==2473== Cachegrind, a cache and branch-prediction profiler
==2473== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2473== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==2473== Command: _bin/cxx-opt/osh -n --ast-format none benchmarks/testdata/t4014-format-patch.sh
==2473== Parent PID: 2466
==2473== 
--2473-- warning: L3 cache found, using its data for the LL simulation.
==2473== 
==2473== I   refs:      11,812,188
==2473== I1  misses:        77,315
==2473== LLi misses:         8,379
==2473== I1  miss rate:       0.65%
==2473== LLi miss rate:       0.07%
==2473== 
==2473== D   refs:       5,219,592  (2,949,784 rd   + 2,269,808 wr)
==2473== D1  misses:        63,620  (   35,965 rd   +    27,655 wr)
==2473== LLd misses:        37,951  (   13,265 rd   +    24,686 wr)
==2473== D1  miss rate:        1.2% (      1.2%     +       1.2%  )
==2473== LLd miss rate:        0.7% (      0.4%     +       1.1%  )
==2473== 
==2473== LL refs:          140,935  (  113,280 rd   +    27,655 wr)
==2473== LL misses:         46,330  (   21,644 rd   +    24,686 wr)
==2473== LL miss rate:         0.3% (      0.1%     +       1.1%  )