==8102== Cachegrind, a cache and branch-prediction profiler
==8102== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8102== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8102== Command: mksh -n benchmarks/testdata/abuild
==8102== Parent PID: 8095
==8102== 
--8102-- warning: L3 cache found, using its data for the LL simulation.
--8102-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8102-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8102== 
==8102== I   refs:      22,513,434
==8102== I1  misses:         9,641
==8102== LLi misses:         2,147
==8102== I1  miss rate:       0.04%
==8102== LLi miss rate:       0.01%
==8102== 
==8102== D   refs:       8,176,218  (5,146,681 rd   + 3,029,537 wr)
==8102== D1  misses:        78,332  (   62,383 rd   +    15,949 wr)
==8102== LLd misses:         7,200  (    3,045 rd   +     4,155 wr)
==8102== D1  miss rate:        1.0% (      1.2%     +       0.5%  )
==8102== LLd miss rate:        0.1% (      0.1%     +       0.1%  )
==8102== 
==8102== LL refs:           87,973  (   72,024 rd   +    15,949 wr)
==8102== LL misses:          9,347  (    5,192 rd   +     4,155 wr)
==8102== LL miss rate:         0.0% (      0.0%     +       0.1%  )