# JMH 1.6.3 (released 5 days ago)
# VM invoker: /aurora/clredest/contended/jdk-cache64/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: 12308325.781 ±(99.9%) 3710425.539 us/op
# Processing profiler results: perf 


Run result: 12308325.78 us/op (<= 2 samples)

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

     162152.903823 task-clock                #    9.141 CPUs utilized          
         5,140,000 context-switches          #    0.032 M/sec                  
               320 CPU-migrations            #    0.000 M/sec                  
            13,532 page-faults               #    0.000 M/sec                  
   450,653,815,053 cycles                    #    2.779 GHz                     [25.05%]
   328,376,742,579 stalled-cycles-frontend   #   72.87% frontend cycles idle    [25.03%]
   271,469,592,686 stalled-cycles-backend    #   60.24% backend  cycles idle    [25.06%]
   285,493,986,735 instructions              #    0.63  insns per cycle        
                                             #    1.15  stalled cycles per insn [31.28%]
    56,294,206,289 branches                  #  347.167 M/sec                   [31.28%]
       196,921,112 branch-misses             #    0.35% of all branches         [31.27%]
    92,525,075,583 L1-dcache-loads           #  570.604 M/sec                   [31.24%]
     2,036,163,692 L1-dcache-load-misses     #    2.20% of all L1-dcache hits   [31.19%]
         1,608,250 LLC-loads                 #    0.010 M/sec                   [25.04%]
         1,676,716 LLC-load-misses           #  104.26% of all LL-cache hits    [25.08%]
   <not supported> L1-icache-loads         
     1,321,107,845 L1-icache-load-misses     #    0.00% of all L1-icache hits   [25.10%]
    93,127,649,373 dTLB-loads                #  574.320 M/sec                   [25.11%]
        20,810,315 dTLB-load-misses          #    0.02% of all dTLB cache hits  [25.10%]
        41,884,277 iTLB-loads                #    0.258 M/sec                   [25.10%]
         6,664,063 iTLB-load-misses          #   15.91% of all iTLB cache hits  [25.14%]
   <not supported> L1-dcache-prefetches    
       305,145,223 L1-dcache-prefetch-misses #    1.882 M/sec                   [25.09%]

      17.739166146 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-cache64/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 00:00:35
# Fork: 1 of 1
# Preparing profilers: perf 
# Profilers consume stderr from target VM, use -v EXTRA to copy to console
Iteration   1: 12364109.264 ±(99.9%) 5573003.736 us/op
# Processing profiler results: perf 


Run result: 12364109.26 us/op (<= 2 samples)

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

     180531.115244 task-clock                #    8.294 CPUs utilized          
         2,313,920 context-switches          #    0.013 M/sec                  
               304 CPU-migrations            #    0.000 M/sec                  
            13,443 page-faults               #    0.000 M/sec                  
   513,056,356,619 cycles                    #    2.842 GHz                     [25.01%]
   391,912,149,230 stalled-cycles-frontend   #   76.39% frontend cycles idle    [24.98%]
   337,905,994,148 stalled-cycles-backend    #   65.86% backend  cycles idle    [25.06%]
   291,392,313,706 instructions              #    0.57  insns per cycle        
                                             #    1.34  stalled cycles per insn [31.34%]
    60,267,782,482 branches                  #  333.836 M/sec                   [31.34%]
       156,837,024 branch-misses             #    0.26% of all branches         [31.35%]
    92,631,700,787 L1-dcache-loads           #  513.107 M/sec                   [31.34%]
     2,223,257,186 L1-dcache-load-misses     #    2.40% of all L1-dcache hits   [31.33%]
         3,760,962 LLC-loads                 #    0.021 M/sec                   [25.00%]
         3,608,386 LLC-load-misses           #   95.94% of all LL-cache hits    [25.07%]
   <not supported> L1-icache-loads         
       731,457,299 L1-icache-load-misses     #    0.00% of all L1-icache hits   [25.07%]
    92,961,283,184 dTLB-loads                #  514.932 M/sec                   [25.03%]
        16,564,285 dTLB-load-misses          #    0.02% of all dTLB cache hits  [25.09%]
        47,386,755 iTLB-loads                #    0.262 M/sec                   [25.07%]
         6,159,962 iTLB-load-misses          #   13.00% of all iTLB cache hits  [25.03%]
   <not supported> L1-dcache-prefetches    
       499,830,124 L1-dcache-prefetch-misses #    2.769 M/sec                   [25.03%]

      21.767610685 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-cache64/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 00:00:19
# Fork: 1 of 1
# Preparing profilers: perf 
# Profilers consume stderr from target VM, use -v EXTRA to copy to console
Iteration   1: 6796076.923 ±(99.9%) 3196070.148 us/op
# Processing profiler results: perf 


Run result: 6796076.92 us/op (<= 2 samples)

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

     101775.394342 task-clock                #    8.166 CPUs utilized          
         1,048,293 context-switches          #    0.010 M/sec                  
               353 CPU-migrations            #    0.000 M/sec                  
            13,482 page-faults               #    0.000 M/sec                  
   289,875,107,369 cycles                    #    2.848 GHz                     [25.08%]
   219,777,091,492 stalled-cycles-frontend   #   75.82% frontend cycles idle    [25.09%]
   183,384,300,566 stalled-cycles-backend    #   63.26% backend  cycles idle    [25.15%]
   153,288,228,012 instructions              #    0.53  insns per cycle        
                                             #    1.43  stalled cycles per insn [31.45%]
    39,211,696,063 branches                  #  385.277 M/sec                   [31.47%]
       162,117,207 branch-misses             #    0.41% of all branches         [31.39%]
    44,594,817,084 L1-dcache-loads           #  438.169 M/sec                   [31.45%]
     1,185,313,053 L1-dcache-load-misses     #    2.66% of all L1-dcache hits   [31.33%]
         2,502,285 LLC-loads                 #    0.025 M/sec                   [25.00%]
         1,629,143 LLC-load-misses           #   65.11% of all LL-cache hits    [25.14%]
   <not supported> L1-icache-loads         
       470,004,032 L1-icache-load-misses     #    0.00% of all L1-icache hits   [25.08%]
    44,715,564,655 dTLB-loads                #  439.355 M/sec                   [25.12%]
        10,933,767 dTLB-load-misses          #    0.02% of all dTLB cache hits  [25.09%]
        28,890,058 iTLB-loads                #    0.284 M/sec                   [25.02%]
         2,891,515 iTLB-load-misses          #   10.01% of all iTLB cache hits  [24.99%]
   <not supported> L1-dcache-prefetches    
       306,523,799 L1-dcache-prefetch-misses #    3.012 M/sec                   [24.99%]

      12.463403128 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: 00:00:52

Benchmark                                                         (inflate)  (monitors)  (step)  Mode  Cnt         Score   Error  Units
ContendedMonitorBench.synchronizeAndAccessContendedHeader             false           8       8    ss    1  12308325.781 ±   NaN  us/op
ContendedMonitorBench.synchronizeAndAccessContendedHeader:@cpi        false           8       8    ss    1         1.579 ±   NaN    CPI
ContendedMonitorBench.synchronizeAndAccessOwnHeader                   false           8       8    ss    1  12364109.264 ±   NaN  us/op
ContendedMonitorBench.synchronizeAndAccessOwnHeader:@cpi              false           8       8    ss    1         1.761 ±   NaN    CPI
ContendedMonitorBench.synchronizeAndAccessUncontendedHeader           false           8       8    ss    1   6796076.923 ±   NaN  us/op
ContendedMonitorBench.synchronizeAndAccessUncontendedHeader:@cpi      false           8       8    ss    1         1.891 ±   NaN    CPI