==8156== Cachegrind, a cache and branch-prediction profiler
==8156== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8156== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8156== Command: mksh -n benchmarks/testdata/abuild
==8156== Parent PID: 8149
==8156== 
--8156-- warning: L3 cache found, using its data for the LL simulation.
--8156-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8156-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8156== 
==8156== I   refs:      22,519,918
==8156== I1  misses:         9,690
==8156== LLi misses:         2,148
==8156== I1  miss rate:       0.04%
==8156== LLi miss rate:       0.01%
==8156== 
==8156== D   refs:       8,179,336  (5,148,301 rd   + 3,031,035 wr)
==8156== D1  misses:        78,819  (   62,869 rd   +    15,950 wr)
==8156== LLd misses:         7,198  (    3,016 rd   +     4,182 wr)
==8156== D1  miss rate:        1.0% (      1.2%     +       0.5%  )
==8156== LLd miss rate:        0.1% (      0.1%     +       0.1%  )
==8156== 
==8156== LL refs:           88,509  (   72,559 rd   +    15,950 wr)
==8156== LL misses:          9,346  (    5,164 rd   +     4,182 wr)
==8156== LL miss rate:         0.0% (      0.0%     +       0.1%  )