==8227== Cachegrind, a cache and branch-prediction profiler
==8227== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8227== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8227== Command: mksh -n benchmarks/testdata/t9300-fast-import.sh
==8227== Parent PID: 8220
==8227== 
--8227-- warning: L3 cache found, using its data for the LL simulation.
--8227-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8227-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8227== 
==8227== I   refs:      10,749,987
==8227== I1  misses:         2,477
==8227== LLi misses:         1,962
==8227== I1  miss rate:       0.02%
==8227== LLi miss rate:       0.02%
==8227== 
==8227== D   refs:       3,592,472  (2,342,077 rd   + 1,250,395 wr)
==8227== D1  misses:         8,385  (    4,857 rd   +     3,528 wr)
==8227== LLd misses:         5,782  (    2,647 rd   +     3,135 wr)
==8227== D1  miss rate:        0.2% (      0.2%     +       0.3%  )
==8227== LLd miss rate:        0.2% (      0.1%     +       0.3%  )
==8227== 
==8227== LL refs:           10,862  (    7,334 rd   +     3,528 wr)
==8227== LL misses:          7,744  (    4,609 rd   +     3,135 wr)
==8227== LL miss rate:         0.1% (      0.0%     +       0.3%  )