==2530== Cachegrind, a cache and branch-prediction profiler
==2530== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2530== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==2530== Command: _bin/cxx-opt/osh -n --ast-format none benchmarks/testdata/test-cmd-util.sh
==2530== Parent PID: 2524
==2530== 
--2530-- warning: L3 cache found, using its data for the LL simulation.
==2530== 
==2530== I   refs:      115,051,404
==2530== I1  misses:        591,163
==2530== LLi misses:          8,779
==2530== I1  miss rate:        0.51%
==2530== LLi miss rate:        0.01%
==2530== 
==2530== D   refs:       54,037,543  (28,581,308 rd   + 25,456,235 wr)
==2530== D1  misses:        661,998  (   446,416 rd   +    215,582 wr)
==2530== LLd misses:        112,474  (    15,103 rd   +     97,371 wr)
==2530== D1  miss rate:         1.2% (       1.6%     +        0.8%  )
==2530== LLd miss rate:         0.2% (       0.1%     +        0.4%  )
==2530== 
==2530== LL refs:         1,253,161  ( 1,037,579 rd   +    215,582 wr)
==2530== LL misses:         121,253  (    23,882 rd   +     97,371 wr)
==2530== LL miss rate:          0.1% (       0.0%     +        0.4%  )