Added support for Parastation MPICH toolchains with Intel compilers #1072
Conversation
|
Automatic reply from Jenkins: Can I test this? |
| Intel Math Kernel Library (MKL) and Intel FFTW wrappers. | ||
| """ | ||
| NAME = 'intel-para' | ||
| BLACS_LIB = ["mkl_blacs_intelmpi%(lp64)s"] |
There was a problem hiding this comment.
maybe add a comment here why you're overriding what is being set by IntelMKL?
is this a fix specific to Parastation?
also: you're including the 'generic' MPICH component here, yet naming the toolchain specifically for Parastation.
Maybe here we should be using:
class Impmkl(IntelIccIfort, Mpich, IntelMKL, IntelFFTW):
NAME = 'impmkl'
BLACS_LIB = [...]and then on your end:
class IntelPara(Impmkl):
NAME = 'intel-para'I'm OK with including the 'empty' intel-para toolchain definition in the framework as well if that makes things easier for you
There was a problem hiding this comment.
I'm not sure if the blacs fix is specific to Parastation or not. Perhaps it's best to put it in the empty toolchain
|
Jenkins: ok to test |
|
Test PASSed. |
|
I've updated things so that generic patterns are created first and then wrapped with ParaStation specific extras. |
|
Test PASSed. |
2 similar comments
|
Test PASSed. |
|
Test PASSed. |
|
@ocaisa: as far as I can tell, there are no easyconfigs yet for |
| """ | ||
| NAME = 'intel-para' | ||
| # Parastation MPI needs to be matched with the IntelMPI blacs library | ||
| BLACS_LIB = ["mkl_blacs_intelmpi%(lp64)s"] |
There was a problem hiding this comment.
@ocaisa: as discussed, this should be fixed in toolchains/linalg/intelmkl.py instead, since the MPICH2 value is now also wrong?
… and MPICH2 and corrected toolchain to match
|
Note https://software.intel.com/en-us/articles/intel-mkl-link-line-advisor to help figure out BLACS library for mpi implementation |
|
Test FAILed. |
Simple support for Parastation MPICH with intel compilers