==8167== Cachegrind, a cache and branch-prediction profiler
==8167== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8167== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8167== Command: mksh -n benchmarks/testdata/configure-helper.sh
==8167== Parent PID: 8160
==8167== 
--8167-- warning: L3 cache found, using its data for the LL simulation.
--8167-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8167-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8167== 
==8167== I   refs:      16,915,881
==8167== I1  misses:         8,557
==8167== LLi misses:         2,147
==8167== I1  miss rate:       0.05%
==8167== LLi miss rate:       0.01%
==8167== 
==8167== D   refs:       6,048,610  (3,865,006 rd   + 2,183,604 wr)
==8167== D1  misses:        53,890  (   43,381 rd   +    10,509 wr)
==8167== LLd misses:         7,185  (    2,959 rd   +     4,226 wr)
==8167== D1  miss rate:        0.9% (      1.1%     +       0.5%  )
==8167== LLd miss rate:        0.1% (      0.1%     +       0.2%  )
==8167== 
==8167== LL refs:           62,447  (   51,938 rd   +    10,509 wr)
==8167== LL misses:          9,332  (    5,106 rd   +     4,226 wr)
==8167== LL miss rate:         0.0% (      0.0%     +       0.2%  )