==2560== Cachegrind, a cache and branch-prediction profiler
==2560== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2560== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==2560== Command: _bin/cxx-opt/osh -n --ast-format none benchmarks/testdata/t9300-fast-import.sh
==2560== Parent PID: 2553
==2560== 
--2560-- warning: L3 cache found, using its data for the LL simulation.
==2560== 
==2560== I   refs:      13,862,014
==2560== I1  misses:        59,450
==2560== LLi misses:         7,941
==2560== I1  miss rate:       0.43%
==2560== LLi miss rate:       0.06%
==2560== 
==2560== D   refs:       6,246,150  (3,508,390 rd   + 2,737,760 wr)
==2560== D1  misses:        71,088  (   37,922 rd   +    33,166 wr)
==2560== LLd misses:        43,152  (   13,165 rd   +    29,987 wr)
==2560== D1  miss rate:        1.1% (      1.1%     +       1.2%  )
==2560== LLd miss rate:        0.7% (      0.4%     +       1.1%  )
==2560== 
==2560== LL refs:          130,538  (   97,372 rd   +    33,166 wr)
==2560== LL misses:         51,093  (   21,106 rd   +    29,987 wr)
==2560== LL miss rate:         0.3% (      0.1%     +       1.1%  )