==2548== Cachegrind, a cache and branch-prediction profiler
==2548== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2548== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==2548== Command: _bin/cxx-opt/osh -n --ast-format none benchmarks/testdata/t9300-fast-import.sh
==2548== Parent PID: 2541
==2548== 
--2548-- warning: L3 cache found, using its data for the LL simulation.
==2548== 
==2548== I   refs:      13,871,294
==2548== I1  misses:        58,965
==2548== LLi misses:         7,954
==2548== I1  miss rate:       0.43%
==2548== LLi miss rate:       0.06%
==2548== 
==2548== D   refs:       6,249,582  (3,511,012 rd   + 2,738,570 wr)
==2548== D1  misses:        71,760  (   38,098 rd   +    33,662 wr)
==2548== LLd misses:        43,989  (   13,524 rd   +    30,465 wr)
==2548== D1  miss rate:        1.1% (      1.1%     +       1.2%  )
==2548== LLd miss rate:        0.7% (      0.4%     +       1.1%  )
==2548== 
==2548== LL refs:          130,725  (   97,063 rd   +    33,662 wr)
==2548== LL misses:         51,943  (   21,478 rd   +    30,465 wr)
==2548== LL miss rate:         0.3% (      0.1%     +       1.1%  )