==2533== Cachegrind, a cache and branch-prediction profiler
==2533== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2533== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==2533== Command: _bin/cxx-opt/osh -n --ast-format none benchmarks/testdata/t9300-fast-import.sh
==2533== Parent PID: 2527
==2533== 
--2533-- warning: L3 cache found, using its data for the LL simulation.
==2533== 
==2533== I   refs:      14,009,691
==2533== I1  misses:        57,076
==2533== LLi misses:         7,775
==2533== I1  miss rate:       0.41%
==2533== LLi miss rate:       0.06%
==2533== 
==2533== D   refs:       6,373,448  (3,573,704 rd   + 2,799,744 wr)
==2533== D1  misses:        63,574  (   30,602 rd   +    32,972 wr)
==2533== LLd misses:        43,614  (   13,388 rd   +    30,226 wr)
==2533== D1  miss rate:        1.0% (      0.9%     +       1.2%  )
==2533== LLd miss rate:        0.7% (      0.4%     +       1.1%  )
==2533== 
==2533== LL refs:          120,650  (   87,678 rd   +    32,972 wr)
==2533== LL misses:         51,389  (   21,163 rd   +    30,226 wr)
==2533== LL miss rate:         0.3% (      0.1%     +       1.1%  )