==8198== Cachegrind, a cache and branch-prediction profiler
==8198== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8198== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8198== Command: mksh -n benchmarks/testdata/ltmain.sh
==8198== Parent PID: 8191
==8198== 
--8198-- warning: L3 cache found, using its data for the LL simulation.
--8198-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8198-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8198== 
==8198== I   refs:      60,169,581
==8198== I1  misses:         7,557
==8198== LLi misses:         2,090
==8198== I1  miss rate:       0.01%
==8198== LLi miss rate:       0.00%
==8198== 
==8198== D   refs:      21,756,124  (13,921,299 rd   + 7,834,825 wr)
==8198== D1  misses:       352,994  (   315,732 rd   +    37,262 wr)
==8198== LLd misses:        23,705  (     5,159 rd   +    18,546 wr)
==8198== D1  miss rate:        1.6% (       2.3%     +       0.5%  )
==8198== LLd miss rate:        0.1% (       0.0%     +       0.2%  )
==8198== 
==8198== LL refs:          360,551  (   323,289 rd   +    37,262 wr)
==8198== LL misses:         25,795  (     7,249 rd   +    18,546 wr)
==8198== LL miss rate:         0.0% (       0.0%     +       0.2%  )