==8278== Cachegrind, a cache and branch-prediction profiler
==8278== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8278== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8278== Command: _bin/osh_eval.opt.stripped -n --ast-format none benchmarks/testdata/functions
==8278== Parent PID: 8271
==8278== 
--8278-- warning: L3 cache found, using its data for the LL simulation.
--8278-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8278-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8278== 
==8278== I   refs:      23,739,565
==8278== I1  misses:       243,920
==8278== LLi misses:         4,552
==8278== I1  miss rate:       1.03%
==8278== LLi miss rate:       0.02%
==8278== 
==8278== D   refs:      10,921,418  (5,914,450 rd   + 5,006,968 wr)
==8278== D1  misses:        93,302  (   27,576 rd   +    65,726 wr)
==8278== LLd misses:        68,128  (    9,577 rd   +    58,551 wr)
==8278== D1  miss rate:        0.9% (      0.5%     +       1.3%  )
==8278== LLd miss rate:        0.6% (      0.2%     +       1.2%  )
==8278== 
==8278== LL refs:          337,222  (  271,496 rd   +    65,726 wr)
==8278== LL misses:         72,680  (   14,129 rd   +    58,551 wr)
==8278== LL miss rate:         0.2% (      0.0%     +       1.2%  )