==8108== Cachegrind, a cache and branch-prediction profiler
==8108== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8108== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8108== Command: dash -n benchmarks/testdata/ltmain.sh
==8108== Parent PID: 8101
==8108== 
--8108-- warning: L3 cache found, using its data for the LL simulation.
--8108-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8108-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8108== 
==8108== I   refs:      17,260,203
==8108== I1  misses:         1,509
==8108== LLi misses:         1,455
==8108== I1  miss rate:       0.01%
==8108== LLi miss rate:       0.01%
==8108== 
==8108== D   refs:       6,534,077  (4,396,753 rd   + 2,137,324 wr)
==8108== D1  misses:        19,520  (    8,465 rd   +    11,055 wr)
==8108== LLd misses:        11,177  (    2,958 rd   +     8,219 wr)
==8108== D1  miss rate:        0.3% (      0.2%     +       0.5%  )
==8108== LLd miss rate:        0.2% (      0.1%     +       0.4%  )
==8108== 
==8108== LL refs:           21,029  (    9,974 rd   +    11,055 wr)
==8108== LL misses:         12,632  (    4,413 rd   +     8,219 wr)
==8108== LL miss rate:         0.1% (      0.0%     +       0.4%  )