==2470== Cachegrind, a cache and branch-prediction profiler
==2470== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2470== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==2470== Command: _bin/cxx-opt/osh -n --ast-format none benchmarks/testdata/t4014-format-patch.sh
==2470== Parent PID: 2463
==2470== 
--2470-- warning: L3 cache found, using its data for the LL simulation.
==2470== 
==2470== I   refs:      11,800,954
==2470== I1  misses:        69,027
==2470== LLi misses:         8,380
==2470== I1  miss rate:       0.58%
==2470== LLi miss rate:       0.07%
==2470== 
==2470== D   refs:       5,214,868  (2,947,131 rd   + 2,267,737 wr)
==2470== D1  misses:        63,356  (   36,052 rd   +    27,304 wr)
==2470== LLd misses:        37,866  (   13,245 rd   +    24,621 wr)
==2470== D1  miss rate:        1.2% (      1.2%     +       1.2%  )
==2470== LLd miss rate:        0.7% (      0.4%     +       1.1%  )
==2470== 
==2470== LL refs:          132,383  (  105,079 rd   +    27,304 wr)
==2470== LL misses:         46,246  (   21,625 rd   +    24,621 wr)
==2470== LL miss rate:         0.3% (      0.1%     +       1.1%  )