==8174== Cachegrind, a cache and branch-prediction profiler
==8174== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8174== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8174== Command: mksh -n benchmarks/testdata/functions
==8174== Parent PID: 8167
==8174== 
--8174-- warning: L3 cache found, using its data for the LL simulation.
--8174-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8174-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8174== 
==8174== I   refs:      14,874,149
==8174== I1  misses:         7,152
==8174== LLi misses:         2,140
==8174== I1  miss rate:       0.05%
==8174== LLi miss rate:       0.01%
==8174== 
==8174== D   refs:       5,355,258  (3,383,509 rd   + 1,971,749 wr)
==8174== D1  misses:        38,964  (   29,157 rd   +     9,807 wr)
==8174== LLd misses:         6,223  (    2,877 rd   +     3,346 wr)
==8174== D1  miss rate:        0.7% (      0.9%     +       0.5%  )
==8174== LLd miss rate:        0.1% (      0.1%     +       0.2%  )
==8174== 
==8174== LL refs:           46,116  (   36,309 rd   +     9,807 wr)
==8174== LL misses:          8,363  (    5,017 rd   +     3,346 wr)
==8174== LL miss rate:         0.0% (      0.0%     +       0.2%  )