==8288== Cachegrind, a cache and branch-prediction profiler
==8288== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8288== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8288== Command: mksh -n benchmarks/testdata/test-cmd-util.sh
==8288== Parent PID: 8281
==8288== 
--8288-- warning: L3 cache found, using its data for the LL simulation.
--8288-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8288-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8288== 
==8288== I   refs:      17,177,570
==8288== I1  misses:         8,788
==8288== LLi misses:         2,168
==8288== I1  miss rate:       0.05%
==8288== LLi miss rate:       0.01%
==8288== 
==8288== D   refs:       6,061,286  (3,881,190 rd   + 2,180,096 wr)
==8288== D1  misses:        57,664  (   46,350 rd   +    11,314 wr)
==8288== LLd misses:         9,282  (    3,095 rd   +     6,187 wr)
==8288== D1  miss rate:        1.0% (      1.2%     +       0.5%  )
==8288== LLd miss rate:        0.2% (      0.1%     +       0.3%  )
==8288== 
==8288== LL refs:           66,452  (   55,138 rd   +    11,314 wr)
==8288== LL misses:         11,450  (    5,263 rd   +     6,187 wr)
==8288== LL miss rate:         0.0% (      0.0%     +       0.3%  )