==8423== Cachegrind, a cache and branch-prediction profiler
==8423== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8423== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8423== Command: _bin/osh_eval.opt.stripped -n --ast-format none benchmarks/testdata/t9300-fast-import.sh
==8423== Parent PID: 8416
==8423== 
--8423-- warning: L3 cache found, using its data for the LL simulation.
--8423-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8423-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8423== 
==8423== I   refs:      10,145,756
==8423== I1  misses:        45,323
==8423== LLi misses:         3,972
==8423== I1  miss rate:       0.45%
==8423== LLi miss rate:       0.04%
==8423== 
==8423== D   refs:       4,465,520  (2,620,217 rd   + 1,845,303 wr)
==8423== D1  misses:        47,591  (   19,511 rd   +    28,080 wr)
==8423== LLd misses:        35,509  (    8,767 rd   +    26,742 wr)
==8423== D1  miss rate:        1.1% (      0.7%     +       1.5%  )
==8423== LLd miss rate:        0.8% (      0.3%     +       1.4%  )
==8423== 
==8423== LL refs:           92,914  (   64,834 rd   +    28,080 wr)
==8423== LL misses:         39,481  (   12,739 rd   +    26,742 wr)
==8423== LL miss rate:         0.3% (      0.1%     +       1.4%  )