==2602== Cachegrind, a cache and branch-prediction profiler
==2602== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2602== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==2602== Command: _bin/cxx-opt/osh -n --ast-format none benchmarks/testdata/ltmain.sh
==2602== Parent PID: 2595
==2602== 
--2602-- warning: L3 cache found, using its data for the LL simulation.
==2602== brk segment overflow in thread #1: can't grow to 0x482b000
==2602== (see section Limitations in user manual)
==2602== NOTE: further instances of this message will not be shown
==2602== 
==2602== I   refs:      112,717,745
==2602== I1  misses:        987,655
==2602== LLi misses:          8,749
==2602== I1  miss rate:        0.88%
==2602== LLi miss rate:        0.01%
==2602== 
==2602== D   refs:       53,183,974  (27,628,045 rd   + 25,555,929 wr)
==2602== D1  misses:        669,403  (   388,269 rd   +    281,134 wr)
==2602== LLd misses:        157,136  (    13,970 rd   +    143,166 wr)
==2602== D1  miss rate:         1.3% (       1.4%     +        1.1%  )
==2602== LLd miss rate:         0.3% (       0.1%     +        0.6%  )
==2602== 
==2602== LL refs:         1,657,058  ( 1,375,924 rd   +    281,134 wr)
==2602== LL misses:         165,885  (    22,719 rd   +    143,166 wr)
==2602== LL miss rate:          0.1% (       0.0%     +        0.6%  )