==2580== Cachegrind, a cache and branch-prediction profiler
==2580== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2580== Using Valgrind-3.19.0 and LibVEX; rerun with -h for copyright info
==2580== Command: bash -n benchmarks/testdata/t9300-fast-import.sh
==2580== Parent PID: 2573
==2580== 
--2580-- warning: L3 cache found, using its data for the LL simulation.
==2580== 
==2580== I   refs:      16,672,903
==2580== I1  misses:         6,134
==2580== LLi misses:         2,984
==2580== I1  miss rate:       0.04%
==2580== LLi miss rate:       0.02%
==2580== 
==2580== D   refs:       5,504,603  (3,917,190 rd   + 1,587,413 wr)
==2580== D1  misses:        10,699  (    7,223 rd   +     3,476 wr)
==2580== LLd misses:         7,311  (    4,213 rd   +     3,098 wr)
==2580== D1  miss rate:        0.2% (      0.2%     +       0.2%  )
==2580== LLd miss rate:        0.1% (      0.1%     +       0.2%  )
==2580== 
==2580== LL refs:           16,833  (   13,357 rd   +     3,476 wr)
==2580== LL misses:         10,295  (    7,197 rd   +     3,098 wr)
==2580== LL miss rate:         0.0% (      0.0%     +       0.2%  )