==8123== Cachegrind, a cache and branch-prediction profiler
==8123== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8123== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8123== Command: mksh -n benchmarks/testdata/t4014-format-patch.sh
==8123== Parent PID: 8116
==8123== 
--8123-- warning: L3 cache found, using its data for the LL simulation.
--8123-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8123-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8123== 
==8123== I   refs:      7,768,789
==8123== I1  misses:        3,046
==8123== LLi misses:        2,040
==8123== I1  miss rate:      0.04%
==8123== LLi miss rate:      0.03%
==8123== 
==8123== D   refs:      2,623,050  (1,705,598 rd   + 917,452 wr)
==8123== D1  misses:        9,276  (    5,784 rd   +   3,492 wr)
==8123== LLd misses:        5,547  (    2,674 rd   +   2,873 wr)
==8123== D1  miss rate:       0.4% (      0.3%     +     0.4%  )
==8123== LLd miss rate:       0.2% (      0.2%     +     0.3%  )
==8123== 
==8123== LL refs:          12,322  (    8,830 rd   +   3,492 wr)
==8123== LL misses:         7,587  (    4,714 rd   +   2,873 wr)
==8123== LL miss rate:        0.1% (      0.0%     +     0.3%  )