[Bug c++/48659] New: Segmentation fault when using openMP and SSE

[Bug c++/48659] New: Segmentation fault when using openMP and SSE

[npozar at quick dot cz]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=48659

           Summary: Segmentation fault when using openMP and SSE
           Product: gcc
           Version: 4.5.2
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: c++
        AssignedTo: unassigned@gcc.gnu.org
        ReportedBy: npozar@quick.cz


Created attachment 24026
  --> http://gcc.gnu.org/bugzilla/attachment.cgi?id=24026
A code snippet that reproduces the error

g++ tries to save an xmm register using MOVAPD (SSE instruction) to the stack
when switching between working chunks during openMP multithreading. This
obviously causes a random segmentation fault when the stack pointer happens not
be aligned to a 16-byte boundary. 

Please see the attached code. I compile it with g++ 4.5.2 (I'm using MinGW) and
flags -O3 -msse3 -fopenmp.

It is important that the optimization is on and the compiler tries to save the
xmm register containing the constant zero between working chunks. This is the
instruction that causes the segmentation fault if ebp-0x48 is not divisible by
0x10:

0040143a:   movapd %xmm1,-0x48(%ebp) // right here
0040143f:   call 0x4014bc <GOMP_loop_dynamic_next>



PS. I have to admit that I'm completely new to GCC, openMP or SSE (I just
learned about openMP today and I've playing with them for a couple hours only),
so I might be just doing something really stupid.

[Bug c++/48659] Segmentation fault when using openMP and SSE

[rguenth at gcc dot gnu.org]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=48659

--- Comment #1 from Richard Guenther <rguenth at gcc dot gnu.org> 2011-04-18 12:17:12 UTC ---
On linux we assume a 16 byte aligned stack for threads, so this might hint
at some MinGW specific issue either in our OMP runtime or with windows
thread handling.

[Bug target/48659] Segmentation fault when using openMP and SSE

[redi at gcc dot gnu.org]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=48659

Jonathan Wakely <redi at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |ktietz at gcc dot gnu.org

--- Comment #2 from Jonathan Wakely <redi at gcc dot gnu.org> 2013-01-26 14:03:44 UTC ---
Kai, is this reproducable with current releases, and can you confirm Richard's
suggestion about threads not having 16-byte aligned stacks?

[Bug target/48659] Segmentation fault when using openMP and SSE

[daniel.f.starke at freenet dot de]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=48659

--- Comment #3 from Daniel Starke <daniel.f.starke at freenet dot de> 2013-01-28 11:53:14 UTC ---
I can confirm this bug for gcc 4.7.2 mingw64. The -mstackrealign command-line
flag can be used as workaround as described on
http://stackoverflow.com/questions/6716654/segmentation-fault-using-openmp-and-sse
until this bug is properly patched.