==8364== Cachegrind, a cache and branch-prediction profiler
==8364== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8364== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8364== Command: mksh -n benchmarks/testdata/functions
==8364== Parent PID: 8357
==8364== 
--8364-- warning: L3 cache found, using its data for the LL simulation.
--8364-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8364-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8364== 
==8364== I   refs:      14,873,360
==8364== I1  misses:         7,112
==8364== LLi misses:         2,137
==8364== I1  miss rate:       0.05%
==8364== LLi miss rate:       0.01%
==8364== 
==8364== D   refs:       5,355,304  (3,383,026 rd   + 1,972,278 wr)
==8364== D1  misses:        38,292  (   28,554 rd   +     9,738 wr)
==8364== LLd misses:         6,266  (    2,887 rd   +     3,379 wr)
==8364== D1  miss rate:        0.7% (      0.8%     +       0.5%  )
==8364== LLd miss rate:        0.1% (      0.1%     +       0.2%  )
==8364== 
==8364== LL refs:           45,404  (   35,666 rd   +     9,738 wr)
==8364== LL misses:          8,403  (    5,024 rd   +     3,379 wr)
==8364== LL miss rate:         0.0% (      0.0%     +       0.2%  )