<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body style="word-wrap: break-word; -webkit-nbsp-mode: space; -webkit-line-break: after-white-space;" class="">
Hi Erik,
<div class=""><br class="">
</div>
<div class="">As of this (early) morning, r236977-20150511 is available through the module command as both "clang/3.7.r236977” and "clang/nightly” (the latter will of course point to a different version tomorrow). I’ll also tag the r236977 revision as one we
will keep permanently, so it is safe to use if you want to use a fixed version and not the nightly build.</div>
<div class=""><br class="">
</div>
<div class="">If there are problems, please let me know.</div>
<div class=""><br class="">
</div>
<div class="">Michael</div>
<div class=""><br class="">
</div>
<div class="">
<div>
<blockquote type="cite" class="">
<div class="">On 11 May 2015, at 20:19 , Mark Abraham <<a href="mailto:mark.j.abraham@gmail.com" class="">mark.j.abraham@gmail.com</a>> wrote:</div>
<br class="Apple-interchange-newline">
<div class="">
<div dir="ltr" style="font-family: Helvetica; font-size: 12px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px;" class="">
Hi Hal,<br class="">
<br class="">
<div class="">That's great, I have some builds running on vesta.</div>
<div class=""><br class="">
</div>
<div class="">Erik, that version probably won't make it to JUQUEEN until they do their next update. I'll ask them to do so once I've got it working on vesta.</div>
<div class=""><br class="">
</div>
<div class="">Mark</div>
</div>
<br style="font-family: Helvetica; font-size: 12px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px;" class="">
<div class="gmail_quote" style="font-family: Helvetica; font-size: 12px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px;">
On Mon, May 11, 2015 at 6:30 PM Hal Finkel <<a href="mailto:hfinkel@anl.gov" class="">hfinkel@anl.gov</a>> wrote:<br class="">
<blockquote class="gmail_quote" style="margin: 0px 0px 0px 0.8ex; border-left-width: 1px; border-left-color: rgb(204, 204, 204); border-left-style: solid; padding-left: 1ex;">
Hi Erik,<br class="">
<br class="">
This has now been fixed upstream, and the r236977-20150511 nightly build contains the fix. Thanks again for sending the reduced test case.<br class="">
<br class="">
-Hal<br class="">
<br class="">
----- Original Message -----<br class="">
> From: "Erik Lindahl" <<a href="mailto:erik.lindahl@gmail.com" target="_blank" class="">erik.lindahl@gmail.com</a>><br class="">
> To: "Hal Finkel" <<a href="mailto:hfinkel@anl.gov" target="_blank" class="">hfinkel@anl.gov</a>><br class="">
> Cc:<span class="Apple-converted-space"> </span><a href="mailto:llvm-bgq-discuss@lists.alcf.anl.gov" target="_blank" class="">llvm-bgq-discuss@lists.alcf.anl.gov</a>, "Mark Abraham" <<a href="mailto:mark.j.abraham@gmail.com" target="_blank" class="">mark.j.abraham@gmail.com</a>><br class="">
> Sent: Sunday, May 10, 2015 10:41:26 AM<br class="">
> Subject: Re: [Llvm-bgq-discuss] New bgclang nighty builds (and other updates)<br class="">
><br class="">
><br class="">
> Oops, hit the “send” instead of “attach” button by mistake. Here we<br class="">
> go.<br class="">
><br class="">
><br class="">
> The output with xlc at all optimization levels, and clang at -O0 is<br class="">
> "v: 1 2 3 4”.<br class="">
><br class="">
><br class="">
> With clang and -O3 I get “v: 0.0078125 32 0 0”<br class="">
><br class="">
><br class="">
> Cheers,<br class="">
><br class="">
><br class="">
> E.<br class="">
><br class="">
><br class="">
><br class="">
> From: Erik Lindahl <<a href="mailto:erik.lindahl@gmail.com" target="_blank" class="">erik.lindahl@gmail.com</a>><br class="">
> Reply: Erik Lindahl <<a href="mailto:erik.lindahl@gmail.com" target="_blank" class="">erik.lindahl@gmail.com</a>>><br class="">
> Date: 10 May 2015 at 17:40:02<br class="">
> To: Hal Finkel <<a href="mailto:hfinkel@anl.gov" target="_blank" class="">hfinkel@anl.gov</a>>><br class="">
> Cc: Mark Abraham <<a href="mailto:mark.j.abraham@gmail.com" target="_blank" class="">mark.j.abraham@gmail.com</a>>> ,<br class="">
><span class="Apple-converted-space"> </span><a href="mailto:llvm-bgq-discuss@lists.alcf.anl.gov" target="_blank" class="">llvm-bgq-discuss@lists.alcf.anl.gov</a><br class="">
> <<a href="mailto:llvm-bgq-discuss@lists.alcf.anl.gov" target="_blank" class="">llvm-bgq-discuss@lists.alcf.anl.gov</a>>><br class="">
> Subject: Re: [Llvm-bgq-discuss] New bgclang nighty builds (and other<br class="">
> updates)<br class="">
><br class="">
><br class="">
><br class="">
><br class="">
><br class="">
><br class="">
><br class="">
> Hi Hal,<br class="">
><br class="">
><br class="">
> See attachment!<br class="">
><br class="">
><br class="">
><br class="">
><br class="">
><br class="">
> From: Hal Finkel <<a href="mailto:hfinkel@anl.gov" target="_blank" class="">hfinkel@anl.gov</a>><br class="">
> Reply: Hal Finkel <<a href="mailto:hfinkel@anl.gov" target="_blank" class="">hfinkel@anl.gov</a>>><br class="">
> Date: 10 May 2015 at 17:22:52<br class="">
> To: Erik Lindahl <<a href="mailto:erik.lindahl@gmail.com" target="_blank" class="">erik.lindahl@gmail.com</a>>><br class="">
> Cc:<span class="Apple-converted-space"> </span><a href="mailto:llvm-bgq-discuss@lists.alcf.anl.gov" target="_blank" class="">llvm-bgq-discuss@lists.alcf.anl.gov</a><br class="">
> <<a href="mailto:llvm-bgq-discuss@lists.alcf.anl.gov" target="_blank" class="">llvm-bgq-discuss@lists.alcf.anl.gov</a>>> , Mark Abraham<br class="">
> <<a href="mailto:mark.j.abraham@gmail.com" target="_blank" class="">mark.j.abraham@gmail.com</a>>><br class="">
> Subject: Re: [Llvm-bgq-discuss] New bgclang nighty builds (and other<br class="">
> updates)<br class="">
><br class="">
><br class="">
><br class="">
><br class="">
><br class="">
> Hi Erik,<br class="">
><br class="">
> If you could send this trivial piece of code, that would be greatly<br class="">
> appreciated.<br class="">
><br class="">
> Thanks again,<br class="">
> Hal<br class="">
><br class="">
> ----- Original Message -----<br class="">
> > From: "Erik Lindahl" <<a href="mailto:erik.lindahl@gmail.com" target="_blank" class="">erik.lindahl@gmail.com</a>><br class="">
> > To: "Hal Finkel" <<a href="mailto:hfinkel@anl.gov" target="_blank" class="">hfinkel@anl.gov</a>>, "Mark Abraham"<br class="">
> > <<a href="mailto:mark.j.abraham@gmail.com" target="_blank" class="">mark.j.abraham@gmail.com</a>><br class="">
> > Cc:<span class="Apple-converted-space"> </span><a href="mailto:llvm-bgq-discuss@lists.alcf.anl.gov" target="_blank" class="">llvm-bgq-discuss@lists.alcf.anl.gov</a><br class="">
> > Sent: Sunday, May 10, 2015 9:25:34 AM<br class="">
> > Subject: Re: [Llvm-bgq-discuss] New bgclang nighty builds (and<br class="">
> > other updates)<br class="">
> ><br class="">
> ><br class="">
> > Hi,<br class="">
> ><br class="">
> ><br class="">
> > Super-brief summary:<br class="">
> ><br class="">
> ><br class="">
> > The bug occurs at high optimization (-O3) with the vec_ld() or<br class="">
> > vec_st() functions when calling the (overloaded) version with<br class="">
> > single-precision arguments (i.e., float pointers).<br class="">
> ><br class="">
> ><br class="">
> > This is reproducible even with a trivial piece of code that tries<br class="">
> > to<br class="">
> > load from single precision memory and then write out the contents<br class="">
> > of<br class="">
> > the (double precision) vector4doubles by storing to a double<br class="">
> > variable.<br class="">
> ><br class="">
> ><br class="">
> > - Everything works fine with the double-precision functions,<br class="">
> > regardless of optimization<br class="">
> > - It works fine with clang in single precision without optimization<br class="">
> > - It works fine with xlc.<br class="">
> ><br class="">
> ><br class="">
> > Cheers,<br class="">
> ><br class="">
> ><br class="">
> > Erik<br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> > From: Mark Abraham <<a href="mailto:mark.j.abraham@gmail.com" target="_blank" class="">mark.j.abraham@gmail.com</a>><br class="">
> > Reply: Mark Abraham <<a href="mailto:mark.j.abraham@gmail.com" target="_blank" class="">mark.j.abraham@gmail.com</a>>><br class="">
> > Date: 10 May 2015 at 16:04:51<br class="">
> > To: Hal Finkel <<a href="mailto:hfinkel@anl.gov" target="_blank" class="">hfinkel@anl.gov</a>>><br class="">
> > Cc:<span class="Apple-converted-space"> </span><a href="mailto:llvm-bgq-discuss@lists.alcf.anl.gov" target="_blank" class="">llvm-bgq-discuss@lists.alcf.anl.gov</a><br class="">
> > <<a href="mailto:llvm-bgq-discuss@lists.alcf.anl.gov" target="_blank" class="">llvm-bgq-discuss@lists.alcf.anl.gov</a>>> , Erik Lindahl<br class="">
> > <<a href="mailto:erik.lindahl@gmail.com" target="_blank" class="">erik.lindahl@gmail.com</a>>><br class="">
> > Subject: Re: [Llvm-bgq-discuss] New bgclang nighty builds (and<br class="">
> > other<br class="">
> > updates)<br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> > Hi,<br class="">
> ><br class="">
> > Bump. Erik Lindahl has also observed this on bgclang on JUQUEEN. Is<br class="">
> > it helpful if I produce a small piece of code that reproduces some<br class="">
> > of the issues on bgclang 3.6?<br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> > Mark<br class="">
> ><br class="">
> > On Wed, Mar 25, 2015 at 4:16 PM Mark Abraham <<br class="">
> ><span class="Apple-converted-space"> </span><a href="mailto:mark.j.abraham@gmail.com" target="_blank" class="">mark.j.abraham@gmail.com</a><span class="Apple-converted-space"> </span>> wrote:<br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> > On Tue, Mar 24, 2015 at 7:29 PM, Hal Finkel <<span class="Apple-converted-space"> </span><a href="mailto:hfinkel@anl.gov" target="_blank" class="">hfinkel@anl.gov</a><span class="Apple-converted-space"> </span>><br class="">
> > wrote:<br class="">
> ><br class="">
> ><br class="">
> > ----- Original Message -----<br class="">
> > > From: "Mark Abraham" <<span class="Apple-converted-space"> </span><a href="mailto:mark.j.abraham@gmail.com" target="_blank" class="">mark.j.abraham@gmail.com</a><span class="Apple-converted-space"> </span>><br class="">
> > > To: "Hal Finkel" <<span class="Apple-converted-space"> </span><a href="mailto:hfinkel@anl.gov" target="_blank" class="">hfinkel@anl.gov</a><span class="Apple-converted-space"> </span>><br class="">
> > > Cc:<span class="Apple-converted-space"> </span><a href="mailto:llvm-bgq-discuss@lists.alcf.anl.gov" target="_blank" class="">llvm-bgq-discuss@lists.alcf.anl.gov</a><br class="">
> > > Sent: Tuesday, March 24, 2015 12:35:20 PM<br class="">
> > > Subject: Re: [Llvm-bgq-discuss] New bgclang nighty builds (and<br class="">
> > > other updates)<br class="">
> > ><br class="">
> > ><br class="">
> > > Hi Hal,<br class="">
> > ><br class="">
> > ><br class="">
> > > Thanks very much for the update & effort.<br class="">
> > ><br class="">
> ><br class="">
> > You're very welcome.<br class="">
> ><br class="">
> > ><br class="">
> > > I tried out the default bgclang 3.6.0 on vesta, but found a bunch<br class="">
> > > of<br class="">
> > > the GROMACS SIMD-layer unit tests failing. These need correct QPX<br class="">
> > > vector intrinsics available. From memory, things worked fine with<br class="">
> > > bgclang in ~August last year, but I no longer have those results.<br class="">
> > > Is<br class="">
> > > there a simple way I can compile on vesta with older bgclang to<br class="">
> > > see<br class="">
> > > where a problem might lie? Otherwise / depending what I learn,<br class="">
> > > I'll<br class="">
> > > break out a debugger.<br class="">
> ><br class="">
> > The old builds are still all installed. Just use the MPI wrappers<br class="">
> > from:<br class="">
> ><br class="">
> > /home/projects/llvm/<whatever>/mpi/bgclang/bin -- I don't know<br class="">
> > exactly which build you were using in August of last year,<br class="">
> > r209570-20140527 maybe?<br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> > Yes, that was it, looking at some cruft in my former build script.<br class="">
> > In<br class="">
> > any case, the latest GROMACS SIMD single-precision unit tests pass<br class="">
> > on that old compiler version (3.5.0), and many of them fail in a<br class="">
> > release build on the default 3.6.0 bgclang on vesta. For some of<br class="">
> > the<br class="">
> > cases, it looks like some junk memory gets loaded, somehow. A few<br class="">
> > tests pass, but no theme for passing or failing tests leaps out at<br class="">
> > me. Double precision unit tests are OK, though.<br class="">
> ><br class="">
> ><br class="">
> > Naturally, in debug mode most of the tests pass. However, the two I<br class="">
> > looked at in ddt were fine up until they called vec_extract(x, 0)<br class="">
> > e.g. on lines<br class="">
> ><span class="Apple-converted-space"> </span><a href="https://github.com/gromacs/gromacs/blob/master/src/gromacs/simd/impl_ibm_qpx/impl_ibm_qpx.h#L315" target="_blank" class="">https://github.com/gromacs/gromacs/blob/master/src/gromacs/simd/impl_ibm_qpx/impl_ibm_qpx.h#L315</a><br class="">
> > (where a SIMD vector of 1 2 3 1 was summed to 3, rather than 7) and<br class="">
> ><span class="Apple-converted-space"> </span><a href="https://github.com/gromacs/gromacs/blob/master/src/gromacs/simd/impl_ibm_qpx/impl_ibm_qpx.h#L462" target="_blank" class="">https://github.com/gromacs/gromacs/blob/master/src/gromacs/simd/impl_ibm_qpx/impl_ibm_qpx.h#L462</a><br class="">
> > (where a SIMD vector dot product of the first 3 lanes returns a<br class="">
> > garbage answer). So maybe that is a productive lead?<br class="">
> ><br class="">
> ><br class="">
> > I couldn't inspect the disassembly in ddt, so I'm not sure where we<br class="">
> > can take this from here, Hal. Tarball of test results attached.<br class="">
> ><br class="">
> ><br class="">
> > Thanks,<br class="">
> ><br class="">
> ><br class="">
> > Mark<br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> > -Hal<br class="">
> ><br class="">
> ><br class="">
> ><br class="">
> > ><br class="">
> > ><br class="">
> > > Thanks,<br class="">
> > ><br class="">
> > ><br class="">
> > > Mark<br class="">
> > ><br class="">
> > ><br class="">
> > ><br class="">
> > ><br class="">
> > > On Fri, Mar 20, 2015 at 12:15 AM, Hal Finkel <<span class="Apple-converted-space"> </span><a href="mailto:hfinkel@anl.gov" target="_blank" class="">hfinkel@anl.gov</a><span class="Apple-converted-space"> </span>><br class="">
> > > wrote:<br class="">
> > ><br class="">
> > ><br class="">
> > > Hello everyone,<br class="">
> > ><br class="">
> > > First, let me apologize to everyone, this is a few months late...<br class="">
> > > but, hopefully, this will never be a problem again...<br class="">
> > ><br class="">
> > > I now have a system setup which automatically pulls in upstream<br class="">
> > > changes and tries to merge those with the bgclang-specific<br class="">
> > > patches,<br class="">
> > > and then builds the resulting suite of bgclang RPMs. When this<br class="">
> > > succeeds, the RPMs should be posted automatically to:<br class="">
> > ><br class="">
> > ><span class="Apple-converted-space"> </span><a href="http://www.mcs.anl.gov/~hfinkel/bgclang/" target="_blank" class="">http://www.mcs.anl.gov/~hfinkel/bgclang/</a><br class="">
> > > (note that installing a build from here now also requires both<br class="">
> > > the<br class="">
> > > 'stage1' and 'stage2' RPMs as well)<br class="">
> > ><br class="">
> > > The first such nightly build, r232720-20150319, has been posted<br class="">
> > > to<br class="">
> > > that page.<br class="">
> > ><br class="">
> > > And, for the curious, the local repositories used for version<br class="">
> > > control<br class="">
> > > are now mirrored to github:<br class="">
> > ><br class="">
> > ><span class="Apple-converted-space"> </span><a href="https://github.com/hfinkel/clang-bgq" target="_blank" class="">https://github.com/hfinkel/clang-bgq</a><br class="">
> > ><span class="Apple-converted-space"> </span><a href="https://github.com/hfinkel/llvm-bgq" target="_blank" class="">https://github.com/hfinkel/llvm-bgq</a><br class="">
> > ><span class="Apple-converted-space"> </span><a href="https://github.com/hfinkel/bgclang-aux" target="_blank" class="">https://github.com/hfinkel/bgclang-aux</a><br class="">
> > ><span class="Apple-converted-space"> </span><a href="https://github.com/hfinkel/compiler-rt-bgq" target="_blank" class="">https://github.com/hfinkel/compiler-rt-bgq</a><br class="">
> > ><span class="Apple-converted-space"> </span><a href="https://github.com/hfinkel/libcxx-bgq" target="_blank" class="">https://github.com/hfinkel/libcxx-bgq</a><br class="">
> > ><span class="Apple-converted-space"> </span><a href="https://github.com/hfinkel/openmp-bgq" target="_blank" class="">https://github.com/hfinkel/openmp-bgq</a><br class="">
> > ><span class="Apple-converted-space"> </span><a href="https://github.com/hfinkel/sleef-bgq" target="_blank" class="">https://github.com/hfinkel/sleef-bgq</a><br class="">
> > ><br class="">
> > > Compared to the latest "released" version (r220548-20141024), the<br class="">
> > > most-recent nightly build does show some performance regressions,<br class="">
> > > and there are a few things I've not even tested yet (LTO, ASan,<br class="">
> > > etc.), but it also contains a number of bug fixes and<br class="">
> > > improvements,<br class="">
> > > so feel free to test on your applications.<br class="">
> > ><br class="">
> > > One particular noteworthy improvement is that our OpenMP runtime<br class="">
> > > library now has affinity support enabled. This means that all of<br class="">
> > > the<br class="">
> > > OpenMP 4 affinity features should work, and also that the default<br class="">
> > > thread<->core bindings are now sensible.<br class="">
> > ><br class="">
> > > The bgclang wrapper script no longer disables 'fast-isel'<br class="">
> > > instruction<br class="">
> > > selection at -O0, so your debug builds should now be faster too.<br class="">
> > > Also, the automated vectorization of math functions using our<br class="">
> > > SLEEF<br class="">
> > > library adaptation is controlled using the new -fveclib flag (so<br class="">
> > > the<br class="">
> > > wrapper script contains -fveclib=SLEEF, and you can add<br class="">
> > > -fveclib=none to turn it off if desired for whatever reason).<br class="">
> > ><br class="">
> > > Also, the core QPX support has been contributed upstream<br class="">
> > > (although<br class="">
> > > not yet the Clang-level intrinsics support); so if you're using<br class="">
> > > LLVM<br class="">
> > > as a library, and want to just build from upstream sources<br class="">
> > > instead<br class="">
> > > of depending on the bgclang builds, that is now possible.<br class="">
> > ><br class="">
> > > Thanks again everyone, and please let me know if you experience<br class="">
> > > any<br class="">
> > > difficulties,<br class="">
> > > Hal<br class="">
> > ><br class="">
> > > --<br class="">
> > > Hal Finkel<br class="">
> > > Assistant Computational Scientist<br class="">
> > > Leadership Computing Facility<br class="">
> > > Argonne National Laboratory<br class="">
> > > _______________________________________________<br class="">
> > > llvm-bgq-discuss mailing list<br class="">
> > ><span class="Apple-converted-space"> </span><a href="mailto:llvm-bgq-discuss@lists.alcf.anl.gov" target="_blank" class="">llvm-bgq-discuss@lists.alcf.anl.gov</a><br class="">
> > ><span class="Apple-converted-space"> </span><a href="https://lists.alcf.anl.gov/mailman/listinfo/llvm-bgq-discuss" target="_blank" class="">https://lists.alcf.anl.gov/mailman/listinfo/llvm-bgq-discuss</a><br class="">
> > ><br class="">
> > ><br class="">
> ><br class="">
> > --<br class="">
> > Hal Finkel<br class="">
> > Assistant Computational Scientist<br class="">
> > Leadership Computing Facility<br class="">
> > Argonne National Laboratory<br class="">
> ><br class="">
> ><br class="">
> > --<br class="">
> > Erik Lindahl <<span class="Apple-converted-space"> </span><a href="mailto:erik.lindahl@gmail.com" target="_blank" class="">erik.lindahl@gmail.com</a><span class="Apple-converted-space"> </span>><br class="">
> > Professor of Biophysics, Dept. Biochemistry & Biophysics, Stockholm<br class="">
> > University<br class="">
> > Professor of Theoretical biophysics, Dept. Theoretical Physics,<br class="">
> > Royal<br class="">
> > Inst. Technology<br class="">
> > Science for Life Laboratory, Box 1031, 17121 Solna, Sweden<br class="">
><br class="">
> --<br class="">
> Hal Finkel<br class="">
> Assistant Computational Scientist<br class="">
> Leadership Computing Facility<br class="">
> Argonne National Laboratory<br class="">
><br class="">
><br class="">
> --<br class="">
> Erik Lindahl <<span class="Apple-converted-space"> </span><a href="mailto:erik.lindahl@gmail.com" target="_blank" class="">erik.lindahl@gmail.com</a><span class="Apple-converted-space"> </span>><br class="">
> Professor of Biophysics, Dept. Biochemistry & Biophysics, Stockholm<br class="">
> University<br class="">
> Professor of Theoretical biophysics, Dept. Theoretical Physics, Royal<br class="">
> Inst. Technology<br class="">
> Science for Life Laboratory, Box 1031, 17121 Solna, Sweden<br class="">
><br class="">
> --<br class="">
> Erik Lindahl <<span class="Apple-converted-space"> </span><a href="mailto:erik.lindahl@gmail.com" target="_blank" class="">erik.lindahl@gmail.com</a><span class="Apple-converted-space"> </span>><br class="">
> Professor of Biophysics, Dept. Biochemistry & Biophysics, Stockholm<br class="">
> University<br class="">
> Professor of Theoretical biophysics, Dept. Theoretical Physics, Royal<br class="">
> Inst. Technology<br class="">
> Science for Life Laboratory, Box 1031, 17121 Solna, Sweden<br class="">
<br class="">
--<br class="">
Hal Finkel<br class="">
Assistant Computational Scientist<br class="">
Leadership Computing Facility<br class="">
Argonne National Laboratory<br class="">
</blockquote>
</div>
<span style="font-family: Helvetica; font-size: 12px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px; float: none; display: inline !important;" class="">_______________________________________________</span><br style="font-family: Helvetica; font-size: 12px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px;" class="">
<span style="font-family: Helvetica; font-size: 12px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px; float: none; display: inline !important;" class="">llvm-bgq-discuss
mailing list</span><br style="font-family: Helvetica; font-size: 12px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px;" class="">
<a href="mailto:llvm-bgq-discuss@lists.alcf.anl.gov" style="font-family: Helvetica; font-size: 12px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px;" class="">llvm-bgq-discuss@lists.alcf.anl.gov</a><br style="font-family: Helvetica; font-size: 12px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px;" class="">
<a href="https://lists.alcf.anl.gov/mailman/listinfo/llvm-bgq-discuss" style="font-family: Helvetica; font-size: 12px; font-style: normal; font-variant: normal; font-weight: normal; letter-spacing: normal; line-height: normal; orphans: auto; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: auto; word-spacing: 0px; -webkit-text-stroke-width: 0px;" class="">https://lists.alcf.anl.gov/mailman/listinfo/llvm-bgq-discuss</a></div>
</blockquote>
</div>
<br class="">
</div>
<br>
<font face="Arial" color="Black" size="1"><br>
------------------------------------------------------------------------------------------------<br>
------------------------------------------------------------------------------------------------<br>
Forschungszentrum Juelich GmbH<br>
52425 Juelich<br>
Sitz der Gesellschaft: Juelich<br>
Eingetragen im Handelsregister des Amtsgerichts Dueren Nr. HR B 3498<br>
Vorsitzender des Aufsichtsrats: MinDir Dr. Karl Eugen Huthmacher<br>
Geschaeftsfuehrung: Prof. Dr.-Ing. Wolfgang Marquardt (Vorsitzender),<br>
Karsten Beneke (stellv. Vorsitzender), Prof. Dr.-Ing. Harald Bolt,<br>
Prof. Dr. Sebastian M. Schmidt<br>
------------------------------------------------------------------------------------------------<br>
------------------------------------------------------------------------------------------------<br>
<br>
</font>
</body>
</html>