==8058== Cachegrind, a cache and branch-prediction profiler
==8058== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8058== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8058== Command: mksh -n benchmarks/testdata/t9300-fast-import.sh
==8058== Parent PID: 8051
==8058== 
--8058-- warning: L3 cache found, using its data for the LL simulation.
--8058-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8058-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8058== 
==8058== I   refs:      10,734,121
==8058== I1  misses:         2,478
==8058== LLi misses:         1,962
==8058== I1  miss rate:       0.02%
==8058== LLi miss rate:       0.02%
==8058== 
==8058== D   refs:       3,591,049  (2,340,641 rd   + 1,250,408 wr)
==8058== D1  misses:         8,376  (    4,847 rd   +     3,529 wr)
==8058== LLd misses:         5,779  (    2,650 rd   +     3,129 wr)
==8058== D1  miss rate:        0.2% (      0.2%     +       0.3%  )
==8058== LLd miss rate:        0.2% (      0.1%     +       0.3%  )
==8058== 
==8058== LL refs:           10,854  (    7,325 rd   +     3,529 wr)
==8058== LL misses:          7,741  (    4,612 rd   +     3,129 wr)
==8058== LL miss rate:         0.1% (      0.0%     +       0.3%  )