==8308== Cachegrind, a cache and branch-prediction profiler
==8308== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8308== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8308== Command: mksh -n benchmarks/testdata/ltmain.sh
==8308== Parent PID: 8301
==8308== 
--8308-- warning: L3 cache found, using its data for the LL simulation.
--8308-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8308-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8308== 
==8308== I   refs:      59,144,297
==8308== I1  misses:         7,441
==8308== LLi misses:         2,081
==8308== I1  miss rate:       0.01%
==8308== LLi miss rate:       0.00%
==8308== 
==8308== D   refs:      21,355,003  (13,680,857 rd   + 7,674,146 wr)
==8308== D1  misses:       308,927  (   272,243 rd   +    36,684 wr)
==8308== LLd misses:        23,775  (     5,139 rd   +    18,636 wr)
==8308== D1  miss rate:        1.4% (       2.0%     +       0.5%  )
==8308== LLd miss rate:        0.1% (       0.0%     +       0.2%  )
==8308== 
==8308== LL refs:          316,368  (   279,684 rd   +    36,684 wr)
==8308== LL misses:         25,856  (     7,220 rd   +    18,636 wr)
==8308== LL miss rate:         0.0% (       0.0%     +       0.2%  )