==3262== Cachegrind, a cache and branch-prediction profiler
==3262== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==3262== Using Valgrind-3.19.0 and LibVEX; rerun with -h for copyright info
==3262== Command: _bin/cxx-opt-sh/mycpp-nosouffle/osh -n --ast-format none benchmarks/testdata/ltmain.sh
==3262== Parent PID: 3255
==3262== 
--3262-- warning: L3 cache found, using its data for the LL simulation.
==3262== brk segment overflow in thread #1: can't grow to 0x4840000
==3262== (see section Limitations in user manual)
==3262== NOTE: further instances of this message will not be shown
==3262== 
==3262== I   refs:      112,480,958
==3262== I1  misses:      1,123,019
==3262== LLi misses:          8,834
==3262== I1  miss rate:        1.00%
==3262== LLi miss rate:        0.01%
==3262== 
==3262== D   refs:       53,103,180  (27,608,460 rd   + 25,494,720 wr)
==3262== D1  misses:        736,147  (   437,344 rd   +    298,803 wr)
==3262== LLd misses:        166,073  (    12,778 rd   +    153,295 wr)
==3262== D1  miss rate:         1.4% (       1.6%     +        1.2%  )
==3262== LLd miss rate:         0.3% (       0.0%     +        0.6%  )
==3262== 
==3262== LL refs:         1,859,166  ( 1,560,363 rd   +    298,803 wr)
==3262== LL misses:         174,907  (    21,612 rd   +    153,295 wr)
==3262== LL miss rate:          0.1% (       0.0%     +        0.6%  )