==8265== Cachegrind, a cache and branch-prediction profiler
==8265== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8265== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8265== Command: mksh -n benchmarks/testdata/ltmain.sh
==8265== Parent PID: 8258
==8265== 
--8265-- warning: L3 cache found, using its data for the LL simulation.
--8265-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8265-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8265== 
==8265== I   refs:      60,089,612
==8265== I1  misses:         7,536
==8265== LLi misses:         2,082
==8265== I1  miss rate:       0.01%
==8265== LLi miss rate:       0.00%
==8265== 
==8265== D   refs:      21,742,810  (13,914,506 rd   + 7,828,304 wr)
==8265== D1  misses:       353,095  (   316,493 rd   +    36,602 wr)
==8265== LLd misses:        23,736  (     5,142 rd   +    18,594 wr)
==8265== D1  miss rate:        1.6% (       2.3%     +       0.5%  )
==8265== LLd miss rate:        0.1% (       0.0%     +       0.2%  )
==8265== 
==8265== LL refs:          360,631  (   324,029 rd   +    36,602 wr)
==8265== LL misses:         25,818  (     7,224 rd   +    18,594 wr)
==8265== LL miss rate:         0.0% (       0.0%     +       0.2%  )