==3502== Cachegrind, a cache and branch-prediction profiler
==3502== Copyright (C) 2002-2017, and GNU GPL'd, by Nicholas Nethercote et al.
==3502== Using Valgrind-3.14.0 and LibVEX; rerun with -h for copyright info
==3502== Command: _bin/cxx-opt/osh_eval.stripped -n --ast-format none benchmarks/testdata/configure-coreutils
==3502== Parent PID: 3497
==3502== 
--3502-- warning: L3 cache found, using its data for the LL simulation.
==3502== brk segment overflow in thread #1: can't grow to 0x4846000
==3502== (see section Limitations in user manual)
==3502== NOTE: further instances of this message will not be shown
==3502== 
==3502== I   refs:      2,889,675,073
==3502== I1  misses:        5,193,688
==3502== LLi misses:            9,510
==3502== I1  miss rate:          0.18%
==3502== LLi miss rate:          0.00%
==3502== 
==3502== D   refs:      1,226,538,911  (627,278,011 rd   + 599,260,900 wr)
==3502== D1  misses:       30,378,829  ( 24,828,396 rd   +   5,550,433 wr)
==3502== LLd misses:       21,884,554  ( 16,928,368 rd   +   4,956,186 wr)
==3502== D1  miss rate:           2.5% (        4.0%     +         0.9%  )
==3502== LLd miss rate:           1.8% (        2.7%     +         0.8%  )
==3502== 
==3502== LL refs:          35,572,517  ( 30,022,084 rd   +   5,550,433 wr)
==3502== LL misses:        21,894,064  ( 16,937,878 rd   +   4,956,186 wr)
==3502== LL miss rate:            0.5% (        0.5%     +         0.8%  )