==8510== Cachegrind, a cache and branch-prediction profiler
==8510== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8510== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8510== Command: _bin/osh_eval.opt.stripped -n --ast-format none benchmarks/testdata/test-cmd-util.sh
==8510== Parent PID: 8503
==8510== 
--8510-- warning: L3 cache found, using its data for the LL simulation.
--8510-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8510-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8510== 
==8510== I   refs:      77,560,883
==8510== I1  misses:       799,010
==8510== LLi misses:         4,934
==8510== I1  miss rate:       1.03%
==8510== LLi miss rate:       0.01%
==8510== 
==8510== D   refs:      36,754,848  (19,388,460 rd   + 17,366,388 wr)
==8510== D1  misses:       269,141  (    53,173 rd   +    215,968 wr)
==8510== LLd misses:       216,184  (    11,738 rd   +    204,446 wr)
==8510== D1  miss rate:        0.7% (       0.3%     +        1.2%  )
==8510== LLd miss rate:        0.6% (       0.1%     +        1.2%  )
==8510== 
==8510== LL refs:        1,068,151  (   852,183 rd   +    215,968 wr)
==8510== LL misses:        221,118  (    16,672 rd   +    204,446 wr)
==8510== LL miss rate:         0.2% (       0.0%     +        1.2%  )