==7962== Cachegrind, a cache and branch-prediction profiler
==7962== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==7962== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==7962== Command: dash -n benchmarks/testdata/test-cmd-util.sh
==7962== Parent PID: 7955
==7962== 
--7962-- warning: L3 cache found, using its data for the LL simulation.
--7962-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--7962-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==7962== 
==7962== I   refs:      570,119
==7962== I1  misses:      1,382
==7962== LLi misses:      1,342
==7962== I1  miss rate:    0.24%
==7962== LLi miss rate:    0.24%
==7962== 
==7962== D   refs:      191,470  (143,647 rd   + 47,823 wr)
==7962== D1  misses:      4,231  (  3,397 rd   +    834 wr)
==7962== LLd misses:      3,257  (  2,507 rd   +    750 wr)
==7962== D1  miss rate:     2.2% (    2.4%     +    1.7%  )
==7962== LLd miss rate:     1.7% (    1.7%     +    1.6%  )
==7962== 
==7962== LL refs:         5,613  (  4,779 rd   +    834 wr)
==7962== LL misses:       4,599  (  3,849 rd   +    750 wr)
==7962== LL miss rate:      0.6% (    0.5%     +    1.6%  )