Possible bug in inlined string functions of icc Version 11.1 (Build 20090511 Package ID: l_cproc_p_11.1.038)

Brandon Hewitt (Intel)
Total Points:
2,340
Status Points:
1,840
Brown Belt
August 21, 2009 11:21 AM PDT
Rate
 
#3 Reply to #2
Hi,
thanks for the quick reply. The submitted example is a close to minimal test case.
Command lines:
icc tstr.c -g -O2
...
valgrind ./a.out | & less
valgrind versio is 3.3.0, flags enabled by default are:  -v  --trace-children=yes --time-stamp=yes --error-limit=no --leak-check=full
--leak-resolution=high

best,
Andreas


Looks like this is a known limitation of valgrind.  See http://valgrind.org/docs/manual/dist.news.html under Known Limitations:

- Memcheck is unusable with the Intel compiler suite version 11.1, when it generates code for SSE2-and-above capable targets. This is because of icc's use of highly optimised inlined strlen implementations. It causes Memcheck to report huge numbers of false errors even in simple programs. Helgrind and DRD may also have problems.


If you're using the compiler for 32-bit, you can use the -mia32 option to workaround this, but this option will likely impact your performance.
--------
Brandon Hewitt
Intel Developer Support

Tools Knowledge Base: http://software.intel.com/en-us/articles/tools
Software Product support info: http://www.intel.com/software/support

* Other names and brands may be claimed as the property of others.


Intel Software Network Forums Statistics

8479 users have contributed to 31612 threads and 100674 posts to date.
In the past 24 hours, we have 29 new thread(s) 112 new posts(s), and 168 new user(s).

In the past 3 days, the most popular thread for everyone has been gemm(A,A,A) like possible? The most posts were made to gemm(A,A,A) like possible? The post with the most views is Dear Steve, excuse me for a d

Please welcome our newest member zhpn