==2559== Cachegrind, a cache and branch-prediction profiler
==2559== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2559== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==2559== Command: _bin/cxx-opt/osh -n --ast-format none benchmarks/testdata/t9300-fast-import.sh
==2559== Parent PID: 2552
==2559== 
--2559-- warning: L3 cache found, using its data for the LL simulation.
==2559== 
==2559== I   refs:      13,862,360
==2559== I1  misses:        61,886
==2559== LLi misses:         7,943
==2559== I1  miss rate:       0.45%
==2559== LLi miss rate:       0.06%
==2559== 
==2559== D   refs:       6,246,028  (3,508,286 rd   + 2,737,742 wr)
==2559== D1  misses:        71,124  (   37,951 rd   +    33,173 wr)
==2559== LLd misses:        43,153  (   13,164 rd   +    29,989 wr)
==2559== D1  miss rate:        1.1% (      1.1%     +       1.2%  )
==2559== LLd miss rate:        0.7% (      0.4%     +       1.1%  )
==2559== 
==2559== LL refs:          133,010  (   99,837 rd   +    33,173 wr)
==2559== LL misses:         51,096  (   21,107 rd   +    29,989 wr)
==2559== LL miss rate:         0.3% (      0.1%     +       1.1%  )