==8158== Cachegrind, a cache and branch-prediction profiler
==8158== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8158== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8158== Command: mksh -n benchmarks/testdata/t9300-fast-import.sh
==8158== Parent PID: 8151
==8158== 
--8158-- warning: L3 cache found, using its data for the LL simulation.
--8158-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8158-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8158== 
==8158== I   refs:      10,748,825
==8158== I1  misses:         2,485
==8158== LLi misses:         1,967
==8158== I1  miss rate:       0.02%
==8158== LLi miss rate:       0.02%
==8158== 
==8158== D   refs:       3,592,304  (2,341,920 rd   + 1,250,384 wr)
==8158== D1  misses:         8,365  (    4,824 rd   +     3,541 wr)
==8158== LLd misses:         5,780  (    2,645 rd   +     3,135 wr)
==8158== D1  miss rate:        0.2% (      0.2%     +       0.3%  )
==8158== LLd miss rate:        0.2% (      0.1%     +       0.3%  )
==8158== 
==8158== LL refs:           10,850  (    7,309 rd   +     3,541 wr)
==8158== LL misses:          7,747  (    4,612 rd   +     3,135 wr)
==8158== LL miss rate:         0.1% (      0.0%     +       0.3%  )