==2512== Cachegrind, a cache and branch-prediction profiler
==2512== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2512== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==2512== Command: _bin/cxx-opt/osh -n --ast-format none benchmarks/testdata/t9300-fast-import.sh
==2512== Parent PID: 2506
==2512== 
--2512-- warning: L3 cache found, using its data for the LL simulation.
==2512== 
==2512== I   refs:      14,010,254
==2512== I1  misses:        59,887
==2512== LLi misses:         7,786
==2512== I1  miss rate:       0.43%
==2512== LLi miss rate:       0.06%
==2512== 
==2512== D   refs:       6,373,666  (3,573,866 rd   + 2,799,800 wr)
==2512== D1  misses:        73,544  (   37,354 rd   +    36,190 wr)
==2512== LLd misses:        43,661  (   13,414 rd   +    30,247 wr)
==2512== D1  miss rate:        1.2% (      1.0%     +       1.3%  )
==2512== LLd miss rate:        0.7% (      0.4%     +       1.1%  )
==2512== 
==2512== LL refs:          133,431  (   97,241 rd   +    36,190 wr)
==2512== LL misses:         51,447  (   21,200 rd   +    30,247 wr)
==2512== LL miss rate:         0.3% (      0.1%     +       1.1%  )