==8323== Cachegrind, a cache and branch-prediction profiler
==8323== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8323== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8323== Command: _bin/osh_eval.opt.stripped -n --ast-format none benchmarks/testdata/t4014-format-patch.sh
==8323== Parent PID: 8316
==8323== 
--8323-- warning: L3 cache found, using its data for the LL simulation.
--8323-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8323-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8323== 
==8323== I   refs:      8,482,069
==8323== I1  misses:       54,575
==8323== LLi misses:        4,425
==8323== I1  miss rate:      0.64%
==8323== LLi miss rate:      0.05%
==8323== 
==8323== D   refs:      3,583,066  (2,132,392 rd   + 1,450,674 wr)
==8323== D1  misses:       41,348  (   18,420 rd   +    22,928 wr)
==8323== LLd misses:       30,349  (    8,908 rd   +    21,441 wr)
==8323== D1  miss rate:       1.2% (      0.9%     +       1.6%  )
==8323== LLd miss rate:       0.8% (      0.4%     +       1.5%  )
==8323== 
==8323== LL refs:          95,923  (   72,995 rd   +    22,928 wr)
==8323== LL misses:        34,774  (   13,333 rd   +    21,441 wr)
==8323== LL miss rate:        0.3% (      0.1%     +       1.5%  )