==2347== Cachegrind, a cache and branch-prediction profiler
==2347== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2347== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==2347== Command: _bin/cxx-opt/osh -n --ast-format none benchmarks/testdata/t9300-fast-import.sh
==2347== Parent PID: 2340
==2347== 
--2347-- warning: L3 cache found, using its data for the LL simulation.
==2347== 
==2347== I   refs:      14,038,037
==2347== I1  misses:        76,040
==2347== LLi misses:         7,758
==2347== I1  miss rate:       0.54%
==2347== LLi miss rate:       0.06%
==2347== 
==2347== D   refs:       6,367,656  (3,566,617 rd   + 2,801,039 wr)
==2347== D1  misses:        72,178  (   38,604 rd   +    33,574 wr)
==2347== LLd misses:        43,680  (   13,380 rd   +    30,300 wr)
==2347== D1  miss rate:        1.1% (      1.1%     +       1.2%  )
==2347== LLd miss rate:        0.7% (      0.4%     +       1.1%  )
==2347== 
==2347== LL refs:          148,218  (  114,644 rd   +    33,574 wr)
==2347== LL misses:         51,438  (   21,138 rd   +    30,300 wr)
==2347== LL miss rate:         0.3% (      0.1%     +       1.1%  )