==8282== Cachegrind, a cache and branch-prediction profiler
==8282== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8282== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8282== Command: mksh -n benchmarks/testdata/ltmain.sh
==8282== Parent PID: 8275
==8282== 
--8282-- warning: L3 cache found, using its data for the LL simulation.
--8282-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8282-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8282== 
==8282== I   refs:      60,089,513
==8282== I1  misses:         7,536
==8282== LLi misses:         2,082
==8282== I1  miss rate:       0.01%
==8282== LLi miss rate:       0.00%
==8282== 
==8282== D   refs:      21,742,801  (13,914,497 rd   + 7,828,304 wr)
==8282== D1  misses:       353,096  (   316,494 rd   +    36,602 wr)
==8282== LLd misses:        23,736  (     5,142 rd   +    18,594 wr)
==8282== D1  miss rate:        1.6% (       2.3%     +       0.5%  )
==8282== LLd miss rate:        0.1% (       0.0%     +       0.2%  )
==8282== 
==8282== LL refs:          360,632  (   324,030 rd   +    36,602 wr)
==8282== LL misses:         25,818  (     7,224 rd   +    18,594 wr)
==8282== LL miss rate:         0.0% (       0.0%     +       0.2%  )