==2595== Cachegrind, a cache and branch-prediction profiler
==2595== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2595== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==2595== Command: _bin/cxx-opt/osh -n --ast-format none benchmarks/testdata/configure
==2595== Parent PID: 2588
==2595== 
--2595-- warning: L3 cache found, using its data for the LL simulation.
==2595== brk segment overflow in thread #1: can't grow to 0x483d000
==2595== (see section Limitations in user manual)
==2595== NOTE: further instances of this message will not be shown
==2595== 
==2595== I   refs:      279,051,542
==2595== I1  misses:      2,354,333
==2595== LLi misses:          8,425
==2595== I1  miss rate:        0.84%
==2595== LLi miss rate:        0.00%
==2595== 
==2595== D   refs:      130,393,550  (68,817,610 rd   + 61,575,940 wr)
==2595== D1  misses:      1,725,730  ( 1,185,897 rd   +    539,833 wr)
==2595== LLd misses:        255,496  (    15,405 rd   +    240,091 wr)
==2595== D1  miss rate:         1.3% (       1.7%     +        0.9%  )
==2595== LLd miss rate:         0.2% (       0.0%     +        0.4%  )
==2595== 
==2595== LL refs:         4,080,063  ( 3,540,230 rd   +    539,833 wr)
==2595== LL misses:         263,921  (    23,830 rd   +    240,091 wr)
==2595== LL miss rate:          0.1% (       0.0%     +        0.4%  )