# Detecting actual CPU count: 32 detected
# JMH 1.6.3 (released 4 days ago)
# VM invoker: /aurora/clredest/contended/jdk-padded/jre/bin/java
# VM options: -XX:-UseBiasedLocking -XX:+UseHeavyMonitors
# Warmup: <none>
# Measurement: 1 iterations, 500 ms each, 4000000 calls per op
# Timeout: 10 min per iteration
# Threads: 32 threads
# Benchmark mode: Single shot invocation time
# Benchmark: org.openjdk.micros.contended.ContendedMonitorBench.synchronizeAndAccessContendedHeader
# Parameters: (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: 3555587.120 ±(99.9%) 164240.559 us/op
# Processing profiler results: perf 


Run result: 3555587.12 us/op (<= 2 samples)

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

      49787.262790 task-clock                #   11.440 CPUs utilized          
         1,916,965 context-switches          #    0.039 M/sec                  
             9,277 CPU-migrations            #    0.000 M/sec                  
            10,000 page-faults               #    0.000 M/sec                  
   134,260,643,941 cycles                    #    2.697 GHz                     [25.10%]
    94,839,822,961 stalled-cycles-frontend   #   70.64% frontend cycles idle    [25.18%]
    68,232,194,351 stalled-cycles-backend    #   50.82% backend  cycles idle    [25.36%]
    95,663,448,658 instructions              #    0.71  insns per cycle        
                                             #    0.99  stalled cycles per insn [31.79%]
    17,987,763,290 branches                  #  361.292 M/sec                   [31.70%]
       106,377,250 branch-misses             #    0.59% of all branches         [31.49%]
    34,031,334,168 L1-dcache-loads           #  683.535 M/sec                   [31.43%]
       664,726,002 L1-dcache-load-misses     #    1.95% of all L1-dcache hits   [31.40%]
         7,611,552 LLC-loads                 #    0.153 M/sec                   [25.15%]
         6,832,437 LLC-load-misses           #   89.76% of all LL-cache hits    [25.44%]
   <not supported> L1-icache-loads         
       585,836,333 L1-icache-load-misses     #    0.00% of all L1-icache hits   [25.54%]
    33,628,275,457 dTLB-loads                #  675.439 M/sec                   [25.68%]
        39,555,844 dTLB-load-misses          #    0.12% of all dTLB cache hits  [25.68%]
        45,010,421 iTLB-loads                #    0.904 M/sec                   [25.58%]
        25,511,748 iTLB-load-misses          #   56.68% of all iTLB cache hits  [25.20%]
   <not supported> L1-dcache-prefetches    
        77,036,572 L1-dcache-prefetch-misses #    1.547 M/sec                   [25.09%]

       4.352203492 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 4 days ago)
# VM invoker: /aurora/clredest/contended/jdk-padded/jre/bin/java
# VM options: -XX:-UseBiasedLocking -XX:+UseHeavyMonitors
# Warmup: <none>
# Measurement: 1 iterations, 500 ms each, 4000000 calls per op
# Timeout: 10 min per iteration
# Threads: 32 threads
# Benchmark mode: Single shot invocation time
# Benchmark: org.openjdk.micros.contended.ContendedMonitorBench.synchronizeAndAccessOwnHeader
# Parameters: (monitors = 8, step = 8)

# Run progress: 33.33% complete, ETA 00:00:08
# Fork: 1 of 1
# Preparing profilers: perf 
# Profilers consume stderr from target VM, use -v EXTRA to copy to console
Iteration   1: 3393813.639 ±(99.9%) 145906.746 us/op
# Processing profiler results: perf 


Run result: 3393813.64 us/op (<= 2 samples)

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

      48117.652296 task-clock                #   12.002 CPUs utilized          
         1,794,087 context-switches          #    0.037 M/sec                  
             6,237 CPU-migrations            #    0.000 M/sec                  
            10,074 page-faults               #    0.000 M/sec                  
   130,449,031,859 cycles                    #    2.711 GHz                     [25.58%]
    91,102,954,867 stalled-cycles-frontend   #   69.84% frontend cycles idle    [25.46%]
    64,724,306,831 stalled-cycles-backend    #   49.62% backend  cycles idle    [25.58%]
    95,412,647,437 instructions              #    0.73  insns per cycle        
                                             #    0.95  stalled cycles per insn [31.96%]
    17,837,229,472 branches                  #  370.700 M/sec                   [31.68%]
        98,764,437 branch-misses             #    0.55% of all branches         [31.26%]
    33,469,961,343 L1-dcache-loads           #  695.586 M/sec                   [31.49%]
       604,108,384 L1-dcache-load-misses     #    1.80% of all L1-dcache hits   [31.84%]
         7,378,815 LLC-loads                 #    0.153 M/sec                   [25.48%]
         5,840,637 LLC-load-misses           #   79.15% of all LL-cache hits    [25.89%]
   <not supported> L1-icache-loads         
       537,762,881 L1-icache-load-misses     #    0.00% of all L1-icache hits   [25.66%]
    33,014,346,415 dTLB-loads                #  686.117 M/sec                   [25.26%]
        40,069,168 dTLB-load-misses          #    0.12% of all dTLB cache hits  [25.03%]
        47,923,947 iTLB-loads                #    0.996 M/sec                   [24.85%]
        25,557,381 iTLB-load-misses          #   53.33% of all iTLB cache hits  [24.81%]
   <not supported> L1-dcache-prefetches    
        64,018,468 L1-dcache-prefetch-misses #    1.330 M/sec                   [24.97%]

       4.009238740 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 4 days ago)
# VM invoker: /aurora/clredest/contended/jdk-padded/jre/bin/java
# VM options: -XX:-UseBiasedLocking -XX:+UseHeavyMonitors
# Warmup: <none>
# Measurement: 1 iterations, 500 ms each, 4000000 calls per op
# Timeout: 10 min per iteration
# Threads: 32 threads
# Benchmark mode: Single shot invocation time
# Benchmark: org.openjdk.micros.contended.ContendedMonitorBench.synchronizeAndAccessUncontendedHeader
# Parameters: (monitors = 8, step = 8)

# Run progress: 66.67% complete, ETA 00:00:04
# Fork: 1 of 1
# Preparing profilers: perf 
# Profilers consume stderr from target VM, use -v EXTRA to copy to console
Iteration   1: 2008383.429 ±(99.9%) 172740.804 us/op
# Processing profiler results: perf 


Run result: 2008383.43 us/op (<= 2 samples)

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

      38015.990565 task-clock                #   14.558 CPUs utilized          
         1,028,361 context-switches          #    0.027 M/sec                  
             1,830 CPU-migrations            #    0.000 M/sec                  
             9,977 page-faults               #    0.000 M/sec                  
   103,803,636,638 cycles                    #    2.731 GHz                     [25.33%]
    81,308,869,458 stalled-cycles-frontend   #   78.33% frontend cycles idle    [25.20%]
    63,700,392,425 stalled-cycles-backend    #   61.37% backend  cycles idle    [25.25%]
    53,540,014,735 instructions              #    0.52  insns per cycle        
                                             #    1.52  stalled cycles per insn [31.63%]
    10,461,932,442 branches                  #  275.198 M/sec                   [31.97%]
        95,000,537 branch-misses             #    0.91% of all branches         [32.27%]
    19,390,334,673 L1-dcache-loads           #  510.057 M/sec                   [32.54%]
       502,758,969 L1-dcache-load-misses     #    2.59% of all L1-dcache hits   [32.47%]
         6,350,812 LLC-loads                 #    0.167 M/sec                   [25.70%]
         4,716,856 LLC-load-misses           #   74.27% of all LL-cache hits    [25.18%]
   <not supported> L1-icache-loads         
       386,300,009 L1-icache-load-misses     #    0.00% of all L1-icache hits   [25.04%]
    19,423,505,376 dTLB-loads                #  510.930 M/sec                   [24.62%]
        27,890,174 dTLB-load-misses          #    0.14% of all dTLB cache hits  [24.86%]
        45,337,798 iTLB-loads                #    1.193 M/sec                   [25.20%]
        17,014,600 iTLB-load-misses          #   37.53% of all iTLB cache hits  [25.21%]
   <not supported> L1-dcache-prefetches    
        70,266,670 L1-dcache-prefetch-misses #    1.848 M/sec                   [25.34%]

       2.611322206 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: 00:00:11

Benchmark                                                         (monitors)  (step)  Mode  Cnt        Score   Error  Units
ContendedMonitorBench.synchronizeAndAccessContendedHeader                  8       8    ss    1  3555587.120 ±   NaN  us/op
ContendedMonitorBench.synchronizeAndAccessContendedHeader:@cpi             8       8    ss    1        1.403 ±   NaN    CPI
ContendedMonitorBench.synchronizeAndAccessOwnHeader                        8       8    ss    1  3393813.639 ±   NaN  us/op
ContendedMonitorBench.synchronizeAndAccessOwnHeader:@cpi                   8       8    ss    1        1.367 ±   NaN    CPI
ContendedMonitorBench.synchronizeAndAccessUncontendedHeader                8       8    ss    1  2008383.429 ±   NaN  us/op
ContendedMonitorBench.synchronizeAndAccessUncontendedHeader:@cpi           8       8    ss    1        1.939 ±   NaN    CPI