==2502== Cachegrind, a cache and branch-prediction profiler
==2502== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2502== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==2502== Command: _bin/cxx-opt/osh -n --ast-format none benchmarks/testdata/configure-helper.sh
==2502== Parent PID: 2495
==2502== 
--2502-- warning: L3 cache found, using its data for the LL simulation.
==2502== 
==2502== I   refs:      30,519,229
==2502== I1  misses:       166,257
==2502== LLi misses:         8,664
==2502== I1  miss rate:       0.54%
==2502== LLi miss rate:       0.03%
==2502== 
==2502== D   refs:      14,264,092  (7,524,239 rd   + 6,739,853 wr)
==2502== D1  misses:       147,644  (   81,957 rd   +    65,687 wr)
==2502== LLd misses:        54,736  (   13,289 rd   +    41,447 wr)
==2502== D1  miss rate:        1.0% (      1.1%     +       1.0%  )
==2502== LLd miss rate:        0.4% (      0.2%     +       0.6%  )
==2502== 
==2502== LL refs:          313,901  (  248,214 rd   +    65,687 wr)
==2502== LL misses:         63,400  (   21,953 rd   +    41,447 wr)
==2502== LL miss rate:         0.1% (      0.1%     +       0.6%  )