==8490== Cachegrind, a cache and branch-prediction profiler
==8490== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8490== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8490== Command: _bin/osh_eval.opt.stripped -n --ast-format none benchmarks/testdata/test-cmd-util.sh
==8490== Parent PID: 8483
==8490== 
--8490-- warning: L3 cache found, using its data for the LL simulation.
--8490-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8490-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8490== 
==8490== I   refs:      77,870,387
==8490== I1  misses:       768,932
==8490== LLi misses:         4,913
==8490== I1  miss rate:       0.99%
==8490== LLi miss rate:       0.01%
==8490== 
==8490== D   refs:      36,869,900  (19,488,720 rd   + 17,381,180 wr)
==8490== D1  misses:       265,491  (    50,103 rd   +    215,388 wr)
==8490== LLd misses:       216,186  (    11,761 rd   +    204,425 wr)
==8490== D1  miss rate:        0.7% (       0.3%     +        1.2%  )
==8490== LLd miss rate:        0.6% (       0.1%     +        1.2%  )
==8490== 
==8490== LL refs:        1,034,423  (   819,035 rd   +    215,388 wr)
==8490== LL misses:        221,099  (    16,674 rd   +    204,425 wr)
==8490== LL miss rate:         0.2% (       0.0%     +        1.2%  )