==7681== Cachegrind, a cache and branch-prediction profiler
==7681== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==7681== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==7681== Command: bash -n benchmarks/testdata/abuild
==7681== Parent PID: 7674
==7681== 
--7681-- warning: L3 cache found, using its data for the LL simulation.
--7681-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--7681-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==7681== 
==7681== I   refs:      45,139,259
==7681== I1  misses:        13,170
==7681== LLi misses:         2,585
==7681== I1  miss rate:       0.03%
==7681== LLi miss rate:       0.01%
==7681== 
==7681== D   refs:      19,304,271  (12,265,669 rd   + 7,038,602 wr)
==7681== D1  misses:        44,486  (    34,339 rd   +    10,147 wr)
==7681== LLd misses:         8,544  (     4,815 rd   +     3,729 wr)
==7681== D1  miss rate:        0.2% (       0.3%     +       0.1%  )
==7681== LLd miss rate:        0.0% (       0.0%     +       0.1%  )
==7681== 
==7681== LL refs:           57,656  (    47,509 rd   +    10,147 wr)
==7681== LL misses:         11,129  (     7,400 rd   +     3,729 wr)
==7681== LL miss rate:         0.0% (       0.0%     +       0.1%  )