# JMH 1.6.3 (released 5 days ago)
# VM invoker: /aurora/clredest/contended/jdk-baseline/jre/bin/java
# VM options: -XX:-UseBiasedLocking -XX:+UseHeavyMonitors
# Warmup: <none>
# Measurement: 1 iterations, 500 ms each, 40000000 calls per op
# Timeout: 10 min per iteration
# Threads: 16 threads
# Benchmark mode: Single shot invocation time
# Benchmark: org.openjdk.micros.contended.ContendedMonitorBench.synchronizeAndAccessContendedHeader
# Parameters: (inflate = false, monitors = 8, step = 8)

# Run progress: 0.00% complete, ETA 00:00:00
# Fork: 1 of 1
# Preparing profilers: perf 
# Profilers consume stderr from target VM, use -v EXTRA to copy to console
Iteration   1: 15056698.294 ±(99.9%) 5449569.369 us/op
# Processing profiler results: perf 


Run result: 15056698.29 us/op (<= 2 samples)

Perf stats:
--------------------------------------------------

     209462.733869 task-clock                #    8.531 CPUs utilized          
         4,573,143 context-switches          #    0.022 M/sec                  
               309 CPU-migrations            #    0.000 M/sec                  
            13,685 page-faults               #    0.000 M/sec                  
   589,370,903,103 cycles                    #    2.814 GHz                     [25.05%]
   458,410,643,846 stalled-cycles-frontend   #   77.78% frontend cycles idle    [25.15%]
   400,325,620,138 stalled-cycles-backend    #   67.92% backend  cycles idle    [25.18%]
   302,177,882,917 instructions              #    0.51  insns per cycle        
                                             #    1.52  stalled cycles per insn [31.43%]
    61,922,945,914 branches                  #  295.628 M/sec                   [31.41%]
       198,590,705 branch-misses             #    0.32% of all branches         [31.35%]
    96,580,229,248 L1-dcache-loads           #  461.085 M/sec                   [31.31%]
     2,221,492,915 L1-dcache-load-misses     #    2.30% of all L1-dcache hits   [31.24%]
            84,916 LLC-loads                 #    0.000 M/sec                   [24.96%]
            24,830 LLC-load-misses           #   29.24% of all LL-cache hits    [24.98%]
   <not supported> L1-icache-loads         
     1,164,044,871 L1-icache-load-misses     #    0.00% of all L1-icache hits   [24.95%]
    97,185,593,812 dTLB-loads                #  463.976 M/sec                   [25.02%]
        16,670,517 dTLB-load-misses          #    0.02% of all dTLB cache hits  [25.03%]
        30,893,613 iTLB-loads                #    0.147 M/sec                   [25.00%]
         4,308,096 iTLB-load-misses          #   13.94% of all iTLB cache hits  [25.02%]
   <not supported> L1-dcache-prefetches    
       278,550,304 L1-dcache-prefetch-misses #    1.330 M/sec                   [25.01%]

      24.554084228 seconds time elapsed


WARNING: Your system uses old "perf", which can not delay data collection.
Therefore, perf performance data includes benchmark warmup.


# JMH 1.6.3 (released 5 days ago)
# VM invoker: /aurora/clredest/contended/jdk-baseline/jre/bin/java
# VM options: -XX:-UseBiasedLocking -XX:+UseHeavyMonitors
# Warmup: <none>
# Measurement: 1 iterations, 500 ms each, 40000000 calls per op
# Timeout: 10 min per iteration
# Threads: 16 threads
# Benchmark mode: Single shot invocation time
# Benchmark: org.openjdk.micros.contended.ContendedMonitorBench.synchronizeAndAccessOwnHeader
# Parameters: (inflate = false, monitors = 8, step = 8)

# Run progress: 33.33% complete, ETA 00:00:49
# Fork: 1 of 1
# Preparing profilers: perf 
# Profilers consume stderr from target VM, use -v EXTRA to copy to console
Iteration   1: 12009339.876 ±(99.9%) 5109795.373 us/op
# Processing profiler results: perf 


Run result: 12009339.88 us/op (<= 2 samples)

Perf stats:
--------------------------------------------------

     169906.430189 task-clock                #    8.991 CPUs utilized          
         2,991,095 context-switches          #    0.018 M/sec                  
               292 CPU-migrations            #    0.000 M/sec                  
            13,454 page-faults               #    0.000 M/sec                  
   480,082,715,616 cycles                    #    2.826 GHz                     [25.04%]
   362,361,197,876 stalled-cycles-frontend   #   75.48% frontend cycles idle    [25.03%]
   313,236,174,409 stalled-cycles-backend    #   65.25% backend  cycles idle    [24.98%]
   280,858,131,395 instructions              #    0.59  insns per cycle        
                                             #    1.29  stalled cycles per insn [31.31%]
    56,837,580,053 branches                  #  334.523 M/sec                   [31.35%]
       162,184,019 branch-misses             #    0.29% of all branches         [31.34%]
    90,637,196,025 L1-dcache-loads           #  533.454 M/sec                   [31.39%]
     1,983,530,376 L1-dcache-load-misses     #    2.19% of all L1-dcache hits   [31.41%]
            66,359 LLC-loads                 #    0.000 M/sec                   [25.02%]
           156,045 LLC-load-misses           #  235.15% of all LL-cache hits    [25.04%]
   <not supported> L1-icache-loads         
       962,830,358 L1-icache-load-misses     #    0.00% of all L1-icache hits   [25.10%]
    90,510,349,088 dTLB-loads                #  532.707 M/sec                   [25.07%]
        22,771,531 dTLB-load-misses          #    0.03% of all dTLB cache hits  [25.07%]
        43,926,685 iTLB-loads                #    0.259 M/sec                   [24.99%]
         5,129,203 iTLB-load-misses          #   11.68% of all iTLB cache hits  [25.01%]
   <not supported> L1-dcache-prefetches    
       316,919,299 L1-dcache-prefetch-misses #    1.865 M/sec                   [25.01%]

      18.898158294 seconds time elapsed


WARNING: Your system uses old "perf", which can not delay data collection.
Therefore, perf performance data includes benchmark warmup.


# JMH 1.6.3 (released 5 days ago)
# VM invoker: /aurora/clredest/contended/jdk-baseline/jre/bin/java
# VM options: -XX:-UseBiasedLocking -XX:+UseHeavyMonitors
# Warmup: <none>
# Measurement: 1 iterations, 500 ms each, 40000000 calls per op
# Timeout: 10 min per iteration
# Threads: 16 threads
# Benchmark mode: Single shot invocation time
# Benchmark: org.openjdk.micros.contended.ContendedMonitorBench.synchronizeAndAccessUncontendedHeader
# Parameters: (inflate = false, monitors = 8, step = 8)

# Run progress: 66.67% complete, ETA 00:00:21
# Fork: 1 of 1
# Preparing profilers: perf 
# Profilers consume stderr from target VM, use -v EXTRA to copy to console
Iteration   1: 5672203.159 ±(99.9%) 2079387.775 us/op
# Processing profiler results: perf 


Run result: 5672203.16 us/op (<= 2 samples)

Perf stats:
--------------------------------------------------

      82805.504881 task-clock                #    7.421 CPUs utilized          
         1,192,911 context-switches          #    0.014 M/sec                  
               263 CPU-migrations            #    0.000 M/sec                  
            13,377 page-faults               #    0.000 M/sec                  
   234,258,901,391 cycles                    #    2.829 GHz                     [25.26%]
   170,727,269,220 stalled-cycles-frontend   #   72.88% frontend cycles idle    [25.13%]
   137,518,810,281 stalled-cycles-backend    #   58.70% backend  cycles idle    [25.10%]
   133,681,897,137 instructions              #    0.57  insns per cycle        
                                             #    1.28  stalled cycles per insn [31.46%]
    32,929,086,043 branches                  #  397.668 M/sec                   [31.39%]
       177,580,834 branch-misses             #    0.54% of all branches         [31.38%]
    40,188,146,712 L1-dcache-loads           #  485.332 M/sec                   [31.50%]
     1,157,896,829 L1-dcache-load-misses     #    2.88% of all L1-dcache hits   [31.43%]
                80 LLC-loads                 #    0.000 M/sec                   [25.12%]
           122,909 LLC-load-misses           #  153636.25% of all LL-cache hits    [25.09%]
   <not supported> L1-icache-loads         
       587,517,831 L1-icache-load-misses     #    0.00% of all L1-icache hits   [25.00%]
    40,210,884,783 dTLB-loads                #  485.606 M/sec                   [24.98%]
         5,629,412 dTLB-load-misses          #    0.01% of all dTLB cache hits  [24.95%]
        19,439,003 iTLB-loads                #    0.235 M/sec                   [25.13%]
         2,020,857 iTLB-load-misses          #   10.40% of all iTLB cache hits  [25.16%]
   <not supported> L1-dcache-prefetches    
       233,168,736 L1-dcache-prefetch-misses #    2.816 M/sec                   [25.24%]

      11.157703446 seconds time elapsed


WARNING: Your system uses old "perf", which can not delay data collection.
Therefore, perf performance data includes benchmark warmup.


# Run complete. Total time: 00:00:54

Benchmark                                                         (inflate)  (monitors)  (step)  Mode  Cnt         Score   Error  Units
ContendedMonitorBench.synchronizeAndAccessContendedHeader             false           8       8    ss    1  15056698.294 ±   NaN  us/op
ContendedMonitorBench.synchronizeAndAccessContendedHeader:@cpi        false           8       8    ss    1         1.950 ±   NaN    CPI
ContendedMonitorBench.synchronizeAndAccessOwnHeader                   false           8       8    ss    1  12009339.876 ±   NaN  us/op
ContendedMonitorBench.synchronizeAndAccessOwnHeader:@cpi              false           8       8    ss    1         1.709 ±   NaN    CPI
ContendedMonitorBench.synchronizeAndAccessUncontendedHeader           false           8       8    ss    1   5672203.159 ±   NaN  us/op
ContendedMonitorBench.synchronizeAndAccessUncontendedHeader:@cpi      false           8       8    ss    1         1.752 ±   NaN    CPI