==2348== Cachegrind, a cache and branch-prediction profiler
==2348== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2348== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==2348== Command: _bin/cxx-opt/osh -n --ast-format none benchmarks/testdata/t9300-fast-import.sh
==2348== Parent PID: 2341
==2348== 
--2348-- warning: L3 cache found, using its data for the LL simulation.
==2348== 
==2348== I   refs:      14,037,042
==2348== I1  misses:        63,163
==2348== LLi misses:         7,756
==2348== I1  miss rate:       0.45%
==2348== LLi miss rate:       0.06%
==2348== 
==2348== D   refs:       6,367,034  (3,566,246 rd   + 2,800,788 wr)
==2348== D1  misses:        72,253  (   38,729 rd   +    33,524 wr)
==2348== LLd misses:        43,728  (   13,421 rd   +    30,307 wr)
==2348== D1  miss rate:        1.1% (      1.1%     +       1.2%  )
==2348== LLd miss rate:        0.7% (      0.4%     +       1.1%  )
==2348== 
==2348== LL refs:          135,416  (  101,892 rd   +    33,524 wr)
==2348== LL misses:         51,484  (   21,177 rd   +    30,307 wr)
==2348== LL miss rate:         0.3% (      0.1%     +       1.1%  )