==8464== Cachegrind, a cache and branch-prediction profiler
==8464== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==8464== Using Valgrind-3.13.0 and LibVEX; rerun with -h for copyright info
==8464== Command: mksh -n benchmarks/testdata/test-cmd-util.sh
==8464== Parent PID: 8457
==8464== 
--8464-- warning: L3 cache found, using its data for the LL simulation.
--8464-- warning: specified LL cache: line_size 64  assoc 11  total_size 34,603,008
--8464-- warning: simulated LL cache: line_size 64  assoc 17  total_size 35,651,584
==8464== 
==8464== I   refs:      17,171,074
==8464== I1  misses:         8,788
==8464== LLi misses:         2,167
==8464== I1  miss rate:       0.05%
==8464== LLi miss rate:       0.01%
==8464== 
==8464== D   refs:       6,060,051  (3,880,372 rd   + 2,179,679 wr)
==8464== D1  misses:        56,930  (   45,619 rd   +    11,311 wr)
==8464== LLd misses:         9,290  (    3,099 rd   +     6,191 wr)
==8464== D1  miss rate:        0.9% (      1.2%     +       0.5%  )
==8464== LLd miss rate:        0.2% (      0.1%     +       0.3%  )
==8464== 
==8464== LL refs:           65,718  (   54,407 rd   +    11,311 wr)
==8464== LL misses:         11,457  (    5,266 rd   +     6,191 wr)
==8464== LL miss rate:         0.0% (      0.0%     +       0.3%  )