==8363== Cachegrind, a cache and branch-prediction profiler
==8363== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8363== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8363== Command: _bin/osh_eval.opt.stripped -n --ast-format none benchmarks/testdata/t4014-format-patch.sh
==8363== Parent PID: 8356
==8363== 
--8363-- warning: L3 cache found, using its data for the LL simulation.
--8363-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8363-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8363== 
==8363== I   refs:      8,481,931
==8363== I1  misses:       53,636
==8363== LLi misses:        4,428
==8363== I1  miss rate:      0.63%
==8363== LLi miss rate:      0.05%
==8363== 
==8363== D   refs:      3,582,999  (2,132,353 rd   + 1,450,646 wr)
==8363== D1  misses:       41,336  (   18,426 rd   +    22,910 wr)
==8363== LLd misses:       30,350  (    8,916 rd   +    21,434 wr)
==8363== D1  miss rate:       1.2% (      0.9%     +       1.6%  )
==8363== LLd miss rate:       0.8% (      0.4%     +       1.5%  )
==8363== 
==8363== LL refs:          94,972  (   72,062 rd   +    22,910 wr)
==8363== LL misses:        34,778  (   13,344 rd   +    21,434 wr)
==8363== LL miss rate:        0.3% (      0.1%     +       1.5%  )