==8326== Cachegrind, a cache and branch-prediction profiler
==8326== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8326== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8326== Command: _bin/osh_eval.opt.stripped -n --ast-format none benchmarks/testdata/t9300-fast-import.sh
==8326== Parent PID: 8319
==8326== 
--8326-- warning: L3 cache found, using its data for the LL simulation.
--8326-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8326-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8326== 
==8326== I   refs:      10,137,613
==8326== I1  misses:        46,828
==8326== LLi misses:         3,982
==8326== I1  miss rate:       0.46%
==8326== LLi miss rate:       0.04%
==8326== 
==8326== D   refs:       4,462,438  (2,617,564 rd   + 1,844,874 wr)
==8326== D1  misses:        48,003  (   19,741 rd   +    28,262 wr)
==8326== LLd misses:        35,501  (    8,761 rd   +    26,740 wr)
==8326== D1  miss rate:        1.1% (      0.8%     +       1.5%  )
==8326== LLd miss rate:        0.8% (      0.3%     +       1.4%  )
==8326== 
==8326== LL refs:           94,831  (   66,569 rd   +    28,262 wr)
==8326== LL misses:         39,483  (   12,743 rd   +    26,740 wr)
==8326== LL miss rate:         0.3% (      0.1%     +       1.4%  )