 stalled-cycles-frontend # 5.41% frontend cycles idle ( +- 2.10% ) (83.32%)
16716574843 stalled-cycles-backend # 60.07% backend cycles idle ( +- 0.65% ) (33.38%)
17755545931 instructions # 0.64 insn per cycle
# 0.94 stalled cycles per insn ( +- 0.09% ) (50.04%)
3897255686 branches # 560980426.597 M/sec ( +- 0.06% ) (66.70%)
117045395 branch-misses # 3.00% of all branches ( +- 0.47% ) (83.34%)
6.9507 +- 0.0627 seconds time elapsed ( +- 0.90% )
```
I.e. it's +2.6% slowdown for one whole sweep, or +2% for 5 whole sweeps.
Within noise i'd say.
Should help with [[ https://bugs.llvm.org/show_bug.cgi?id=40787 | PR40787 ]].
Reviewers: courbet, gchatelet
Reviewed By: courbet
Subscribers: tschuett, RKSimon, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D58476
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@354767 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Roman Lebedev
parent
975c87172a
commit
5e1169bafb
@ -219,11 +219,16 @@ OPTIONS
|
||||
Specify the numPoints parameters to be used for DBSCAN clustering
|
||||
(`analysis` mode).
|
||||
|
||||
.. option:: -analysis-epsilon=<dbscan epsilon parameter>
|
||||
.. option:: -analysis-clustering-epsilon=<dbscan epsilon parameter>
|
||||
|
||||
Specify the numPoints parameters to be used for DBSCAN clustering
|
||||
Specify the epsilon parameter used for clustering of benchmark points
|
||||
(`analysis` mode).
|
||||
|
||||
.. option:: -analysis-inconsistency-epsilon=<epsilon>
|
||||
|
||||
Specify the epsilon parameter used for detection of when the cluster
|
||||
is different from the LLVM schedule profile values (`analysis` mode).
|
||||
|
||||
.. option:: -analysis-display-unstable-clusters
|
||||
|
||||
If there is more than one benchmark for an opcode, said benchmarks may end up
|
||||
|
||||
@ -1,6 +1,6 @@
|
||||
# RUN: llvm-exegesis -mode=analysis -benchmarks-file=%s -analysis-clusters-output-file=- -analysis-epsilon=0.1 -analysis-numpoints=1 | FileCheck -check-prefixes=CHECK-CLUSTERS %s
|
||||
# RUN: llvm-exegesis -mode=analysis -benchmarks-file=%s -analysis-inconsistencies-output-file=- -analysis-epsilon=0.5 -analysis-numpoints=1 | FileCheck -check-prefixes=CHECK-INCONSISTENCIES-ALL,CHECK-INCONSISTENCIES-STABLE %s
|
||||
# RUN: llvm-exegesis -mode=analysis -benchmarks-file=%s -analysis-inconsistencies-output-file=- -analysis-epsilon=0.5 -analysis-display-unstable-clusters -analysis-numpoints=1 | FileCheck -check-prefixes=CHECK-INCONSISTENCIES-ALL,CHECK-INCONSISTENCIES-UNSTABLE %s
|
||||
# RUN: llvm-exegesis -mode=analysis -benchmarks-file=%s -analysis-clusters-output-file=- -analysis-clustering-epsilon=0.1 -analysis-inconsistency-epsilon=0.1 -analysis-numpoints=1 | FileCheck -check-prefixes=CHECK-CLUSTERS %s
|
||||
# RUN: llvm-exegesis -mode=analysis -benchmarks-file=%s -analysis-inconsistencies-output-file=- -analysis-clustering-epsilon=0.5 -analysis-inconsistency-epsilon=0.5 -analysis-numpoints=1 | FileCheck -check-prefixes=CHECK-INCONSISTENCIES-ALL,CHECK-INCONSISTENCIES-STABLE %s
|
||||
# RUN: llvm-exegesis -mode=analysis -benchmarks-file=%s -analysis-inconsistencies-output-file=- -analysis-clustering-epsilon=0.5 -analysis-inconsistency-epsilon=0.5 -analysis-display-unstable-clusters -analysis-numpoints=1 | FileCheck -check-prefixes=CHECK-INCONSISTENCIES-ALL,CHECK-INCONSISTENCIES-UNSTABLE %s
|
||||
|
||||
# We have one ADD32rr measurement, and two measurements for SQRTSSr.
|
||||
# The ADD32rr measurement and one of the SQRTSSr measurements are identical,
|
||||
|
||||
63
test/tools/llvm-exegesis/X86/analysis-epsilons.test
Normal file
63
test/tools/llvm-exegesis/X86/analysis-epsilons.test
Normal file
@ -0,0 +1,63 @@
|
||||
# RUN: llvm-exegesis -mode=analysis -benchmarks-file=%s -analysis-clusters-output-file=- -analysis-clustering-epsilon=9 -analysis-inconsistency-epsilon=0.1 -analysis-numpoints=1 | FileCheck -check-prefixes=CHECK-CLUSTERS-ALL,CHECK-CLUSTERS-TWO %s
|
||||
# RUN: llvm-exegesis -mode=analysis -benchmarks-file=%s -analysis-clusters-output-file=- -analysis-clustering-epsilon=9 -analysis-inconsistency-epsilon=100 -analysis-numpoints=1 | FileCheck -check-prefixes=CHECK-CLUSTERS-ALL,CHECK-CLUSTERS-TWO %s
|
||||
# RUN: llvm-exegesis -mode=analysis -benchmarks-file=%s -analysis-clusters-output-file=- -analysis-clustering-epsilon=10 -analysis-inconsistency-epsilon=0.1 -analysis-numpoints=1 | FileCheck -check-prefixes=CHECK-CLUSTERS-ALL,CHECK-CLUSTERS-ONE %s
|
||||
# RUN: llvm-exegesis -mode=analysis -benchmarks-file=%s -analysis-clusters-output-file=- -analysis-clustering-epsilon=10 -analysis-inconsistency-epsilon=100 -analysis-numpoints=1 | FileCheck -check-prefixes=CHECK-CLUSTERS-ALL,CHECK-CLUSTERS-ONE %s
|
||||
|
||||
# RUN: llvm-exegesis -mode=analysis -benchmarks-file=%s -analysis-inconsistencies-output-file=- -analysis-clustering-epsilon=9 -analysis-inconsistency-epsilon=0.1 -analysis-numpoints=1 | FileCheck -check-prefixes=CHECK-INCONSISTENCIES-FAIL %s
|
||||
# RUN: llvm-exegesis -mode=analysis -benchmarks-file=%s -analysis-inconsistencies-output-file=- -analysis-clustering-epsilon=10 -analysis-inconsistency-epsilon=0.1 -analysis-numpoints=1 | FileCheck -check-prefixes=CHECK-INCONSISTENCIES-FAIL %s
|
||||
# RUN: llvm-exegesis -mode=analysis -benchmarks-file=%s -analysis-inconsistencies-output-file=- -analysis-clustering-epsilon=9 -analysis-inconsistency-epsilon=100 -analysis-numpoints=1 | FileCheck -check-prefixes=CHECK-INCONSISTENCIES-PASS %s
|
||||
# RUN: llvm-exegesis -mode=analysis -benchmarks-file=%s -analysis-inconsistencies-output-file=- -analysis-clustering-epsilon=10 -analysis-inconsistency-epsilon=100 -analysis-numpoints=1 | FileCheck -check-prefixes=CHECK-INCONSISTENCIES-PASS %s
|
||||
|
||||
# CHECK-CLUSTERS-ALL: {{^}}cluster_id,opcode_name,config,sched_class,latency{{$}}
|
||||
|
||||
# CHECK-CLUSTERS-TWO: {{^}}0,
|
||||
# CHECK-CLUSTERS-TWO-SAME: ,90.00{{$}}
|
||||
# CHECK-CLUSTERS-TWO: {{^}}1,
|
||||
# CHECK-CLUSTERS-TWO-SAME: ,100.00{{$}}
|
||||
|
||||
# CHECK-CLUSTERS-ONE: {{^}}0,
|
||||
# CHECK-CLUSTERS-ONE-SAME: ,90.00{{$}}
|
||||
# CHECK-CLUSTERS-ONE-NEXT: {{^}}0,
|
||||
# CHECK-CLUSTERS-ONE-SAME: ,100.00{{$}}
|
||||
|
||||
# CHECK-INCONSISTENCIES-FAIL: contains instructions whose performance characteristics do not match that of LLVM
|
||||
# CHECK-INCONSISTENCIES-FAIL: contains instructions whose performance characteristics do not match that of LLVM
|
||||
# CHECK-INCONSISTENCIES-FAIL-NOT: contains instructions whose performance characteristics do not match that of LLVM
|
||||
|
||||
# CHECK-INCONSISTENCIES-PASS-NOT: contains instructions whose performance characteristics do not match that of LLVM
|
||||
|
||||
---
|
||||
mode: latency
|
||||
key:
|
||||
instructions:
|
||||
- 'ADD32rr EDX EDX EAX'
|
||||
config: ''
|
||||
register_initial_values:
|
||||
- 'EDX=0x0'
|
||||
- 'EAX=0x0'
|
||||
cpu_name: bdver2
|
||||
llvm_triple: x86_64-unknown-linux-gnu
|
||||
num_repetitions: 10000
|
||||
measurements:
|
||||
- { key: latency, value: 90, per_snippet_value: 90 }
|
||||
error: ''
|
||||
info: Repeating a single implicitly serial instruction
|
||||
assembled_snippet: BA00000000B80000000001C201C201C201C201C201C201C201C201C201C201C201C201C201C201C201C2C3
|
||||
...
|
||||
---
|
||||
mode: latency
|
||||
key:
|
||||
instructions:
|
||||
- 'SQRTSSr XMM11 XMM11'
|
||||
config: ''
|
||||
register_initial_values:
|
||||
- 'XMM11=0x0'
|
||||
cpu_name: bdver2
|
||||
llvm_triple: x86_64-unknown-linux-gnu
|
||||
num_repetitions: 10000
|
||||
measurements:
|
||||
- { key: latency, value: 100, per_snippet_value: 100 }
|
||||
error: ''
|
||||
info: Repeating a single explicitly serial instruction
|
||||
assembled_snippet: 4883EC10C7042400000000C744240400000000C744240800000000C744240C00000000C57A6F1C244883C410F3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBF3450F51DBC3
|
||||
...
|
||||
@ -170,8 +170,11 @@ void Analysis::printInstructionRowCsv(const size_t PointId,
|
||||
Analysis::Analysis(const llvm::Target &Target,
|
||||
std::unique_ptr<llvm::MCInstrInfo> InstrInfo,
|
||||
const InstructionBenchmarkClustering &Clustering,
|
||||
double AnalysisInconsistencyEpsilon,
|
||||
bool AnalysisDisplayUnstableOpcodes)
|
||||
: Clustering_(Clustering), InstrInfo_(std::move(InstrInfo)),
|
||||
AnalysisInconsistencyEpsilonSquared_(AnalysisInconsistencyEpsilon *
|
||||
AnalysisInconsistencyEpsilon),
|
||||
AnalysisDisplayUnstableOpcodes_(AnalysisDisplayUnstableOpcodes) {
|
||||
if (Clustering.getPoints().empty())
|
||||
return;
|
||||
@ -301,7 +304,8 @@ void Analysis::printSchedClassClustersHtml(
|
||||
OS << "</tr>";
|
||||
for (const SchedClassCluster &Cluster : Clusters) {
|
||||
OS << "<tr class=\""
|
||||
<< (Cluster.measurementsMatch(*SubtargetInfo_, RSC, Clustering_)
|
||||
<< (Cluster.measurementsMatch(*SubtargetInfo_, RSC, Clustering_,
|
||||
AnalysisInconsistencyEpsilonSquared_)
|
||||
? "good-cluster"
|
||||
: "bad-cluster")
|
||||
<< "\"><td>";
|
||||
@ -461,7 +465,8 @@ static unsigned findProcResIdx(const llvm::MCSubtargetInfo &STI,
|
||||
|
||||
bool Analysis::SchedClassCluster::measurementsMatch(
|
||||
const llvm::MCSubtargetInfo &STI, const ResolvedSchedClass &RSC,
|
||||
const InstructionBenchmarkClustering &Clustering) const {
|
||||
const InstructionBenchmarkClustering &Clustering,
|
||||
const double AnalysisInconsistencyEpsilonSquared_) const {
|
||||
const size_t NumMeasurements = Representative.size();
|
||||
std::vector<BenchmarkMeasure> ClusterCenterPoint(NumMeasurements);
|
||||
std::vector<BenchmarkMeasure> SchedClassPoint(NumMeasurements);
|
||||
@ -520,7 +525,8 @@ bool Analysis::SchedClassCluster::measurementsMatch(
|
||||
llvm_unreachable("unimplemented measurement matching mode");
|
||||
return false;
|
||||
}
|
||||
return Clustering.isNeighbour(ClusterCenterPoint, SchedClassPoint);
|
||||
return Clustering.isNeighbour(ClusterCenterPoint, SchedClassPoint,
|
||||
AnalysisInconsistencyEpsilonSquared_);
|
||||
}
|
||||
|
||||
void Analysis::printSchedClassDescHtml(const ResolvedSchedClass &RSC,
|
||||
@ -689,7 +695,8 @@ llvm::Error Analysis::run<Analysis::PrintSchedClassInconsistencies>(
|
||||
if (llvm::all_of(SchedClassClusters,
|
||||
[this, &RSCAndPoints](const SchedClassCluster &C) {
|
||||
return C.measurementsMatch(
|
||||
*SubtargetInfo_, RSCAndPoints.RSC, Clustering_);
|
||||
*SubtargetInfo_, RSCAndPoints.RSC, Clustering_,
|
||||
AnalysisInconsistencyEpsilonSquared_);
|
||||
}))
|
||||
continue; // Nothing weird.
|
||||
|
||||
|
||||
@ -38,6 +38,7 @@ public:
|
||||
Analysis(const llvm::Target &Target,
|
||||
std::unique_ptr<llvm::MCInstrInfo> InstrInfo,
|
||||
const InstructionBenchmarkClustering &Clustering,
|
||||
double AnalysisInconsistencyEpsilon,
|
||||
bool AnalysisDisplayUnstableOpcodes);
|
||||
|
||||
// Prints a csv of instructions for each cluster.
|
||||
@ -81,7 +82,8 @@ private:
|
||||
bool
|
||||
measurementsMatch(const llvm::MCSubtargetInfo &STI,
|
||||
const ResolvedSchedClass &SC,
|
||||
const InstructionBenchmarkClustering &Clustering) const;
|
||||
const InstructionBenchmarkClustering &Clustering,
|
||||
const double AnalysisInconsistencyEpsilonSquared_) const;
|
||||
|
||||
void addPoint(size_t PointId,
|
||||
const InstructionBenchmarkClustering &Clustering);
|
||||
@ -127,6 +129,7 @@ private:
|
||||
std::unique_ptr<llvm::MCAsmInfo> AsmInfo_;
|
||||
std::unique_ptr<llvm::MCInstPrinter> InstPrinter_;
|
||||
std::unique_ptr<llvm::MCDisassembler> Disasm_;
|
||||
const double AnalysisInconsistencyEpsilonSquared_;
|
||||
const bool AnalysisDisplayUnstableOpcodes_;
|
||||
};
|
||||
|
||||
|
||||
@ -46,7 +46,8 @@ void InstructionBenchmarkClustering::rangeQuery(
|
||||
const auto &PMeasurements = Points_[P].Measurements;
|
||||
if (PMeasurements.empty()) // Error point.
|
||||
continue;
|
||||
if (isNeighbour(PMeasurements, QMeasurements)) {
|
||||
if (isNeighbour(PMeasurements, QMeasurements,
|
||||
AnalysisClusteringEpsilonSquared_)) {
|
||||
Neighbors.push_back(P);
|
||||
}
|
||||
}
|
||||
@ -54,8 +55,9 @@ void InstructionBenchmarkClustering::rangeQuery(
|
||||
|
||||
InstructionBenchmarkClustering::InstructionBenchmarkClustering(
|
||||
const std::vector<InstructionBenchmark> &Points,
|
||||
const double EpsilonSquared)
|
||||
: Points_(Points), EpsilonSquared_(EpsilonSquared),
|
||||
const double AnalysisClusteringEpsilonSquared)
|
||||
: Points_(Points),
|
||||
AnalysisClusteringEpsilonSquared_(AnalysisClusteringEpsilonSquared),
|
||||
NoiseCluster_(ClusterId::noise()), ErrorCluster_(ClusterId::error()) {}
|
||||
|
||||
llvm::Error InstructionBenchmarkClustering::validateAndSetup() {
|
||||
@ -245,8 +247,10 @@ void InstructionBenchmarkClustering::stabilize(unsigned NumOpcodes) {
|
||||
llvm::Expected<InstructionBenchmarkClustering>
|
||||
InstructionBenchmarkClustering::create(
|
||||
const std::vector<InstructionBenchmark> &Points, const size_t MinPts,
|
||||
const double Epsilon, llvm::Optional<unsigned> NumOpcodes) {
|
||||
InstructionBenchmarkClustering Clustering(Points, Epsilon * Epsilon);
|
||||
const double AnalysisClusteringEpsilon,
|
||||
llvm::Optional<unsigned> NumOpcodes) {
|
||||
InstructionBenchmarkClustering Clustering(
|
||||
Points, AnalysisClusteringEpsilon * AnalysisClusteringEpsilon);
|
||||
if (auto Error = Clustering.validateAndSetup()) {
|
||||
return std::move(Error);
|
||||
}
|
||||
|
||||
@ -29,7 +29,8 @@ public:
|
||||
// for more explanations on the algorithm.
|
||||
static llvm::Expected<InstructionBenchmarkClustering>
|
||||
create(const std::vector<InstructionBenchmark> &Points, size_t MinPts,
|
||||
double Epsilon, llvm::Optional<unsigned> NumOpcodes = llvm::None);
|
||||
double AnalysisClusteringEpsilon,
|
||||
llvm::Optional<unsigned> NumOpcodes = llvm::None);
|
||||
|
||||
class ClusterId {
|
||||
public:
|
||||
@ -103,7 +104,8 @@ public:
|
||||
|
||||
// Returns true if the given point is within a distance Epsilon of each other.
|
||||
bool isNeighbour(const std::vector<BenchmarkMeasure> &P,
|
||||
const std::vector<BenchmarkMeasure> &Q) const {
|
||||
const std::vector<BenchmarkMeasure> &Q,
|
||||
const double EpsilonSquared_) const {
|
||||
double DistanceSquared = 0.0;
|
||||
for (size_t I = 0, E = P.size(); I < E; ++I) {
|
||||
const auto Diff = P[I].PerInstructionValue - Q[I].PerInstructionValue;
|
||||
@ -114,7 +116,8 @@ public:
|
||||
|
||||
private:
|
||||
InstructionBenchmarkClustering(
|
||||
const std::vector<InstructionBenchmark> &Points, double EpsilonSquared);
|
||||
const std::vector<InstructionBenchmark> &Points,
|
||||
double AnalysisClusteringEpsilonSquared);
|
||||
|
||||
llvm::Error validateAndSetup();
|
||||
void dbScan(size_t MinPts);
|
||||
@ -122,7 +125,7 @@ private:
|
||||
void rangeQuery(size_t Q, std::vector<size_t> &Scratchpad) const;
|
||||
|
||||
const std::vector<InstructionBenchmark> &Points_;
|
||||
const double EpsilonSquared_;
|
||||
const double AnalysisClusteringEpsilonSquared_;
|
||||
int NumDimensions_ = 0;
|
||||
// ClusterForPoint_[P] is the cluster id for Points[P].
|
||||
std::vector<ClusterId> ClusterIdForPoint_;
|
||||
|
||||
@ -84,10 +84,15 @@ static cl::opt<unsigned> AnalysisNumPoints(
|
||||
"analysis-numpoints",
|
||||
cl::desc("minimum number of points in an analysis cluster"), cl::init(3));
|
||||
|
||||
static cl::opt<float>
|
||||
AnalysisEpsilon("analysis-epsilon",
|
||||
cl::desc("dbscan epsilon for analysis clustering"),
|
||||
cl::init(0.1));
|
||||
static cl::opt<float> AnalysisClusteringEpsilon(
|
||||
"analysis-clustering-epsilon",
|
||||
cl::desc("dbscan epsilon for benchmark point clustering"), cl::init(0.1));
|
||||
|
||||
static cl::opt<float> AnalysisInconsistencyEpsilon(
|
||||
"analysis-inconsistency-epsilon",
|
||||
cl::desc("epsilon for detection of when the cluster is different from the "
|
||||
"LLVM schedule profile values"),
|
||||
cl::init(0.1));
|
||||
|
||||
static cl::opt<std::string>
|
||||
AnalysisClustersOutputFile("analysis-clusters-output-file", cl::desc(""),
|
||||
@ -444,9 +449,11 @@ static void analysisMain() {
|
||||
std::unique_ptr<llvm::MCInstrInfo> InstrInfo(TheTarget->createMCInstrInfo());
|
||||
|
||||
const auto Clustering = ExitOnErr(InstructionBenchmarkClustering::create(
|
||||
Points, AnalysisNumPoints, AnalysisEpsilon, InstrInfo->getNumOpcodes()));
|
||||
Points, AnalysisNumPoints, AnalysisClusteringEpsilon,
|
||||
InstrInfo->getNumOpcodes()));
|
||||
|
||||
const Analysis Analyzer(*TheTarget, std::move(InstrInfo), Clustering,
|
||||
AnalysisInconsistencyEpsilon,
|
||||
AnalysisDisplayUnstableOpcodes);
|
||||
|
||||
maybeRunAnalysis<Analysis::PrintClusters>(Analyzer, "analysis clusters",
|
||||
|
||||
Loading…
Reference in New Issue
Block a user