==8450== Cachegrind, a cache and branch-prediction profiler
==8450== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8450== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8450== Command: _bin/osh_eval.opt.stripped -n --ast-format none benchmarks/testdata/test-cmd-util.sh
==8450== Parent PID: 8443
==8450== 
--8450-- warning: L3 cache found, using its data for the LL simulation.
--8450-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8450-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8450== 
==8450== I   refs:      77,249,661
==8450== I1  misses:       704,114
==8450== LLi misses:         4,920
==8450== I1  miss rate:       0.91%
==8450== LLi miss rate:       0.01%
==8450== 
==8450== D   refs:      36,626,269  (19,297,493 rd   + 17,328,776 wr)
==8450== D1  misses:       269,387  (    54,282 rd   +    215,105 wr)
==8450== LLd misses:       216,105  (    11,750 rd   +    204,355 wr)
==8450== D1  miss rate:        0.7% (       0.3%     +        1.2%  )
==8450== LLd miss rate:        0.6% (       0.1%     +        1.2%  )
==8450== 
==8450== LL refs:          973,501  (   758,396 rd   +    215,105 wr)
==8450== LL misses:        221,025  (    16,670 rd   +    204,355 wr)
==8450== LL miss rate:         0.2% (       0.0%     +        1.2%  )