[Llvm-bgq-discuss] Details behind MPI wrapper for bgclang++

[Hal Finkel]

----- Original Message -----
> From: "Jack Poulson" <jack.poulson at gmail.com>
> To: "Hal Finkel" <hfinkel at anl.gov>
> Cc: "Jeff Hammond" <jhammond at alcf.anl.gov>, llvm-bgq-discuss at lists.alcf.anl.gov
> Sent: Friday, March 1, 2013 3:07:17 PM
> Subject: Re: [Llvm-bgq-discuss] Details behind MPI wrapper for bgclang++
> 
> On Fri, Mar 1, 2013 at 1:03 PM, Jack Poulson < jack.poulson at gmail.com
> > wrote:
> 
> 
> 
> 
> On Fri, Mar 1, 2013 at 12:43 PM, Hal Finkel < hfinkel at anl.gov >
> wrote:
> 
> 
> 
> 
> The lightweight core files are really text files, I looked at the
> line:
> While executing instruction at..........0x000000000100c7c4
> 
> Then I ran powerpc64-bgq-linux-objdump -C -d Backproj-2d and looked
> at the assembly around address 100c7c4 (if you search for it in the
> file, note that objdump may omit the leading 0s in the address).
> 
> 
> 
> 
> Thanks!
> 
> 
> 
> 
> Can you try compiling/linking with
> /home/projects/llvm/r175919-20130222/bin/bgclang++ instead of the
> default one; this is a newer build and I'd like to see if it still
> has whatever bug is yielding this miscompile.
> 
> 
> Strangely enough, my executable ran correctly with the new version of
> LLVM (and passed my accuracy tests). I'm rerunning it again right
> now to help rule out whether or not that was a fluke.
> 
> Any ideas as to what might have been the major change in the new
> release?
> 
> 
> 
> Sigh. It was a fluke.

Hrmm... this being something that sometimes works is interesting. Are there any sources of non-determinism here? [I suppose that running on different partitions could cause PAMI to malloc memory differently; Jeff?]

> 
> Perhaps we should take this offline to avoid spamming everyone else
> on the list? I will try linking statically next.

Let's see if static linking "fixes" it; the list would certainly like to know that ;)

 -Hal

> 
> Jack
> 
>