==8459== Cachegrind, a cache and branch-prediction profiler
==8459== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8459== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8459== Command: _bin/osh_eval.opt.stripped -n --ast-format none benchmarks/testdata/t9300-fast-import.sh
==8459== Parent PID: 8452
==8459== 
--8459-- warning: L3 cache found, using its data for the LL simulation.
--8459-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8459-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8459== 
==8459== I   refs:      10,090,747
==8459== I1  misses:        37,988
==8459== LLi misses:         3,969
==8459== I1  miss rate:       0.38%
==8459== LLi miss rate:       0.04%
==8459== 
==8459== D   refs:       4,440,363  (2,604,799 rd   + 1,835,564 wr)
==8459== D1  misses:        47,939  (   19,741 rd   +    28,198 wr)
==8459== LLd misses:        35,503  (    8,765 rd   +    26,738 wr)
==8459== D1  miss rate:        1.1% (      0.8%     +       1.5%  )
==8459== LLd miss rate:        0.8% (      0.3%     +       1.5%  )
==8459== 
==8459== LL refs:           85,927  (   57,729 rd   +    28,198 wr)
==8459== LL misses:         39,472  (   12,734 rd   +    26,738 wr)
==8459== LL miss rate:         0.3% (      0.1%     +       1.5%  )