[petsc-dev] Valgrind MPI-Related Errors

[Jacob Faibussowitsch]

Sorry for late reply.

> I'd welcome a PR to add options like --enable-g=meminit.
In docker? Or in petsc? According to Satish petsc’s —download-mpich already does this by default.

>  I'd rather not make that general-purpose image use ch3:sock
Which image are you referring to? The image I use is jedbrown/mpich-ccache which does ship MPICH configured with ch3:sock (see below). 

MPICH Version:    	3.3.2
MPICH Release date:	Tue Nov 12 21:23:16 CST 2019
MPICH Device:    	ch3:sock
MPICH configure: 	--disable-wrapper-rpath --with-device=ch3:sock
MPICH CC: 	gcc    -O2
MPICH CXX: 	g++   -O2
MPICH F77: 	gfortran   -O2
MPICH FC: 	gfortran   -O2
MPICH Custom Information: 	


Best regards,

Jacob Faibussowitsch
(Jacob Fai - booss - oh - vitch)
Cell: (312) 694-3391

> On Jun 2, 2020, at 3:07 PM, Jed Brown <jed at jedbrown.org> wrote:
> 
> Jacob Faibussowitsch <jacob.fai at gmail.com> writes:
> 
>> 2. (More a question for Jed) If I am using Jeds docker image anyways and we have CI/CD builds also using his docker images (correct me if I am wrong here) and a valgrind build in stage 3 why not include those build arguments in the MPICH included in the images? I think the valgrind build for CI/CD actually downloads and builds MPICH through petsc configure, is this because of the errors I detailed below?
> 
> I'd welcome a PR to add options like --enable-g=meminit.  I'd rather not
> make that general-purpose image use ch3:sock because people also use it
> (via Singularity or Shifter) for performance.  We could make a different
> Docker image with ch3:sock.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.mcs.anl.gov/pipermail/petsc-dev/attachments/20200605/fed4ae26/attachment.html>