On Fri, Apr 22, 2011 at 03:50:25PM -0400, Frank Chang wrote:
Hi, For the last day or two I having been trying to get Valgrind/Callgrind 3.6.1 to work on Centos Linux 5.5 using a simple Fibonacci C++ program(shown below). After compiling the program using g++ -g -o MatchUpAccurate MatchUpAccurate.cpp, we run: /home/frankc/DQTTest/valgrind-3.6.1/coregrind/valgrind --tool=callgrind --dump-instr=yes --simulate-cache=yes --collect-jumps=yes ./MatchUpAccurate.exe. Then we get an error message from callgrind(shown below).
... works for me x86_64 with compiled from source valgrind 3.6.1
[tru@liberte ~]$ g++ -g -o f f.cpp [tru@liberte ~]$ module load valgrind [tru@liberte ~]$ valgrind --tool=callgrind --dump-instr=yes --simulate-cache=yes --collect-jumps=yes ./f ==10998== Callgrind, a call-graph generating cache profiler ==10998== Copyright (C) 2002-2010, and GNU GPL'd, by Josef Weidendorfer et al. ==10998== Using Valgrind-3.6.1 and LibVEX; rerun with -h for copyright info ==10998== Command: ./f ==10998== ==10998== For interactive control, run 'callgrind_control -h'. ==10998== ==10998== Events : Ir Dr Dw I1mr D1mr D1mw ILmr DLmr DLmw ==10998== Collected : 1320456 328293 116346 1012 6964 1177 995 4029 894 ==10998== ==10998== I refs: 1,320,456 ==10998== I1 misses: 1,012 ==10998== LLi misses: 995 ==10998== I1 miss rate: 0.7% ==10998== LLi miss rate: 0.7% ==10998== ==10998== D refs: 444,639 (328,293 rd + 116,346 wr) ==10998== D1 misses: 8,141 ( 6,964 rd + 1,177 wr) ==10998== LLd misses: 4,923 ( 4,029 rd + 894 wr) ==10998== D1 miss rate: 1.8% ( 2.1% + 1.0% ) ==10998== LLd miss rate: 1.1% ( 1.2% + 0.7% ) ==10998== ==10998== LL refs: 9,153 ( 7,976 rd + 1,177 wr) ==10998== LL misses: 5,918 ( 5,024 rd + 894 wr) ==10998== LL miss rate: 0.3% ( 0.3% + 0.7% ) [tru@liberte ~]$ rpm -q glibc glibc-devel glibc-2.5-58.el5_6.2.x86_64 glibc-2.5-58.el5_6.2.i686 glibc-devel-2.5-58.el5_6.2.x86_64 glibc-devel-2.5-58.el5_6.2.i386