==2549== Cachegrind, a cache and branch-prediction profiler
==2549== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2549== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==2549== Command: _bin/cxx-opt/osh -n --ast-format none benchmarks/testdata/t9300-fast-import.sh
==2549== Parent PID: 2542
==2549== 
--2549-- warning: L3 cache found, using its data for the LL simulation.
==2549== 
==2549== I   refs:      13,871,584
==2549== I1  misses:        60,912
==2549== LLi misses:         7,942
==2549== I1  miss rate:       0.44%
==2549== LLi miss rate:       0.06%
==2549== 
==2549== D   refs:       6,249,689  (3,511,059 rd   + 2,738,630 wr)
==2549== D1  misses:        72,191  (   38,497 rd   +    33,694 wr)
==2549== LLd misses:        43,986  (   13,523 rd   +    30,463 wr)
==2549== D1  miss rate:        1.2% (      1.1%     +       1.2%  )
==2549== LLd miss rate:        0.7% (      0.4%     +       1.1%  )
==2549== 
==2549== LL refs:          133,103  (   99,409 rd   +    33,694 wr)
==2549== LL misses:         51,928  (   21,465 rd   +    30,463 wr)
==2549== LL miss rate:         0.3% (      0.1%     +       1.1%  )