==8223== Cachegrind, a cache and branch-prediction profiler
==8223== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8223== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8223== Command: mksh -n benchmarks/testdata/abuild
==8223== Parent PID: 8216
==8223== 
--8223-- warning: L3 cache found, using its data for the LL simulation.
--8223-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8223-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8223== 
==8223== I   refs:      22,516,921
==8223== I1  misses:         9,510
==8223== LLi misses:         2,146
==8223== I1  miss rate:       0.04%
==8223== LLi miss rate:       0.01%
==8223== 
==8223== D   refs:       8,178,227  (5,147,524 rd   + 3,030,703 wr)
==8223== D1  misses:        79,030  (   63,153 rd   +    15,877 wr)
==8223== LLd misses:         7,200  (    3,042 rd   +     4,158 wr)
==8223== D1  miss rate:        1.0% (      1.2%     +       0.5%  )
==8223== LLd miss rate:        0.1% (      0.1%     +       0.1%  )
==8223== 
==8223== LL refs:           88,540  (   72,663 rd   +    15,877 wr)
==8223== LL misses:          9,346  (    5,188 rd   +     4,158 wr)
==8223== LL miss rate:         0.0% (      0.0%     +       0.1%  )