Created
November 1, 2023 14:03
-
-
Save ChrisHegarty/508bb1857cb50df0d757f711c81fd740 to your computer and use it in GitHub Desktop.
VectorUtilBenchmark.binaryDotProductScalar- #12743
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
davekim$ sudo /home/chegar/binaries/jdk-21.0.1/bin/java -XX:+UnlockDiagnosticVMOptions -jar lucene/benchmark-jmh/build/benchmarks/lucene-benchmark-jmh-10.0.0-SNAPSHOT.jar .*binaryDotProductScalar.* -psize=1024 -prof 'perfasm:intelSyntax=true' | |
# JMH version: 1.37 | |
# VM version: JDK 21.0.1, OpenJDK 64-Bit Server VM, 21.0.1+12-29 | |
# VM invoker: /home/chegar/binaries/jdk-21.0.1/bin/java | |
# VM options: -XX:+UnlockDiagnosticVMOptions | |
# Blackhole mode: compiler (auto-detected, use -Djmh.blackhole.autoDetect=false to disable) | |
# Warmup: 3 iterations, 3 s each | |
# Measurement: 5 iterations, 3 s each | |
# Timeout: 10 min per iteration | |
# Threads: 1 thread, will synchronize iterations | |
# Benchmark mode: Throughput, ops/time | |
# Benchmark: org.apache.lucene.benchmark.jmh.VectorUtilBenchmark.binaryDotProductScalar | |
# Parameters: (size = 1024) | |
# Run progress: 0.00% complete, ETA 00:00:24 | |
# Fork: 1 of 1 | |
# Preparing profilers: LinuxPerfAsmProfiler | |
# Profilers consume stdout and stderr from target VM, use -v EXTRA to copy to console | |
# Warmup Iteration 1: Nov 01, 2023 1:53:27 PM org.apache.lucene.internal.vectorization.VectorizationProvider lookup | |
WARNING: Java vector incubator module is not readable. For optimal vector performance, pass '--add-modules jdk.incubator.vector' to enable Vector API. | |
2.505 ops/us | |
# Warmup Iteration 2: 2.674 ops/us | |
# Warmup Iteration 3: 2.813 ops/us | |
Iteration 1: 2.810 ops/us | |
Iteration 2: 2.816 ops/us | |
Iteration 3: 2.814 ops/us | |
Iteration 4: 2.816 ops/us | |
Iteration 5: 2.815 ops/us | |
# Processing profiler results: LinuxPerfAsmProfiler | |
Result "org.apache.lucene.benchmark.jmh.VectorUtilBenchmark.binaryDotProductScalar": | |
2.814 ±(99.9%) 0.010 ops/us [Average] | |
(min, avg, max) = (2.810, 2.814, 2.816), stdev = 0.003 | |
CI (99.9%): [2.804, 2.824] (assumes normal distribution) | |
Secondary result "org.apache.lucene.benchmark.jmh.VectorUtilBenchmark.binaryDotProductScalar:asm": | |
PrintAssembly processed: 149072 total address lines. | |
Perf output processed (skipped 10.433 seconds): | |
Column 1: cycles (15173 events) | |
Hottest code regions (>10.00% "cycles" events): | |
Event counts are percents of total event count. | |
....[Hottest Region 1].............................................................................. | |
c2, level 4, org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub, version 5, compile id 667 | |
0x00007f5594510252: movzx r10d,BYTE PTR [rdx+0x94] ; implicit exception: dispatches to 0x00007f5594510b18 | |
;*getfield isDone {reexecute=0 rethrow=0 return_oop=0} | |
; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@30 (line 146) | |
0x00007f559451025a: test r10d,r10d | |
╭ 0x00007f559451025d: jne 0x00007f5594510767 ;*ifeq {reexecute=0 rethrow=0 return_oop=0} | |
│ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@33 (line 146) | |
│ 0x00007f5594510263: mov ebx,0x1 | |
│╭ 0x00007f5594510268: jmp 0x00007f559451062f | |
││ 0x00007f559451026d: mov r10d,ebp | |
││ 0x00007f5594510270: jmp 0x00007f5594510220 | |
0.02% ││↗ 0x00007f5594510272: mov r13d,esi ;*iload_3 {reexecute=0 rethrow=0 return_oop=0} | |
│││ ; - org.apache.lucene.internal.vectorization.DefaultVectorUtilSupport::dotProduct@19 (line 147) | |
│││ ; - org.apache.lucene.util.VectorUtil::dotProduct@29 (line 151) | |
│││ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
│││ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
0.04% │││ ↗ 0x00007f5594510275: movsxd rax,DWORD PTR [rsp+0xc] ;*baload {reexecute=0 rethrow=0 return_oop=0} | |
│││ │ ; - org.apache.lucene.internal.vectorization.DefaultVectorUtilSupport::dotProduct@23 (line 147) | |
│││ │ ; - org.apache.lucene.util.VectorUtil::dotProduct@29 (line 151) | |
│││ │ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
│││ │ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
0.05% │││ │ 0x00007f559451027a: movsx r10d,BYTE PTR [rdx+rax*1+0x2e] | |
5.39% │││ │ 0x00007f5594510280: mov r14d,r10d | |
0.01% │││ │ 0x00007f5594510283: movsx r8d,BYTE PTR [rbx+rax*1+0x2b] | |
0.56% │││ │ 0x00007f5594510289: movsx r11d,BYTE PTR [rdx+rax*1+0x2b] | |
1.73% │││ │ 0x00007f559451028f: movsx ecx,BYTE PTR [rbx+rax*1+0x2a]; {no_reloc} | |
0.55% │││ │ 0x00007f5594510294: movsx r9d,BYTE PTR [rbx+rax*1+0x2e] | |
0.82% │││ │ 0x00007f559451029a: movsx r10d,BYTE PTR [rdx+rax*1+0x2a] | |
0.35% │││ │ 0x00007f55945102a0: vmovd xmm10,r10d | |
2.81% │││ │ 0x00007f55945102a5: movsx edi,BYTE PTR [rdx+rax*1+0x2f] | |
0.45% │││ │ 0x00007f55945102aa: movsx esi,BYTE PTR [rbx+rax*1+0x2f] | |
0.21% │││ │ 0x00007f55945102af: movsx ebp,BYTE PTR [rbx+rax*1+0x26] | |
0.27% │││ │ 0x00007f55945102b4: movsx r10d,BYTE PTR [rdx+rax*1+0x2d] | |
1.16% │││ │ 0x00007f55945102ba: vmovd xmm9,r10d | |
1.61% │││ │ 0x00007f55945102bf: movsx r10d,BYTE PTR [rdx+rax*1+0x26] | |
0.07% │││ │ 0x00007f55945102c5: imul r10d,ebp | |
4.19% │││ │ 0x00007f55945102c9: mov DWORD PTR [rsp+0x5c],r10d | |
3.81% │││ │ 0x00007f55945102ce: movsx ebp,BYTE PTR [rbx+rax*1+0x27] | |
│││ │ 0x00007f55945102d3: mov DWORD PTR [rsp+0x58],ebp | |
│││ │ 0x00007f55945102d7: imul edi,esi | |
0.01% │││ │ 0x00007f55945102da: movsx r10d,BYTE PTR [rbx+rax*1+0x25] | |
0.01% │││ │ 0x00007f55945102e0: mov DWORD PTR [rsp+0x60],r10d | |
0.01% │││ │ 0x00007f55945102e5: vmovd r10d,xmm10 | |
0.03% │││ │ 0x00007f55945102ea: imul r10d,ecx | |
0.03% │││ │ 0x00007f55945102ee: mov esi,r10d | |
1.80% │││ │ 0x00007f55945102f1: movsx r10d,BYTE PTR [rbx+rax*1+0x24] | |
│││ │ 0x00007f55945102f7: mov DWORD PTR [rsp+0x64],r10d | |
0.01% │││ │ 0x00007f55945102fc: mov r10d,r14d | |
0.01% │││ │ 0x00007f55945102ff: imul r10d,r9d | |
0.01% │││ │ 0x00007f5594510303: movsx r9d,BYTE PTR [rbx+rax*1+0x23] | |
0.01% │││ │ 0x00007f5594510309: add r10d,edi | |
0.39% │││ │ 0x00007f559451030c: vmovd xmm10,r10d | |
0.01% │││ │ 0x00007f5594510311: movsx r10d,BYTE PTR [rdx+rax*1+0x23] | |
1.85% │││ │ 0x00007f5594510317: imul r10d,r9d | |
0.16% │││ │ 0x00007f559451031b: mov DWORD PTR [rsp+0x4],r10d | |
0.40% │││ │ 0x00007f5594510320: movsx r10d,BYTE PTR [rbx+rax*1+0x22] | |
0.01% │││ │ 0x00007f5594510326: mov DWORD PTR [rsp],r10d | |
│││ │ 0x00007f559451032a: imul r11d,r8d | |
│││ │ 0x00007f559451032e: movsx r8d,BYTE PTR [rbx+rax*1+0x1e] | |
0.34% │││ │ 0x00007f5594510334: lea r10d,[rsi+r11*1] | |
0.28% │││ │ 0x00007f5594510338: mov DWORD PTR [rsp+0x8],r10d | |
1.56% │││ │ 0x00007f559451033d: movsx r9d,BYTE PTR [rdx+rax*1+0x1e] | |
0.01% │││ │ 0x00007f5594510343: imul r9d,r8d | |
0.05% │││ │ 0x00007f5594510347: movsx r10d,BYTE PTR [rbx+rax*1+0x1f] | |
0.02% │││ │ 0x00007f559451034d: movsx r14d,BYTE PTR [rdx+rax*1+0x1f] | |
1.44% │││ │ 0x00007f5594510353: imul r14d,r10d | |
0.01% │││ │ 0x00007f5594510357: add r14d,r9d | |
0.77% │││ │ 0x00007f559451035a: movsx r11d,BYTE PTR [rbx+rax*1+0x1d] | |
0.01% │││ │ 0x00007f5594510360: movsx r10d,BYTE PTR [rdx+rax*1+0x1d] | |
0.21% │││ │ 0x00007f5594510366: imul r10d,r11d | |
│││ │ 0x00007f559451036a: movsx r8d,BYTE PTR [rbx+rax*1+0x1c] | |
0.38% │││ │ 0x00007f5594510370: movsx esi,BYTE PTR [rdx+rax*1+0x1c] | |
0.02% │││ │ 0x00007f5594510375: imul esi,r8d | |
1.72% │││ │ 0x00007f5594510379: add esi,r10d | |
1.57% │││ │ 0x00007f559451037c: movsx r10d,BYTE PTR [rbx+rax*1+0x1b] | |
0.32% │││ │ 0x00007f5594510382: movsx r11d,BYTE PTR [rdx+rax*1+0x1b] | |
0.01% │││ │ 0x00007f5594510388: imul r11d,r10d | |
0.63% │││ │ 0x00007f559451038c: movsx r9d,BYTE PTR [rbx+rax*1+0x1a]; {no_reloc} | |
0.72% │││ │ 0x00007f5594510392: movsx r10d,BYTE PTR [rdx+rax*1+0x1a] | |
0.32% │││ │ 0x00007f5594510398: imul r10d,r9d | |
0.01% │││ │ 0x00007f559451039c: add r10d,r11d | |
1.64% │││ │ 0x00007f559451039f: movsx r11d,BYTE PTR [rbx+rax*1+0x16] | |
0.10% │││ │ 0x00007f55945103a5: movsx r9d,BYTE PTR [rdx+rax*1+0x16] | |
0.09% │││ │ 0x00007f55945103ab: imul r9d,r11d | |
0.18% │││ │ 0x00007f55945103af: movsx r8d,BYTE PTR [rbx+rax*1+0x17] | |
1.30% │││ │ 0x00007f55945103b5: movsx r11d,BYTE PTR [rdx+rax*1+0x17] | |
0.11% │││ │ 0x00007f55945103bb: imul r11d,r8d | |
0.34% │││ │ 0x00007f55945103bf: add r11d,r9d | |
1.52% │││ │ 0x00007f55945103c2: movsx ecx,BYTE PTR [rbx+rax*1+0x15] | |
0.05% │││ │ 0x00007f55945103c7: movsx r8d,BYTE PTR [rdx+rax*1+0x15] | |
0.01% │││ │ 0x00007f55945103cd: imul r8d,ecx | |
0.44% │││ │ 0x00007f55945103d1: movsx ecx,BYTE PTR [rbx+rax*1+0x14] | |
1.17% │││ │ 0x00007f55945103d6: movsx r9d,BYTE PTR [rdx+rax*1+0x14] | |
0.16% │││ │ 0x00007f55945103dc: imul r9d,ecx | |
0.17% │││ │ 0x00007f55945103e0: add r9d,r8d | |
1.72% │││ │ 0x00007f55945103e3: movsx r8d,BYTE PTR [rbx+rax*1+0x13] | |
0.11% │││ │ 0x00007f55945103e9: movsx edi,BYTE PTR [rdx+rax*1+0x13] | |
│││ │ 0x00007f55945103ee: imul edi,r8d | |
0.20% │││ │ 0x00007f55945103f2: movsx ecx,BYTE PTR [rbx+rax*1+0x12] | |
1.44% │││ │ 0x00007f55945103f7: movsx r8d,BYTE PTR [rdx+rax*1+0x12] | |
0.16% │││ │ 0x00007f55945103fd: imul r8d,ecx | |
0.11% │││ │ 0x00007f5594510401: add r8d,edi | |
1.60% │││ │ 0x00007f5594510404: movsx ecx,BYTE PTR [rbx+rax*1+0x10] | |
0.03% │││ │ 0x00007f5594510409: movsx edi,BYTE PTR [rdx+rax*1+0x10] | |
0.28% │││ │ 0x00007f559451040e: imul edi,ecx | |
0.34% │││ │ 0x00007f5594510411: movsx ecx,BYTE PTR [rbx+rax*1+0x11] | |
1.44% │││ │ 0x00007f5594510416: movsx ebp,BYTE PTR [rdx+rax*1+0x11] | |
0.13% │││ │ 0x00007f559451041b: imul ebp,ecx | |
0.13% │││ │ 0x00007f559451041e: add ebp,edi | |
1.98% │││ │ 0x00007f5594510420: add ebp,r13d | |
1.93% │││ │ 0x00007f5594510423: add ebp,r8d | |
1.82% │││ │ 0x00007f5594510426: add ebp,r9d | |
2.01% │││ │ 0x00007f5594510429: add ebp,r11d | |
1.71% │││ │ 0x00007f559451042c: movsx r8d,BYTE PTR [rbx+rax*1+0x19] | |
0.02% │││ │ 0x00007f5594510432: movsx r11d,BYTE PTR [rdx+rax*1+0x19] | |
0.02% │││ │ 0x00007f5594510438: imul r11d,r8d | |
│││ │ 0x00007f559451043c: movsx ecx,BYTE PTR [rbx+rax*1+0x18] | |
0.03% │││ │ 0x00007f5594510441: movsx r9d,BYTE PTR [rdx+rax*1+0x18] | |
│││ │ 0x00007f5594510447: imul r9d,ecx | |
0.01% │││ │ 0x00007f559451044b: add r9d,r11d | |
0.01% │││ │ 0x00007f559451044e: add r9d,ebp | |
1.82% │││ │ 0x00007f5594510451: add r9d,r10d | |
1.92% │││ │ 0x00007f5594510454: add r9d,esi | |
1.77% │││ │ 0x00007f5594510457: add r9d,r14d | |
1.86% │││ │ 0x00007f559451045a: movsx r8d,BYTE PTR [rbx+rax*1+0x20] | |
0.01% │││ │ 0x00007f5594510460: movsx r10d,BYTE PTR [rdx+rax*1+0x20] | |
│││ │ 0x00007f5594510466: imul r10d,r8d | |
│││ │ 0x00007f559451046a: movsx r11d,BYTE PTR [rbx+rax*1+0x21] | |
0.02% │││ │ 0x00007f5594510470: movsx ecx,BYTE PTR [rdx+rax*1+0x21] | |
│││ │ 0x00007f5594510475: imul ecx,r11d | |
0.01% │││ │ 0x00007f5594510479: add ecx,r10d | |
0.02% │││ │ 0x00007f559451047c: add ecx,r9d | |
1.82% │││ │ 0x00007f559451047f: movsx r11d,BYTE PTR [rbx+rax*1+0x28] | |
│││ │ 0x00007f5594510485: movsx r10d,BYTE PTR [rdx+rax*1+0x28] | |
│││ │ 0x00007f559451048b: imul r10d,r11d ; {no_reloc} | |
│││ │ 0x00007f559451048f: movsx r8d,BYTE PTR [rbx+rax*1+0x29] | |
0.03% │││ │ 0x00007f5594510495: movsx r11d,BYTE PTR [rdx+rax*1+0x29] | |
│││ │ 0x00007f559451049b: imul r11d,r8d | |
0.01% │││ │ 0x00007f559451049f: add r11d,r10d | |
0.03% │││ │ 0x00007f55945104a2: movsx r10d,BYTE PTR [rbx+rax*1+0x2c] | |
1.85% │││ │ 0x00007f55945104a8: movsx edi,BYTE PTR [rdx+rax*1+0x2c] | |
0.02% │││ │ 0x00007f55945104ad: imul edi,r10d | |
│││ │ 0x00007f55945104b1: movsx r8d,BYTE PTR [rbx+rax*1+0x2d] | |
│││ │ 0x00007f55945104b7: vmovd r10d,xmm9 | |
0.01% │││ │ 0x00007f55945104bc: imul r10d,r8d | |
│││ │ 0x00007f55945104c0: add r10d,edi | |
0.01% │││ │ 0x00007f55945104c3: mov r9d,r10d | |
0.03% │││ │ 0x00007f55945104c6: movsx r10d,BYTE PTR [rdx+rax*1+0x27] | |
1.73% │││ │ 0x00007f55945104cc: imul r10d,DWORD PTR [rsp+0x58] | |
0.50% │││ │ 0x00007f55945104d2: add r10d,DWORD PTR [rsp+0x5c] | |
0.01% │││ │ 0x00007f55945104d7: movsx r8d,BYTE PTR [rdx+rax*1+0x25] | |
│││ │ 0x00007f55945104dd: imul r8d,DWORD PTR [rsp+0x60] | |
0.01% │││ │ 0x00007f55945104e3: movsx edi,BYTE PTR [rdx+rax*1+0x24] | |
│││ │ 0x00007f55945104e8: imul edi,DWORD PTR [rsp+0x64] | |
0.02% │││ │ 0x00007f55945104ed: movsx esi,BYTE PTR [rdx+rax*1+0x22] | |
0.02% │││ │ 0x00007f55945104f2: add edi,r8d | |
2.02% │││ │ 0x00007f55945104f5: imul esi,DWORD PTR [rsp] | |
0.24% │││ │ 0x00007f55945104f9: add esi,DWORD PTR [rsp+0x4] | |
0.05% │││ │ 0x00007f55945104fd: add ecx,esi | |
1.50% │││ │ 0x00007f55945104ff: add ecx,edi | |
1.92% │││ │ 0x00007f5594510501: add ecx,r10d | |
1.71% │││ │ 0x00007f5594510504: add r11d,ecx | |
1.71% │││ │ 0x00007f5594510507: add r11d,DWORD PTR [rsp+0x8] | |
2.07% │││ │ 0x00007f559451050c: add r9d,r11d | |
1.87% │││ │ 0x00007f559451050f: vmovd r10d,xmm10 | |
0.01% │││ │ 0x00007f5594510514: add r10d,r9d ;*iadd {reexecute=0 rethrow=0 return_oop=0} | |
│││ │ ; - org.apache.lucene.internal.vectorization.DefaultVectorUtilSupport::dotProduct@43 (line 147) | |
│││ │ ; - org.apache.lucene.util.VectorUtil::dotProduct@29 (line 151) | |
│││ │ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
│││ │ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
1.83% │││ │ 0x00007f5594510517: mov esi,r10d | |
│││ │ 0x00007f559451051a: mov r10d,DWORD PTR [rsp+0xc] | |
0.03% │││ │ 0x00007f559451051f: add r10d,0x20 ;*iinc {reexecute=0 rethrow=0 return_oop=0} | |
│││ │ ; - org.apache.lucene.internal.vectorization.DefaultVectorUtilSupport::dotProduct@45 (line 146) | |
│││ │ ; - org.apache.lucene.util.VectorUtil::dotProduct@29 (line 151) | |
│││ │ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
│││ │ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
│││ │ 0x00007f5594510523: mov DWORD PTR [rsp+0xc],r10d | |
0.03% │││ │ 0x00007f5594510528: cmp r10d,DWORD PTR [rsp+0x54] | |
││╰ │ 0x00007f559451052d: jl 0x00007f5594510272 ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0} | |
││ │ ; - org.apache.lucene.internal.vectorization.DefaultVectorUtilSupport::dotProduct@16 (line 146) | |
││ │ ; - org.apache.lucene.util.VectorUtil::dotProduct@29 (line 151) | |
││ │ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
││ │ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
││ │ 0x00007f5594510533: mov r10,QWORD PTR [r15+0x458] ; ImmutableOopMap {rbx=Oop rdx=Oop xmm0=Oop xmm1=Oop xmm2=Oop xmm3=Oop xmm6=NarrowOop xmm8=NarrowOop } | |
││ │ ;*goto {reexecute=1 rethrow=0 return_oop=0} | |
││ │ ; - (reexecute) org.apache.lucene.internal.vectorization.DefaultVectorUtilSupport::dotProduct@48 (line 146) | |
││ │ ; - org.apache.lucene.util.VectorUtil::dotProduct@29 (line 151) | |
││ │ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
││ │ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
││ │ 0x00007f559451053a: test DWORD PTR [r10],eax ;*goto {reexecute=0 rethrow=0 return_oop=0} | |
││ │ ; - org.apache.lucene.internal.vectorization.DefaultVectorUtilSupport::dotProduct@48 (line 146) | |
││ │ ; - org.apache.lucene.util.VectorUtil::dotProduct@29 (line 151) | |
││ │ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
││ │ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
││ │ ; {poll} | |
││ │ 0x00007f559451053d: mov r10d,DWORD PTR [rsp+0xc] | |
0.05% ││ │ 0x00007f5594510542: cmp r10d,DWORD PTR [rsp+0x50] | |
││ ╭│ 0x00007f5594510547: jge 0x00007f559451058c | |
││ ││ 0x00007f5594510549: mov r13d,esi | |
││ ││ 0x00007f559451054c: mov r10d,DWORD PTR [rsp+0x50] | |
0.01% ││ ││ ↗ 0x00007f5594510551: mov DWORD PTR [rsp+0x50],r10d | |
0.01% ││ ││ │ 0x00007f5594510556: sub r10d,DWORD PTR [rsp+0xc] | |
0.02% ││ ││ │ 0x00007f559451055b: mov r11d,DWORD PTR [rsp+0x50] | |
0.01% ││ ││ │ 0x00007f5594510560: xor r9d,r9d | |
0.01% ││ ││ │ 0x00007f5594510563: cmp r11d,DWORD PTR [rsp+0xc] | |
0.01% ││ ││ │ 0x00007f5594510568: cmovl r10d,r9d | |
0.01% ││ ││ │ 0x00007f559451056c: cmp r10d,0x7d00 | |
0.08% ││ ││ │ 0x00007f5594510573: mov r11d,0x7d00 | |
0.03% ││ ││ │ 0x00007f5594510579: cmova r10d,r11d | |
0.05% ││ ││ │ 0x00007f559451057d: add r10d,DWORD PTR [rsp+0xc] | |
0.18% ││ ││ │ 0x00007f5594510582: mov DWORD PTR [rsp+0x54],r10d | |
0.09% ││ │╰ │ 0x00007f5594510587: jmp 0x00007f5594510275 | |
││ ↘ │ 0x00007f559451058c: vmovd ecx,xmm6 | |
││ │ 0x00007f5594510590: vmovd edi,xmm5 | |
││ │ 0x00007f5594510594: vmovd r9d,xmm8 | |
0.01% ││ │ 0x00007f5594510599: vmovd r11d,xmm7 | |
││ │ 0x00007f559451059e: cmp r10d,r11d | |
││ ╭ │ 0x00007f55945105a1: jge 0x00007f55945105eb | |
││ │ │ 0x00007f55945105a3: mov ebp,edi | |
││ │ │ 0x00007f55945105a5: mov eax,r9d | |
0.08% ││ │ │ 0x00007f55945105a8: mov r14d,r11d ;*iload_3 {reexecute=0 rethrow=0 return_oop=0} | |
││ │ │ ; - org.apache.lucene.internal.vectorization.DefaultVectorUtilSupport::dotProduct@19 (line 147) | |
││ │ │ ; - org.apache.lucene.util.VectorUtil::dotProduct@29 (line 151) | |
││ │ │ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
││ │ │ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
0.16% ││ │↗ │ 0x00007f55945105ab: mov edi,r10d | |
0.01% ││ ││ │ 0x00007f55945105ae: movsxd r8,r10d ;*baload {reexecute=0 rethrow=0 return_oop=0} | |
││ ││ │ ; - org.apache.lucene.internal.vectorization.DefaultVectorUtilSupport::dotProduct@23 (line 147) | |
││ ││ │ ; - org.apache.lucene.util.VectorUtil::dotProduct@29 (line 151) | |
││ ││ │ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
││ ││ │ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
0.20% ││ ││ │ 0x00007f55945105b1: movsx r11d,BYTE PTR [rdx+r8*1+0x11] | |
0.24% ││ ││ │ 0x00007f55945105b7: movsx r10d,BYTE PTR [rbx+r8*1+0x10] | |
0.39% ││ ││ │ 0x00007f55945105bd: movsx r9d,BYTE PTR [rdx+r8*1+0x10] | |
0.09% ││ ││ │ 0x00007f55945105c3: movsx r8d,BYTE PTR [rbx+r8*1+0x11] | |
0.33% ││ ││ │ 0x00007f55945105c9: imul r9d,r10d | |
0.24% ││ ││ │ 0x00007f55945105cd: imul r11d,r8d | |
0.45% ││ ││ │ 0x00007f55945105d1: add r11d,r9d | |
0.49% ││ ││ │ 0x00007f55945105d4: lea r10d,[rsi+r11*1] | |
0.68% ││ ││ │ 0x00007f55945105d8: mov esi,r10d | |
0.01% ││ ││ │ 0x00007f55945105db: add edi,0x2 ;*iinc {reexecute=0 rethrow=0 return_oop=0} | |
││ ││ │ ; - org.apache.lucene.internal.vectorization.DefaultVectorUtilSupport::dotProduct@45 (line 146) | |
││ ││ │ ; - org.apache.lucene.util.VectorUtil::dotProduct@29 (line 151) | |
││ ││ │ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
││ ││ │ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
0.18% ││ ││ │ 0x00007f55945105de: mov r10d,edi | |
││ ││ │ 0x00007f55945105e1: cmp edi,r14d | |
││ │╰ │ 0x00007f55945105e4: jl 0x00007f55945105ab | |
0.02% ││ │ │ 0x00007f55945105e6: mov edi,ebp | |
││ │ │ 0x00007f55945105e8: mov r9d,eax | |
0.01% ││ ↘ │ 0x00007f55945105eb: vmovq r13,xmm0 | |
││ │ 0x00007f55945105f0: vmovq r8,xmm1 | |
0.01% ││ │ 0x00007f55945105f5: vmovq rdx,xmm2 | |
││ │ 0x00007f55945105fa: vmovq rax,xmm3 | |
0.02% ││ │ 0x00007f55945105ff: vmovq rbx,xmm4 | |
││ │ 0x00007f5594510604: mov r11d,esi ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0} | |
││ │ ; - org.apache.lucene.internal.vectorization.DefaultVectorUtilSupport::dotProduct@16 (line 146) | |
││ │ ; - org.apache.lucene.util.VectorUtil::dotProduct@29 (line 151) | |
││ │ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
││ │ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
0.04% ││ │↗ 0x00007f5594510607: cmp r10d,edi | |
││ ││ 0x00007f559451060a: jl 0x00007f55945108f0 ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0} | |
││ ││ ; - org.apache.lucene.internal.vectorization.DefaultVectorUtilSupport::dotProduct@55 (line 149) | |
││ ││ ; - org.apache.lucene.util.VectorUtil::dotProduct@29 (line 151) | |
││ ││ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
││ ││ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
││ ││ 0x00007f5594510610: movzx r10d,BYTE PTR [rdx+0x94] ;*getfield isDone {reexecute=0 rethrow=0 return_oop=0} | |
││ ││ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@30 (line 146) | |
0.03% ││ ││ 0x00007f5594510618: mov r11,QWORD PTR [r15+0x458] | |
││ ││ 0x00007f559451061f: add rbx,0x1 ; ImmutableOopMap {r8=Oop rdx=Oop rax=Oop r13=Oop } | |
││ ││ ;*ifeq {reexecute=1 rethrow=0 return_oop=0} | |
││ ││ ; - (reexecute) org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@33 (line 146) | |
0.01% ││ ││ 0x00007f5594510623: test DWORD PTR [r11],eax ; {poll} | |
││ ││ 0x00007f5594510626: test r10d,r10d | |
││ ││ 0x00007f5594510629: jne 0x00007f559451076c ;*aload_1 {reexecute=0 rethrow=0 return_oop=0} | |
││ ││ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@36 (line 147) | |
0.03% │↘ ││ 0x00007f559451062f: mov ecx,DWORD PTR [r8+0x10] ;*getfield bytesA {reexecute=0 rethrow=0 return_oop=0} | |
│ ││ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@1 (line 75) | |
│ ││ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
│ ││ 0x00007f5594510633: mov edi,DWORD PTR [r12+rcx*8+0xc]; implicit exception: dispatches to 0x00007f5594510ab4 | |
│ ││ ;*arraylength {reexecute=0 rethrow=0 return_oop=0} | |
│ ││ ; - org.apache.lucene.util.VectorUtil::dotProduct@1 (line 148) | |
│ ││ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
│ ││ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
0.01% │ ││ 0x00007f5594510638: mov r9d,DWORD PTR [r8+0x14] ;*getfield bytesB {reexecute=0 rethrow=0 return_oop=0} | |
│ ││ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@5 (line 75) | |
│ ││ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
│ ││ 0x00007f559451063c: mov r10d,DWORD PTR [r12+r9*8+0xc]; implicit exception: dispatches to 0x00007f5594510ac8 | |
│ ││ ;*arraylength {reexecute=0 rethrow=0 return_oop=0} | |
│ ││ ; - org.apache.lucene.util.VectorUtil::dotProduct@3 (line 148) | |
│ ││ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
│ ││ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
0.01% │ ││ 0x00007f5594510641: cmp edi,r10d | |
│ ││ 0x00007f5594510644: jne 0x00007f55945108b4 ;*if_icmpeq {reexecute=0 rethrow=0 return_oop=0} | |
│ ││ ; - org.apache.lucene.util.VectorUtil::dotProduct@4 (line 148) | |
│ ││ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
│ ││ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
0.01% │ ││ 0x00007f559451064a: mov r11d,edi | |
0.02% │ ││ 0x00007f559451064d: and r11d,0xfffffffe ;*iand {reexecute=0 rethrow=0 return_oop=0} | |
│ ││ ; - org.apache.lucene.internal.vectorization.DefaultVectorUtilSupport::dotProduct@9 (line 145) | |
│ ││ ; - org.apache.lucene.util.VectorUtil::dotProduct@29 (line 151) | |
│ ││ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
│ ││ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
│ ││ 0x00007f5594510651: test r11d,r11d | |
│ ╭││ 0x00007f5594510654: jle 0x00007f559451075c ;*if_icmpge {reexecute=0 rethrow=0 return_oop=0} | |
│ │││ ; - org.apache.lucene.internal.vectorization.DefaultVectorUtilSupport::dotProduct@16 (line 146) | |
│ │││ ; - org.apache.lucene.util.VectorUtil::dotProduct@29 (line 151) | |
│ │││ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
│ │││ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
0.03% │ │││ 0x00007f559451065a: test edi,edi | |
│ │││ 0x00007f559451065c: jbe 0x00007f55945107b6 | |
0.01% │ │││ 0x00007f5594510662: vmovq xmm3,rax | |
0.01% │ │││ 0x00007f5594510667: vmovq xmm2,rdx | |
│ │││ 0x00007f559451066c: vmovq xmm1,r8 | |
0.01% │ │││ 0x00007f5594510671: vmovq xmm0,r13 | |
│ │││ 0x00007f5594510676: movsxd rdx,edi | |
0.01% │ │││ 0x00007f5594510679: movsxd rsi,r11d | |
│ │││ 0x00007f559451067c: lea r8,[rsi+0x1] | |
0.05% │ │││ 0x00007f5594510680: and r8,0xfffffffffffffffe | |
│ │││ 0x00007f5594510684: mov r8d,r8d | |
0.01% │ │││ 0x00007f5594510687: movsxd r8,r8d | |
0.01% │ │││ 0x00007f559451068a: lea rax,[r8-0x2] | |
0.05% │ │││ 0x00007f559451068e: cmp rax,rdx | |
│ │││ 0x00007f5594510691: jae 0x00007f55945107a7 | |
0.04% │ │││ 0x00007f5594510697: test r10d,r10d | |
│ │││ 0x00007f559451069a: jbe 0x00007f5594510872 | |
0.01% │ │││ 0x00007f55945106a0: mov ebp,r11d | |
│ │││ 0x00007f55945106a3: vmovq xmm4,rbx | |
0.01% │ │││ 0x00007f55945106a8: movsxd r11,r10d | |
0.02% │ │││ 0x00007f55945106ab: cmp rax,r11 | |
│ │││ 0x00007f55945106ae: jae 0x00007f55945107ec | |
0.03% │ │││ 0x00007f55945106b4: cmp edi,0x1 | |
│ │││ 0x00007f55945106b7: jbe 0x00007f5594510886 | |
│ │││ 0x00007f55945106bd: dec r8 | |
0.01% │ │││ 0x00007f55945106c0: cmp r8,rdx | |
│ │││ 0x00007f55945106c3: jae 0x00007f5594510800 | |
0.03% │ │││ 0x00007f55945106c9: cmp r10d,0x1 | |
│ │││ 0x00007f55945106cd: jbe 0x00007f559451089d | |
│ │││ 0x00007f55945106d3: cmp r8,r11 | |
│ │││ 0x00007f55945106d6: jae 0x00007f5594510814 | |
0.04% │ │││ 0x00007f55945106dc: mov r11d,ebp | |
0.01% │ │││ 0x00007f55945106df: cmp r11d,0x7ffffffe | |
│ │││ 0x00007f55945106e6: jg 0x00007f5594510828 | |
│ │││ 0x00007f55945106ec: movsx r10d,BYTE PTR [r12+r9*8+0x11];*baload {reexecute=0 rethrow=0 return_oop=0} | |
│ │││ ; - org.apache.lucene.internal.vectorization.DefaultVectorUtilSupport::dotProduct@40 (line 147) | |
│ │││ ; - org.apache.lucene.util.VectorUtil::dotProduct@29 (line 151) | |
│ │││ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
│ │││ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
0.01% │ │││ 0x00007f55945106f2: movsx r13d,BYTE PTR [r12+rcx*8+0x11] | |
│ │││ 0x00007f55945106f8: movsx ebx,BYTE PTR [r12+r9*8+0x10] | |
│ │││ 0x00007f55945106fe: imul r13d,r10d | |
│ │││ 0x00007f5594510702: movsx r10d,BYTE PTR [r12+rcx*8+0x10];*baload {reexecute=0 rethrow=0 return_oop=0} | |
│ │││ ; - org.apache.lucene.internal.vectorization.DefaultVectorUtilSupport::dotProduct@23 (line 147) | |
│ │││ ; - org.apache.lucene.util.VectorUtil::dotProduct@29 (line 151) | |
│ │││ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
│ │││ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
│ │││ 0x00007f5594510708: imul r10d,ebx | |
0.01% │ │││ 0x00007f559451070c: add r13d,r10d ;*iadd {reexecute=0 rethrow=0 return_oop=0} | |
│ │││ ; - org.apache.lucene.internal.vectorization.DefaultVectorUtilSupport::dotProduct@42 (line 147) | |
│ │││ ; - org.apache.lucene.util.VectorUtil::dotProduct@29 (line 151) | |
│ │││ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@8 (line 75) | |
│ │││ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
0.01% │ │││ 0x00007f559451070f: lea rbx,[r12+r9*8] ;*getfield bytesB {reexecute=0 rethrow=0 return_oop=0} | |
│ │││ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@5 (line 75) | |
│ │││ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
0.01% │ │││ 0x00007f5594510713: add rsi,0xffffffffffffffe2 | |
0.01% │ │││ 0x00007f5594510717: lea rdx,[r12+rcx*8] ;*getfield bytesA {reexecute=0 rethrow=0 return_oop=0} | |
│ │││ ; - org.apache.lucene.benchmark.jmh.VectorUtilBenchmark::binaryDotProductScalar@1 (line 75) | |
│ │││ ; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@17 (line 144) | |
│ │││ 0x00007f559451071b: cmp rsi,0xffffffff80000000 | |
0.01% │ │││ 0x00007f5594510722: mov r10,0xffffffff80000000 ; {no_reloc} | |
│ │││ 0x00007f5594510729: cmovl rsi,r10 | |
0.01% │ │││ 0x00007f559451072d: mov r10d,esi | |
0.01% │ │││ 0x00007f5594510730: cmp r10d,0x2 | |
│ │││ 0x00007f5594510734: jle 0x00007f5594510864 | |
0.01% │ │││ 0x00007f559451073a: mov r8d,0x2 | |
0.01% │ │││ 0x00007f5594510740: vmovd xmm6,ecx | |
0.03% │ │││ 0x00007f5594510744: vmovd xmm5,edi | |
│ │││ 0x00007f5594510748: vmovd xmm8,r9d | |
│ │││ 0x00007f559451074d: vmovd xmm7,r11d | |
│ │││ 0x00007f5594510752: mov DWORD PTR [rsp+0xc],r8d | |
│ │╰│ 0x00007f5594510757: jmp 0x00007f5594510551 | |
│ ↘ │ 0x00007f559451075c: xor r10d,r10d | |
│ │ 0x00007f559451075f: xor r11d,r11d | |
│ ╰ 0x00007f5594510762: jmp 0x00007f5594510607 | |
↘ 0x00007f5594510767: mov ebx,0x1 ;*aload_1 {reexecute=0 rethrow=0 return_oop=0} | |
; - org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub@36 (line 147) | |
0x00007f559451076c: movabs r10,0x7f55aa4ca4f0 | |
.................................................................................................... | |
97.04% <total for region 1> | |
....[Hottest Regions]............................................................................... | |
97.04% c2, level 4 org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub, version 5, compile id 667 | |
2.66% [kernel.kallsyms] native_write_msr | |
0.02% libjvm.so ElfSymbolTable::lookup | |
0.01% [kernel.kallsyms] mutex_lock | |
0.01% interpreter method entry point (kind = zerolocals) | |
0.01% libjvm.so fileStream::write | |
0.01% [kernel.kallsyms] __task_pid_nr_ns | |
0.01% [kernel.kallsyms] __wake_up_common | |
0.01% [kernel.kallsyms] autoremove_wake_function | |
0.01% [kernel.kallsyms] mutex_spin_on_owner | |
0.01% [kernel.kallsyms] exit_to_user_mode_prepare | |
0.01% [kernel.kallsyms] rw_verify_area | |
0.01% [kernel.kallsyms] pipe_write | |
0.01% [kernel.kallsyms] pipe_write | |
0.01% <unknown> | |
0.01% [kernel.kallsyms] __ext4_journal_get_write_access | |
0.01% [kernel.kallsyms] copy_page_from_iter | |
0.01% [kernel.kallsyms] do_syscall_64 | |
0.01% [kernel.kallsyms] _raw_spin_lock_irq | |
0.01% [kernel.kallsyms] entry_SYSCALL_64_safe_stack | |
0.14% <...other 22 warm regions...> | |
.................................................................................................... | |
99.99% <totals> | |
....[Hottest Methods (after inlining)].............................................................. | |
97.04% c2, level 4 org.apache.lucene.benchmark.jmh.jmh_generated.VectorUtilBenchmark_binaryDotProductScalar_jmhTest::binaryDotProductScalar_thrpt_jmhStub, version 5, compile id 667 | |
2.66% [kernel.kallsyms] native_write_msr | |
0.02% interpreter method entry point (kind = zerolocals) | |
0.02% libjvm.so ElfSymbolTable::lookup | |
0.01% libjvm.so fileStream::write | |
0.01% <unknown> | |
0.01% [kernel.kallsyms] mutex_lock | |
0.01% [kernel.kallsyms] pipe_write | |
0.01% interpreter return entry points | |
0.01% [kernel.kallsyms] _raw_spin_lock_irq | |
0.01% libjvm.so GraphBuilder::try_inline_full | |
0.01% interpreter fast_iputfield 217 fast_iputfield | |
0.01% [kernel.kallsyms] __task_pid_nr_ns | |
0.01% [kernel.kallsyms] do_syscall_64 | |
0.01% hsdis-amd64.so hsdis_read_memory_func | |
0.01% libc.so.6 __strchr_evex | |
0.01% [kernel.kallsyms] syscall_return_via_sysret | |
0.01% [kernel.kallsyms] entry_SYSCALL_64_safe_stack | |
0.01% libjvm.so xmlTextStream::flush | |
0.01% libc.so.6 __sigsetjmp | |
0.13% <...other 19 warm methods...> | |
.................................................................................................... | |
99.99% <totals> | |
....[Distribution by Source]........................................................................ | |
97.04% c2, level 4 | |
2.77% [kernel.kallsyms] | |
0.09% libjvm.so | |
0.04% interpreter | |
0.02% libc.so.6 | |
0.01% | |
0.01% hsdis-amd64.so | |
.................................................................................................... | |
99.99% <totals> | |
# Run complete. Total time: 00:00:27 | |
REMEMBER: The numbers below are just data. To gain reusable insights, you need to follow up on | |
why the numbers are the way they are. Use profilers (see -prof, -lprof), design factorial | |
experiments, perform baseline and negative tests that provide experimental control, make sure | |
the benchmarking environment is safe on JVM/OS/HW level, ask for reviews from the domain experts. | |
Do not assume the numbers tell you what you want them to tell. | |
NOTE: Current JVM experimentally supports Compiler Blackholes, and they are in use. Please exercise | |
extra caution when trusting the results, look into the generated code to check the benchmark still | |
works, and factor in a small probability of new VM bugs. Additionally, while comparisons between | |
different JVMs are already problematic, the performance difference caused by different Blackhole | |
modes can be very significant. Please make sure you use the consistent Blackhole mode for comparisons. | |
Benchmark (size) Mode Cnt Score Error Units | |
VectorUtilBenchmark.binaryDotProductScalar 1024 thrpt 5 2.814 ± 0.010 ops/us | |
VectorUtilBenchmark.binaryDotProductScalar:asm 1024 thrpt NaN --- |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment