==8066== Cachegrind, a cache and branch-prediction profiler
==8066== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8066== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8066== Command: mksh -n benchmarks/testdata/functions
==8066== Parent PID: 8059
==8066== 
--8066-- warning: L3 cache found, using its data for the LL simulation.
--8066-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8066-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8066== 
==8066== I   refs:      14,888,056
==8066== I1  misses:         7,149
==8066== LLi misses:         2,143
==8066== I1  miss rate:       0.05%
==8066== LLi miss rate:       0.01%
==8066== 
==8066== D   refs:       5,356,413  (3,383,847 rd   + 1,972,566 wr)
==8066== D1  misses:        38,187  (   28,503 rd   +     9,684 wr)
==8066== LLd misses:         6,287  (    2,900 rd   +     3,387 wr)
==8066== D1  miss rate:        0.7% (      0.8%     +       0.5%  )
==8066== LLd miss rate:        0.1% (      0.1%     +       0.2%  )
==8066== 
==8066== LL refs:           45,336  (   35,652 rd   +     9,684 wr)
==8066== LL misses:          8,430  (    5,043 rd   +     3,387 wr)
==8066== LL miss rate:         0.0% (      0.0%     +       0.2%  )