==2624== Cachegrind, a cache and branch-prediction profiler
==2624== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==2624== Using Valgrind-3.19.0 and LibVEX; rerun with -h for copyright info
==2624== Command: bash -n benchmarks/testdata/ltmain.sh
==2624== Parent PID: 2617
==2624== 
--2624-- warning: L3 cache found, using its data for the LL simulation.
==2624== 
==2624== I   refs:      80,310,064
==2624== I1  misses:        27,427
==2624== LLi misses:         3,153
==2624== I1  miss rate:       0.03%
==2624== LLi miss rate:       0.00%
==2624== 
==2624== D   refs:      27,266,511  (19,288,674 rd   + 7,977,837 wr)
==2624== D1  misses:        65,343  (    42,098 rd   +    23,245 wr)
==2624== LLd misses:        22,405  (     4,205 rd   +    18,200 wr)
==2624== D1  miss rate:        0.2% (       0.2%     +       0.3%  )
==2624== LLd miss rate:        0.1% (       0.0%     +       0.2%  )
==2624== 
==2624== LL refs:           92,770  (    69,525 rd   +    23,245 wr)
==2624== LL misses:         25,558  (     7,358 rd   +    18,200 wr)
==2624== LL miss rate:         0.0% (       0.0%     +       0.2%  )