1 Turn on the benchmark counters, and listen for specific patterns on System.out/System.err.
   2 The format of this option is:
   3 
   4   (err|out),start pattern,end pattern
   5   

   6 You can use "~" to match 1 or more digits.
   7 Examples:
   8 
   9   err, starting =====, PASSED in
  10   out,Iteration ~ (~s) begins:,Iteration ~ (~s) ends:
  11   
  12 The first pattern matches DaCapo output and the second matches SPECjvm2008 output.
  13 
  14 As a more detailed example, here are the options to use for getting statistics
  15 about allocations within the DaCapo pmd benchmark:
  16 
  17   -XX:JVMCICounterSize=<value> -XX:-JVMCICountersExcludeCompiler \
  18   -Dgraal.BenchmarkDynamicCounters="err, starting ====, PASSED in " \
  19   -Dgraal.ProfileAllocations=true
  20   
  21 The JVMCICounterSize value depends on the granularity of the profiling -
  22 10000 should be sufficient. Omit JVMCICountersExcludeCompiler to exclude
  23 counting allocations on the compiler threads.
  24 The counters can be further configured by the ProfileAllocationsContext option.

   1 Turn on the benchmark counters. The format of this option is:

   2 
   3   (err|out),start pattern,end pattern
   4   
   5 Start counting when the start pattern matches on the given stream and stop when the end pattern occurs.
   6 You can use "~" to match 1 or more digits.
   7 Examples:
   8 
   9   err, starting =====, PASSED in
  10   out,Iteration ~ (~s) begins:,Iteration ~ (~s) ends:
  11   
  12 The first pattern matches DaCapo output and the second matches SPECjvm2008 output.
  13 
  14 As a more detailed example, here are the options to use for getting statistics
  15 about allocations within the DaCapo pmd benchmark:
  16 
  17   -XX:JVMCICounterSize=<value> -XX:-JVMCICountersExcludeCompiler \
  18   -Dgraal.BenchmarkDynamicCounters="err, starting ====, PASSED in " \
  19   -Dgraal.ProfileAllocations=true
  20   
  21 The JVMCICounterSize value depends on the granularity of the profiling -
  22 10000 should be sufficient. Omit JVMCICountersExcludeCompiler to exclude
  23 counting allocations on the compiler threads.
  24 The counters can be further configured by the ProfileAllocationsContext option.
  25 
  26 We highly recommend the use of -Dgraal.AbortOnBenchmarkCounterOverflow=true to
  27 detect counter overflows eagerly.