==8553== Cachegrind, a cache and branch-prediction profiler
==8553== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8553== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8553== Command: _bin/osh_eval.opt.stripped -n --ast-format none benchmarks/testdata/ltmain.sh
==8553== Parent PID: 8546
==8553== 
--8553-- warning: L3 cache found, using its data for the LL simulation.
--8553-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8553-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8553== 
==8553== I   refs:      89,638,349
==8553== I1  misses:       992,138
==8553== LLi misses:         4,733
==8553== I1  miss rate:       1.11%
==8553== LLi miss rate:       0.01%
==8553== 
==8553== D   refs:      42,619,206  (22,544,899 rd   + 20,074,307 wr)
==8553== D1  misses:       323,491  (    62,844 rd   +    260,647 wr)
==8553== LLd misses:       248,549  (    12,105 rd   +    236,444 wr)
==8553== D1  miss rate:        0.8% (       0.3%     +        1.3%  )
==8553== LLd miss rate:        0.6% (       0.1%     +        1.2%  )
==8553== 
==8553== LL refs:        1,315,629  ( 1,054,982 rd   +    260,647 wr)
==8553== LL misses:        253,282  (    16,838 rd   +    236,444 wr)
==8553== LL miss rate:         0.2% (       0.0%     +        1.2%  )