==1868== Cachegrind, a cache and branch-prediction profiler
==1868== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==1868== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==1868== Command: bash -n benchmarks/testdata/functions
==1868== Parent PID: 1861
==1868== 
--1868-- warning: L3 cache found, using its data for the LL simulation.
==1868== 
==1868== I   refs:      28,169,399
==1868== I1  misses:        11,985
==1868== LLi misses:         2,810
==1868== I1  miss rate:       0.04%
==1868== LLi miss rate:       0.01%
==1868== 
==1868== D   refs:      11,424,989  (7,238,901 rd   + 4,186,088 wr)
==1868== D1  misses:        26,057  (   20,443 rd   +     5,614 wr)
==1868== LLd misses:         7,745  (    4,849 rd   +     2,896 wr)
==1868== D1  miss rate:        0.2% (      0.3%     +       0.1%  )
==1868== LLd miss rate:        0.1% (      0.1%     +       0.1%  )
==1868== 
==1868== LL refs:           38,042  (   32,428 rd   +     5,614 wr)
==1868== LL misses:         10,555  (    7,659 rd   +     2,896 wr)
==1868== LL miss rate:         0.0% (      0.0%     +       0.1%  )