Skip to Content.
Sympa Menu

charm - Re: [charm] Question about Charm++ Compilation Using UCX + OpenMPI with PMIx

charm AT lists.cs.illinois.edu

Subject: Charm++ parallel programming system

List archive

Re: [charm] Question about Charm++ Compilation Using UCX + OpenMPI with PMIx


Chronological Thread 
  • From: Matthias Diener <mdiener AT illinois.edu>
  • To: "#LI MENGYANG#" <LIME0040 AT e.ntu.edu.sg>
  • Cc: "charm AT cs.illinois.edu" <charm AT cs.illinois.edu>
  • Subject: Re: [charm] Question about Charm++ Compilation Using UCX + OpenMPI with PMIx
  • Date: Thu, 8 Oct 2020 15:15:17 -0500
  • Arc-authentication-results: i=1; mx.microsoft.com 1; spf=pass smtp.mailfrom=illinois.edu; dmarc=pass action=none header.from=illinois.edu; dkim=pass header.d=illinois.edu; arc=none
  • Arc-message-signature: i=1; a=rsa-sha256; c=relaxed/relaxed; d=microsoft.com; s=arcselector9901; h=From:Date:Subject:Message-ID:Content-Type:MIME-Version:X-MS-Exchange-SenderADCheck; bh=7OPutUmfrPV0ovqtZIIAsfsAjAwczZKgnbv44ANEcEg=; b=Vx49/Ciq0odVCPOjYsRPQSkoLGIs2p8lTDVh3RPPzEd0/hrTbYxwJuaGw0tnLWEnnPwq4BqGeyuYtsEqRIuuFe3VMiHCcwsHQijn4BAcOHRltzPObsDLiqmSdEEPaVcbl3u2BvmZ23yILyKMJBzK9/LIe6kRw5XZzjGTa6KNQ49fb9iXZOREzdoWiyY2jTbi48SN9f2MkE5G+3OnTJcf4BMNyx8ZV9dVMLNpzdBChII5SPPC7YJsYE+e5wiyWPnbyQ+B0WTB0JQ+ZARWleRnpyX/Lu4bCV9qM9iXsmvo8FtfW5Z7qP3isCdaYwptQyTnWzp/3qNWiW3hhxFKI8AKdA==
  • Arc-seal: i=1; a=rsa-sha256; s=arcselector9901; d=microsoft.com; cv=none; b=IghHQZc85WGgsJJd+loh6OtmLSJ7MPUO5cucJ/qDELoMgLkwQo1q5RRcoABnQZKhzrzsCEcW6qIC7tXMdcr/wPWh47wTTtW/KveXxqKXkmVyKKJ1TujjC5ERuCsiDPWRkn+VPzFUFK+NPw+n2MsGuEDqaXa0PjgrY1KJMksuz5f5URLy1hRItRHJ7loHoGb5uoWuPUGpH51uRQIYcJCLjsVSXSnMUZSX/Vm1uj0L1HnY+kS07uHUw9vVybaHZMtOC9xt+5nQ8YdR/Sn4O+CtmiGylaYW58bt30d/KHsw6r0OfsGj8MP3iye1emKwsdZm4Dpcyl1jrkEb4pXJZ83tOA==
  • Authentication-results: illinois.edu; spf=neutral smtp.mailfrom=mdiener AT illinois.edu; dmarc=none header.from=illinois.edu
  • Authentication-results: cs.illinois.edu; dkim=none (message not signed) header.d=none;cs.illinois.edu; dmarc=none action=none header.from=illinois.edu;

[resending since I had not sent my response to Li Mengyang directly]

Hello,

Could you please post the full Charm++ build output? It is possible
that there is another error earlier in the compilation.

Also, we have seen some recent issues with OpenMPI 4.0.5 and UCX (in
particular, --enable-install-libpmix might not work anymore). Could
you please try to use OpenMPI 4.0.4?

Best,
Matthias

On Fri, Oct 2, 2020 at 7:22 AM #LI MENGYANG#
<LIME0040 AT e.ntu.edu.sg>
wrote:
>
> Dear Sir/Madam,
>
> I am a student at Nanyang Technological University, and I am using Charm++
> for the APAC-HPCAI competition. I currently encountered a problem during
> the compilation for charm++. It will be sincerely appreciated if you could
> help me about this compilation issue.
>
> I followed the link here
> (https://charm.readthedocs.io/en/latest/charm++/manual.html#ucx)
>
> Build UCX
>
> $ wget
> https://github.com/openucx/ucx/releases/download/v1.9.0/ucx-1.9.0.tar.gz
>
> $ tar -xvf ucx-1.9.0.tar.gz
>
> $ cd ucx-1.9.0
>
> $ ./contrib/configure-release --prefix=~/ucx-1.9.0/build
>
> $ make -j24
>
> $ make install all
>
>
> 2. Build OpenMPI
>
> $ wget
> https://download.open-mpi.org/release/open-mpi/v4.0/openmpi-4.0.5.tar.gz
>
> $ tar -xvf openmpi-4.0.5.tar.gz
>
> $ cd openmpi-4.0.5
>
> $ ./configure --enable-install-libpmix --prefix=~/openmpi-4.0.5/build
>
> $ make -j24
>
> $ make install all
>
>
> 3. Build Charm++
>
> $ git clone https://github.com/UIUC-PPL/charm charm-6.10.2
>
> $ cd charm-6.10.2 && git checkout charm-6.10.2
>
> $ ./build charm++ ucx-linux-x86_64 ompipmix --with-production
> --basedir=~/ucx-1.9.0/build --basedir=~/openmpi-4.0.5/build
>
>
> While I was building Charm++, I encountered the problem below that
> prevents the build process to succeed
>
> ../bin/charmc -optimize -production -o ../lib/libconv-core.a convcore.o
> hrctimer.o conv-conds.o conv-taskQ.o queueing.o msgmgr.o cpm.o cpthreads.o
> futures.o cldb.o random.o debug-conv.o debug-conv++.o conv-ccs.o
> ccs-builtins.o middle-ccs.o traceCore.o traceCoreCommon.o
> converseProjections.o machineProjections.o quiescence.o isomalloc.o
> mem-arena.o memory-darwin-clang.o global-nop.o cmipool.o cpuaffinity.o
> cputopology.o cmitls.o memoryaffinity.o commitid.o conv-interoperate.o
> conv-rdma.o conv-rdmadevice.o
>
> ar: creating ../lib/libconv-core.a
>
> ../bin/charmc -optimize -production -I. -c -o conv-static.o
> conv-static.c
>
> cp -f conv-static.o ../lib/conv-static.o
>
> gmake: *** No rule to make target `machine.d', needed by `machine.o'. Stop.
>
> I used GCC/5.1.0 as the compiler, and I am not very sure where does the
> machine.d file comes from.
>
> Looking forward to hearing from you soon!
>
> Sincerely,
> Li Mengyang
>
>



Archive powered by MHonArc 2.6.19.

Top of Page