[Bug libgomp/65589] OpenMP 3.1 produces random results for simple array copy

2015-03-27 Thread felix.ospald at gmx dot de
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65589 felix.ospald at gmx dot de changed: What|Removed |Added Status|WAITING |RESOLVED Resolution

[Bug libgomp/65589] OpenMP 3.1 produces random results for simple array copy

2015-03-27 Thread felix.ospald at gmx dot de
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65589 --- Comment #11 from felix.ospald at gmx dot de --- I can confirm that the bug still exists for the trunk version (rev 221721) of gcc. So as mentioned above it is very likely the kernel bug.

[Bug libgomp/65589] OpenMP 3.1 produces random results for simple array copy

2015-03-27 Thread felix.ospald at gmx dot de
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65589 --- Comment #10 from felix.ospald at gmx dot de --- gcc still compiles, but I think I found the answer here: http://stackoverflow.com/questions/24219263/openmp-on-a-2-socket-system "The problem was due to a bug in Linux Kernel kernel 3.11

[Bug libgomp/65589] OpenMP 3.1 produces random results for simple array copy

2015-03-26 Thread felix.ospald at gmx dot de
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65589 --- Comment #9 from felix.ospald at gmx dot de --- Hi, I attached an output from strace ./main 2>&1 | tee log Maybe this helps. I see that there are some futex EAGAIN errors. I'm not sure if this is a problem (I also get them on my notebook).

[Bug libgomp/65589] OpenMP 3.1 produces random results for simple array copy

2015-03-26 Thread felix.ospald at gmx dot de
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65589 --- Comment #8 from felix.ospald at gmx dot de --- Created attachment 35156 --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=35156&action=edit strace output

[Bug libgomp/65589] OpenMP 3.1 produces random results for simple array copy

2015-03-26 Thread felix.ospald at gmx dot de
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65589 --- Comment #7 from felix.ospald at gmx dot de --- (In reply to Andrew Pinski from comment #6) > I ran for 2836 iterations with the trunk GCC and aarch64 which has a very > weak memory ordering and did not run into a single failure. This i

[Bug libgomp/65589] OpenMP 3.1 produces random results for simple array copy

2015-03-26 Thread felix.ospald at gmx dot de
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65589 --- Comment #4 from felix.ospald at gmx dot de --- (In reply to Jakub Jelinek from comment #3) > Can't reproduce here, with neither 4.8 nor 4.9. But tested just on 16 > threads box (both with argument 16 and 32). With only 16 thr

[Bug libgomp/65589] OpenMP 3.1 produces random results for simple array copy

2015-03-26 Thread felix.ospald at gmx dot de
https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65589 --- Comment #2 from felix.ospald at gmx dot de --- (In reply to Andrew Pinski from comment #1) > I cannot reproduce this on an AARCH64 target with 48 cores with the trunk. I do not have the trunk installed. What do you suggest? Should I comp

[Bug libgomp/65589] New: OpenMP 3.1 produces random results for simple array copy

2015-03-26 Thread felix.ospald at gmx dot de
Priority: P3 Component: libgomp Assignee: unassigned at gcc dot gnu.org Reporter: felix.ospald at gmx dot de CC: jakub at gcc dot gnu.org /* gcc --version gcc (SUSE Linux) 4.8.1 20130909 [gcc-4_8-branch revision 202388] echo | cpp -fopenmp -dM | grep -i