==8530== Cachegrind, a cache and branch-prediction profiler
==8530== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8530== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8530== Command: _bin/osh_eval.opt.stripped -n --ast-format none benchmarks/testdata/ltmain.sh
==8530== Parent PID: 8523
==8530== 
--8530-- warning: L3 cache found, using its data for the LL simulation.
--8530-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8530-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8530== 
==8530== I   refs:      89,319,874
==8530== I1  misses:       987,177
==8530== LLi misses:         4,755
==8530== I1  miss rate:       1.11%
==8530== LLi miss rate:       0.01%
==8530== 
==8530== D   refs:      42,500,897  (22,441,618 rd   + 20,059,279 wr)
==8530== D1  misses:       329,592  (    68,252 rd   +    261,340 wr)
==8530== LLd misses:       248,551  (    12,062 rd   +    236,489 wr)
==8530== D1  miss rate:        0.8% (       0.3%     +        1.3%  )
==8530== LLd miss rate:        0.6% (       0.1%     +        1.2%  )
==8530== 
==8530== LL refs:        1,316,769  ( 1,055,429 rd   +    261,340 wr)
==8530== LL misses:        253,306  (    16,817 rd   +    236,489 wr)
==8530== LL miss rate:         0.2% (       0.0%     +        1.2%  )