==8188== Cachegrind, a cache and branch-prediction profiler
==8188== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8188== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8188== Command: mksh -n benchmarks/testdata/functions
==8188== Parent PID: 8181
==8188== 
--8188-- warning: L3 cache found, using its data for the LL simulation.
--8188-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8188-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8188== 
==8188== I   refs:      14,890,051
==8188== I1  misses:         7,151
==8188== LLi misses:         2,134
==8188== I1  miss rate:       0.05%
==8188== LLi miss rate:       0.01%
==8188== 
==8188== D   refs:       5,359,137  (3,385,186 rd   + 1,973,951 wr)
==8188== D1  misses:        38,338  (   28,708 rd   +     9,630 wr)
==8188== LLd misses:         6,256  (    2,899 rd   +     3,357 wr)
==8188== D1  miss rate:        0.7% (      0.8%     +       0.5%  )
==8188== LLd miss rate:        0.1% (      0.1%     +       0.2%  )
==8188== 
==8188== LL refs:           45,489  (   35,859 rd   +     9,630 wr)
==8188== LL misses:          8,390  (    5,033 rd   +     3,357 wr)
==8188== LL miss rate:         0.0% (      0.0%     +       0.2%  )