[llvm] r353024 - [llvm-exegesis] Cut run time of analysis mode by -84% (*sic*) (YamlContext::getInstrOpcode())

Roman Lebedev via llvm-commits llvm-commits at lists.llvm.org
Mon Feb 4 01:12:21 PST 2019


Author: lebedevri
Date: Mon Feb  4 01:12:21 2019
New Revision: 353024

URL: http://llvm.org/viewvc/llvm-project?rev=353024&view=rev
Log:
[llvm-exegesis] Cut run time of analysis mode by -84% (*sic*) (YamlContext::getInstrOpcode())

Summary:
```
$ perf stat -r 9 ./bin/llvm-exegesis -mode=analysis -analysis-epsilon=1.0 -benchmarks-file=/tmp/benchmarks-inverse_throughput-onefull.yaml -analysis-clusters-output-file="" -analysis-inconsistencies-output-file=/tmp/clusters-old.html
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 14656 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-old.html'
...
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 14656 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-old.html'

 Performance counter stats for './bin/llvm-exegesis -mode=analysis -analysis-epsilon=1.0 -benchmarks-file=/tmp/benchmarks-inverse_throughput-onefull.yaml -analysis-clusters-output-file= -analysis-inconsistencies-output-file=/tmp/clusters-old.html' (9 runs):

           9465.46 msec task-clock                #    1.000 CPUs utilized            ( +-  0.05% )
                60      context-switches          #    6.363 M/sec                    ( +- 79.45% )
                 0      cpu-migrations            #    0.000 K/sec
             11364      page-faults               # 1200.697 M/sec                    ( +-  0.60% )
       37935623543      cycles                    # 4008083.912 GHz                   ( +-  0.05% )  (83.32%)
        2371625356      stalled-cycles-frontend   #    6.25% frontend cycles idle     ( +-  0.37% )  (83.32%)
        8476077875      stalled-cycles-backend    #   22.34% backend cycles idle      ( +-  0.18% )  (33.36%)
       41822439158      instructions              #    1.10  insn per cycle
                                                  #    0.20  stalled cycles per insn  ( +-  0.02% )  (50.03%)
       11607658944      branches                  # 1226405861.486 M/sec              ( +-  0.01% )  (66.69%)
         210864633      branch-misses             #    1.82% of all branches          ( +-  0.06% )  (83.34%)

           9.46636 +- 0.00441 seconds time elapsed  ( +-  0.05% )
```
```
$ perf stat -r 9 ./bin/llvm-exegesis -mode=analysis -analysis-epsilon=1.0 -benchmarks-file=/tmp/benchmarks-inverse_throughput-onefull.yaml -analysis-clusters-output-file="" -analysis-inconsistencies-output-file=/tmp/clusters-bew.html
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 14656 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-bew.html'
...
no exegesis target for x86_64-unknown-linux-gnu, using default
Parsed 14656 benchmark points
Printing sched class consistency analysis results to file '/tmp/clusters-bew.html'

 Performance counter stats for './bin/llvm-exegesis -mode=analysis -analysis-epsilon=1.0 -benchmarks-file=/tmp/benchmarks-inverse_throughput-onefull.yaml -analysis-clusters-output-file= -analysis-inconsistencies-output-file=/tmp/clusters-bew.html' (9 runs):

           1480.66 msec task-clock                #    1.000 CPUs utilized            ( +-  0.19% )
                13      context-switches          #    8.483 M/sec                    ( +- 83.10% )
                 0      cpu-migrations            #    0.075 M/sec                    ( +-100.00% )
             11596      page-faults               # 7834.247 M/sec                    ( +-  0.59% )
        5933732194      cycles                    # 4008977.535 GHz                   ( +-  0.19% )  (83.22%)
         438111928      stalled-cycles-frontend   #    7.38% frontend cycles idle     ( +-  0.37% )  (83.25%)
        1454969705      stalled-cycles-backend    #   24.52% backend cycles idle      ( +-  0.94% )  (33.53%)
        7724218604      instructions              #    1.30  insn per cycle
                                                  #    0.19  stalled cycles per insn  ( +-  0.07% )  (50.14%)
        1979796413      branches                  # 1337599858.945 M/sec              ( +-  0.06% )  (66.74%)
          32641638      branch-misses             #    1.65% of all branches          ( +-  0.18% )  (83.31%)

           1.48128 +- 0.00284 seconds time elapsed  ( +-  0.19% )

$ sha512sum /tmp/clusters-*
db4bbd904fe8840853b589b032c5041bc060b91bcd9c27b914b56581fbc473550eea74b852238c79963b5adf2419f379e9f5db76784048b48e3937f9f3e732bf  /tmp/clusters-bew.html
db4bbd904fe8840853b589b032c5041bc060b91bcd9c27b914b56581fbc473550eea74b852238c79963b5adf2419f379e9f5db76784048b48e3937f9f3e732bf  /tmp/clusters-old.html
```

Reviewers: courbet, gchatelet

Reviewed By: courbet

Subscribers: tschuett, llvm-commits, RKSimon

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D57657

Modified:
    llvm/trunk/tools/llvm-exegesis/lib/BenchmarkResult.cpp

Modified: llvm/trunk/tools/llvm-exegesis/lib/BenchmarkResult.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/tools/llvm-exegesis/lib/BenchmarkResult.cpp?rev=353024&r1=353023&r2=353024&view=diff
==============================================================================
--- llvm/trunk/tools/llvm-exegesis/lib/BenchmarkResult.cpp (original)
+++ llvm/trunk/tools/llvm-exegesis/lib/BenchmarkResult.cpp Mon Feb  4 01:12:21 2019
@@ -9,8 +9,9 @@
 #include "BenchmarkResult.h"
 #include "BenchmarkRunner.h"
 #include "llvm/ADT/STLExtras.h"
-#include "llvm/ADT/bit.h"
+#include "llvm/ADT/StringMap.h"
 #include "llvm/ADT/StringRef.h"
+#include "llvm/ADT/bit.h"
 #include "llvm/ObjectYAML/YAML.h"
 #include "llvm/Support/FileOutputBuffer.h"
 #include "llvm/Support/FileSystem.h"
@@ -29,7 +30,18 @@ namespace {
 // serialization process to encode/decode registers and instructions.
 struct YamlContext {
   YamlContext(const exegesis::LLVMState &State)
-      : State(&State), ErrorStream(LastError) {}
+      : State(&State), ErrorStream(LastError),
+        OpcodeNameToOpcodeIdx(
+            generateOpcodeNameToOpcodeIdxMapping(State.getInstrInfo())) {}
+
+  static llvm::StringMap<unsigned>
+  generateOpcodeNameToOpcodeIdxMapping(const llvm::MCInstrInfo &InstrInfo) {
+    llvm::StringMap<unsigned> Map(InstrInfo.getNumOpcodes());
+    for (unsigned I = 0, E = InstrInfo.getNumOpcodes(); I < E; ++I)
+      Map[InstrInfo.getName(I)] = I;
+    assert(Map.size() == InstrInfo.getNumOpcodes() && "Size prediction failed");
+    return Map;
+  };
 
   void serializeMCInst(const llvm::MCInst &MCInst, llvm::raw_ostream &OS) {
     OS << getInstrName(MCInst.getOpcode());
@@ -136,10 +148,9 @@ private:
   }
 
   unsigned getInstrOpcode(llvm::StringRef InstrName) {
-    const llvm::MCInstrInfo &InstrInfo = State->getInstrInfo();
-    for (unsigned E = InstrInfo.getNumOpcodes(), I = 0; I < E; ++I)
-      if (InstrInfo.getName(I) == InstrName)
-        return I;
+    auto Iter = OpcodeNameToOpcodeIdx.find(InstrName);
+    if (Iter != OpcodeNameToOpcodeIdx.end())
+      return Iter->second;
     ErrorStream << "No opcode with name " << InstrName;
     return 0;
   }
@@ -147,6 +158,7 @@ private:
   const llvm::exegesis::LLVMState *State;
   std::string LastError;
   llvm::raw_string_ostream ErrorStream;
+  const llvm::StringMap<unsigned> OpcodeNameToOpcodeIdx;
 };
 } // namespace
 




More information about the llvm-commits mailing list