==2584== Cachegrind, a cache and branch-prediction profiler
==2584== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2584== Using Valgrind-3.19.0 and LibVEX; rerun with -h for copyright info
==2584== Command: bash -n benchmarks/testdata/t9300-fast-import.sh
==2584== Parent PID: 2577
==2584== 
--2584-- warning: L3 cache found, using its data for the LL simulation.
==2584== 
==2584== I   refs:      16,659,503
==2584== I1  misses:         5,755
==2584== LLi misses:         2,979
==2584== I1  miss rate:       0.03%
==2584== LLi miss rate:       0.02%
==2584== 
==2584== D   refs:       5,500,234  (3,914,613 rd   + 1,585,621 wr)
==2584== D1  misses:         9,479  (    6,183 rd   +     3,296 wr)
==2584== LLd misses:         7,301  (    4,210 rd   +     3,091 wr)
==2584== D1  miss rate:        0.2% (      0.2%     +       0.2%  )
==2584== LLd miss rate:        0.1% (      0.1%     +       0.2%  )
==2584== 
==2584== LL refs:           15,234  (   11,938 rd   +     3,296 wr)
==2584== LL misses:         10,280  (    7,189 rd   +     3,091 wr)
==2584== LL miss rate:         0.0% (      0.0%     +       0.2%  )