<html><head><meta http-equiv="Content-Type" content="text/html; charset=us-ascii"></head><body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class=""><div class=""><br class=""></div> Toby,<div class=""><br class=""></div><div class=""> It was never our intention that MPIUNI support any other packages besides PETSc/SLEPc as an "mpi substitute". There are just so many fragile aspects to it. I think it is is best if p4est maintains its own non-MPI version (if it wants to have such as thing) and does not have it involve MPIUNI.</div><div class=""><br class=""></div><div class=""> Barry</div><div class=""><br class=""></div><div class=""><br class=""><div><br class=""><blockquote type="cite" class=""><div class="">On Apr 16, 2021, at 12:53 PM, Isaac, Tobin G <<a href="mailto:tisaac@cc.gatech.edu" class="">tisaac@cc.gatech.edu</a>> wrote:</div><br class="Apple-interchange-newline"><div class="">
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii" class="">
<div class="">
<div dir="auto" style="direction: ltr; margin: 0px; padding: 0px; font-family: sans-serif; font-size: 11pt;" class="">
Hmm. So if petsc always compiles mpiuni if --with-mpi=0, then it makes me think it should be possible to drop requires(MPI) from p4est, while still passing `--enable-mpi` to p4est.<br class="">
<br class="">
</div>
<div dir="auto" style="direction: ltr; margin: 0px; padding: 0px; font-family: sans-serif; font-size: 11pt;" class="">
<span id="ms-outlook-android-cursor" class=""></span>Maybe: if mpiuni doesn't provide some esoteric part of MPI that p4est uses, it will break.<br class="">
<br class="">
</div>
<div dir="auto" style="direction: ltr; margin: 0px; padding: 0px; font-family: sans-serif; font-size: 11pt;" class="">
<span id="OutlookSignature" class="">
<div dir="auto" style="direction: ltr; margin: 0px; padding: 0px; font-family: sans-serif; font-size: 11pt;" class="">
Toby Isaac, Assistant Professor, GTCSE</div>
</span><br class="">
</div>
<hr style="display:inline-block;width:98%" tabindex="-1" class="">
<div id="divRplyFwdMsg" dir="ltr" class=""><font face="Calibri, sans-serif" style="font-size:11pt" class=""><b class="">From:</b> Satish Balay <<a href="mailto:balay@mcs.anl.gov" class="">balay@mcs.anl.gov</a>><br class="">
<b class="">Sent:</b> Friday, April 16, 2021 1:03:55 PM<br class="">
<b class="">To:</b> Isaac, Tobin G <<a href="mailto:tisaac@cc.gatech.edu" class="">tisaac@cc.gatech.edu</a>><br class="">
<b class="">Cc:</b> petsc-dev <<a href="mailto:petsc-dev@mcs.anl.gov" class="">petsc-dev@mcs.anl.gov</a>><br class="">
<b class="">Subject:</b> Re: [petsc-dev] p4est w/o MPI</font>
<div class=""> </div>
</div>
<div class="BodyFragment"><font size="2" class=""><span style="font-size:11pt;" class="">
<div class="PlainText">Thanks! Another issue:<br class="">
<br class="">
mpiuni provides mpi.h. And I get the following errors when building PETSc.<br class="">
<br class="">
/home/balay/petsc/arch-linux-c-debug/include/sc.h:87:2: error: #error "mpi.h is included. Use --enable-mpi."<br class="">
87 | #error "mpi.h is included. Use --enable-mpi."<br class="">
| ^~~~~<br class="">
<br class="">
etc..<br class="">
<br class="">
Satish<br class="">
<br class="">
<br class="">
On Fri, 16 Apr 2021, Isaac, Tobin G wrote:<br class="">
<br class="">
> Yes, `--disable-mpi` should be accepted by p4est.<br class="">
> <br class="">
> ________________________________________<br class="">
> From: Satish Balay <<a href="mailto:balay@mcs.anl.gov" class="">balay@mcs.anl.gov</a>><br class="">
> Sent: Friday, April 16, 2021 11:47<br class="">
> To: Satish Balay via petsc-dev<br class="">
> Cc: Isaac, Tobin G<br class="">
> Subject: Re: [petsc-dev] p4est w/o MPI<br class="">
> <br class="">
> BTW: Is there no --disable-mpi option?<br class="">
> <br class="">
> Satish<br class="">
> <br class="">
> On Fri, 16 Apr 2021, Satish Balay via petsc-dev wrote:<br class="">
> <br class="">
> > MPI pacakge is a bit weird compared to others [as it does this funny thing with MPIUNI].<br class="">
> ><br class="">
> > For regular packages - I guess I would use 'if package.found'<br class="">
> ><br class="">
> > I guess I should create an MR with this diff.<br class="">
> ><br class="">
> > Satish<br class="">
> ><br class="">
> > ----<br class="">
> ><br class="">
> > diff --git a/config/BuildSystem/config/packages/p4est.py b/config/BuildSystem/config/packages/p4est.py<br class="">
> > index e7108b0ab8..40d6797f02 100644<br class="">
> > --- a/config/BuildSystem/config/packages/p4est.py<br class="">
> > +++ b/config/BuildSystem/config/packages/p4est.py<br class="">
> > @@ -24,14 +24,16 @@ class Configure(config.package.GNUPackage):<br class="">
> > self.blasLapack = framework.require('config.packages.BlasLapack',self)<br class="">
> > self.zlib = framework.require('config.packages.zlib',self)<br class="">
> > self.memalign = framework.argDB['with-memalign']<br class="">
> > - self.deps = [self.mpi,self.blasLapack,self.zlib]<br class="">
> > + self.deps = [self.blasLapack,self.zlib]<br class="">
> > + self.odeps = [self.mpi]<br class="">
> > return<br class="">
> ><br class="">
> > def formGNUConfigureArgs(self):<br class="">
> > args = config.package.GNUPackage.formGNUConfigureArgs(self)<br class="">
> > if self.argDB['with-p4est-debugging']:<br class="">
> > args.append('--enable-debug')<br class="">
> > - args.append('--enable-mpi')<br class="">
> > + if not self.mpi.usingMPIUni:<br class="">
> > + args.append('--enable-mpi')<br class="">
> > args.append('CPPFLAGS="'+self.headers.toStringNoDupes(self.dinclude)+'"')<br class="">
> > args.append('LIBS="'+self.libraries.toString(self.dlib)+'"')<br class="">
> > args.append('--enable-memalign='+self.memalign)<br class="">
> ><br class="">
> > On Fri, 16 Apr 2021, Isaac, Tobin G wrote:<br class="">
> ><br class="">
> > > Matt, this is the configure logic I would like, but I don't know how to do it:<br class="">
> > > - configure p4est after MPI, but do not require MPI<br class="">
> > > - if MPI is present, add the '--enable-mpi' flack in formGNUConfigureArgs(), otherwise omit it.<br class="">
> > ><br class="">
> > > ________________________________________<br class="">
> > > From: Isaac, Tobin G <<a href="mailto:tisaac@cc.gatech.edu" class="">tisaac@cc.gatech.edu</a>><br class="">
> > > Sent: Friday, April 16, 2021 11:03<br class="">
> > > To: Mark Adams; For users of the development version of PETSc<br class="">
> > > Subject: Re: [petsc-dev] p4est w/o MPI<br class="">
> > ><br class="">
> > > p4est has a mode where it can compile without MPI, I don't know if PETSc is using it, will check.<br class="">
> > ><br class="">
> > > ________________________________________<br class="">
> > > From: petsc-dev <<a href="mailto:petsc-dev-bounces@mcs.anl.gov" class="">petsc-dev-bounces@mcs.anl.gov</a>> on behalf of Mark Adams <<a href="mailto:mfadams@lbl.gov" class="">mfadams@lbl.gov</a>><br class="">
> > > Sent: Friday, April 16, 2021 10:23<br class="">
> > > To: For users of the development version of PETSc<br class="">
> > > Subject: [petsc-dev] p4est w/o MPI<br class="">
> > ><br class="">
> > > I don't have MPI (Fugaku w/ gcc) and p4est seems to need it. Is there a work around?<br class="">
> > > Thanks,<br class="">
> > > Mark<br class="">
> > ><br class="">
> ><br class="">
> <br class="">
<br class="">
</div>
</span></font></div>
</div>
</div></blockquote></div><br class=""></div></body></html>