==8150== Cachegrind, a cache and branch-prediction profiler
==8150== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8150== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8150== Command: mksh -n benchmarks/testdata/functions
==8150== Parent PID: 8143
==8150== 
--8150-- warning: L3 cache found, using its data for the LL simulation.
--8150-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8150-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8150== 
==8150== I   refs:      14,893,064
==8150== I1  misses:         7,091
==8150== LLi misses:         2,137
==8150== I1  miss rate:       0.05%
==8150== LLi miss rate:       0.01%
==8150== 
==8150== D   refs:       5,358,484  (3,384,982 rd   + 1,973,502 wr)
==8150== D1  misses:        38,772  (   29,022 rd   +     9,750 wr)
==8150== LLd misses:         6,299  (    2,889 rd   +     3,410 wr)
==8150== D1  miss rate:        0.7% (      0.9%     +       0.5%  )
==8150== LLd miss rate:        0.1% (      0.1%     +       0.2%  )
==8150== 
==8150== LL refs:           45,863  (   36,113 rd   +     9,750 wr)
==8150== LL misses:          8,436  (    5,026 rd   +     3,410 wr)
==8150== LL miss rate:         0.0% (      0.0%     +       0.2%  )