==2530== Cachegrind, a cache and branch-prediction profiler
==2530== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2530== Using Valgrind-3.19.0 and LibVEX; rerun with -h for copyright info
==2530== Command: bash -n benchmarks/testdata/t4014-format-patch.sh
==2530== Parent PID: 2523
==2530== 
--2530-- warning: L3 cache found, using its data for the LL simulation.
==2530== 
==2530== I   refs:      11,082,677
==2530== I1  misses:         7,078
==2530== LLi misses:         3,122
==2530== I1  miss rate:       0.06%
==2530== LLi miss rate:       0.03%
==2530== 
==2530== D   refs:       3,700,037  (2,617,859 rd   + 1,082,178 wr)
==2530== D1  misses:        10,616  (    7,572 rd   +     3,044 wr)
==2530== LLd misses:         6,881  (    4,207 rd   +     2,674 wr)
==2530== D1  miss rate:        0.3% (      0.3%     +       0.3%  )
==2530== LLd miss rate:        0.2% (      0.2%     +       0.2%  )
==2530== 
==2530== LL refs:           17,694  (   14,650 rd   +     3,044 wr)
==2530== LL misses:         10,003  (    7,329 rd   +     2,674 wr)
==2530== LL miss rate:         0.1% (      0.1%     +       0.2%  )