==2535== Cachegrind, a cache and branch-prediction profiler
==2535== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2535== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==2535== Command: _bin/cxx-opt/osh -n --ast-format none benchmarks/testdata/t9300-fast-import.sh
==2535== Parent PID: 2528
==2535== 
--2535-- warning: L3 cache found, using its data for the LL simulation.
==2535== 
==2535== I   refs:      13,884,948
==2535== I1  misses:        61,977
==2535== LLi misses:         7,895
==2535== I1  miss rate:       0.45%
==2535== LLi miss rate:       0.06%
==2535== 
==2535== D   refs:       6,257,035  (3,515,476 rd   + 2,741,559 wr)
==2535== D1  misses:        71,759  (   38,121 rd   +    33,638 wr)
==2535== LLd misses:        43,931  (   13,497 rd   +    30,434 wr)
==2535== D1  miss rate:        1.1% (      1.1%     +       1.2%  )
==2535== LLd miss rate:        0.7% (      0.4%     +       1.1%  )
==2535== 
==2535== LL refs:          133,736  (  100,098 rd   +    33,638 wr)
==2535== LL misses:         51,826  (   21,392 rd   +    30,434 wr)
==2535== LL miss rate:         0.3% (      0.1%     +       1.1%  )