==2614== Cachegrind, a cache and branch-prediction profiler
==2614== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2614== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==2614== Command: _bin/cxx-opt/osh -n --ast-format none benchmarks/testdata/ltmain.sh
==2614== Parent PID: 2607
==2614== 
--2614-- warning: L3 cache found, using its data for the LL simulation.
==2614== brk segment overflow in thread #1: can't grow to 0x482b000
==2614== (see section Limitations in user manual)
==2614== NOTE: further instances of this message will not be shown
==2614== 
==2614== I   refs:      112,717,830
==2614== I1  misses:      1,015,463
==2614== LLi misses:          8,779
==2614== I1  miss rate:        0.90%
==2614== LLi miss rate:        0.01%
==2614== 
==2614== D   refs:       53,184,195  (27,628,237 rd   + 25,555,958 wr)
==2614== D1  misses:        670,731  (   389,737 rd   +    280,994 wr)
==2614== LLd misses:        157,138  (    13,974 rd   +    143,164 wr)
==2614== D1  miss rate:         1.3% (       1.4%     +        1.1%  )
==2614== LLd miss rate:         0.3% (       0.1%     +        0.6%  )
==2614== 
==2614== LL refs:         1,686,194  ( 1,405,200 rd   +    280,994 wr)
==2614== LL misses:         165,917  (    22,753 rd   +    143,164 wr)
==2614== LL miss rate:          0.1% (       0.0%     +        0.6%  )