==2924== Cachegrind, a cache and branch-prediction profiler
==2924== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2924== Using Valgrind-3.19.0 and LibVEX; rerun with -h for copyright info
==2924== Command: _bin/cxx-opt-sh/osh -n --ast-format none benchmarks/testdata/Build.sh
==2924== Parent PID: 2917
==2924== 
--2924-- warning: L3 cache found, using its data for the LL simulation.
==2924== 
==2924== I   refs:      31,406,478
==2924== I1  misses:       154,525
==2924== LLi misses:         8,331
==2924== I1  miss rate:       0.49%
==2924== LLi miss rate:       0.03%
==2924== 
==2924== D   refs:      14,008,310  (7,766,938 rd   + 6,241,372 wr)
==2924== D1  misses:       235,631  (  141,372 rd   +    94,259 wr)
==2924== LLd misses:        64,204  (   12,549 rd   +    51,655 wr)
==2924== D1  miss rate:        1.7% (      1.8%     +       1.5%  )
==2924== LLd miss rate:        0.5% (      0.2%     +       0.8%  )
==2924== 
==2924== LL refs:          390,156  (  295,897 rd   +    94,259 wr)
==2924== LL misses:         72,535  (   20,880 rd   +    51,655 wr)
==2924== LL miss rate:         0.2% (      0.1%     +       0.8%  )