KAUST Supercomputing Laboratory Newsletter 6th January 2016

XSEDE HPC Workshop: OpenMP

The registration page for the XSEDE HPC Monthly Workshop Series - January 20th - OpenMP session is up.
The portal registration page can be found here:

https://portal.xsede.org/course-calendar/-/training-user/class/454/sessi...

If there is enough interest, KSL will investigate the possibility of streaming this course live in the Library computer room on the 20th of January.

February 4 - KSL Workshop Series:  Optimizing I/O on Shaheen II  

KAUST Supercomputing Laboratory (KSL) invites you to the second Shaheen II Seminar Series on maximizing efficient use of the parallel file system.  It will provide an overview of Parallel I/O, explore using various profiling tools for validating I/O performance, and cover best practices for efficient I/O operations.  The focus will be on scientific codes for climate, seismic, and biology applications. 
 
This seminar is for all Shaheen II users dealing with large files, or a large number of files.
Seats are limited. Please register your interest at: https://www.surveymonkey.com/r/H6FNM7C
 
Venue/Time: Computer Lab Room, 3rd floor at the Library, from 9:30am-11:00am
 
Agenda:
        09:30am - Optimizing I/O on Shaheen II
        10:00am - Interactive Exercises on Shaheen II
        10:30am - Q&A with KSL team (bring all your HPC questions)
 

Neser Last Day of Service

Please note this system has now been decommissioned.

Shaheen I/ Neser Data

We will continue to have the Shaheen I/Neser ‘home' and ‘project' filesystems available until at least 31st July 2016. However, please note that the ‘scratch' filesystem will be taken off-line and deleted on the 1st February 2016.

For data that is needed for projects on Shaheen II, rather than copying it yourself, please contact us and we can assist in moving the data as we have dedicated systems for this that have direct access to both storage subsystems.

Maintenance Session 12th January 2016

The next maintenance session on Shaheen II will be on Tuesday 12th January from 09:00 until 17:00.

RCAC Meeting

The deadline for project submission for the next RCAC meeting is 31st January 2016. Please note that RCAC meeting are held every month.

New limit for one node jobs on Shaheen II

It has been observed that a few users were submitting thousands of one node jobs using scripts, which overwhelmed the scheduler. To allow jobs of various sizes to run efficiently on Shaheen II, the limit of 800 one node jobs per user has been put in place.

Tip of the Week: Which library are you using ?

When your code is linked with different libraries,  you can retrieve the path library of a given routine by using the -Wl ,-y option.
For example:

with Cray and linking a code with Libsci, here is the output:

ftn -o test test_scalapack.f90 -Wl,-ydgemm_
/opt/cray/libsci/13.2.0/CRAY/8.3/x86_64/lib/libsci_cray_mpi_mp.a(PB_Cdtypeset.o): reference to dgemm_
/opt/cray/libsci/13.2.0/CRAY/8.3/x86_64/lib/libsci_cray_mp.a(dgemm_.o): definition of dgemm_

with Intel and MKL ( after unloading libsci)

ftn -o exe_dgemm_mkl timing_dgemm.f90 -Wl,--start-group ${MKLROOT}/lib/intel64/libmkl_intel_lp64.a ${MKLROOT}/lib/intel64/libmkl_core.a ${MKLROOT}/lib/intel64/libmkl_sequential.a -Wl,--end-group -lpthread -lm -Wl,-ydgemm_
/tmp/ifortu3oFZN.o: reference to dgemm_
/opt/intel/composer_xe_2015.2.164/mkl/lib/intel64/libmkl_intel_lp64.a(_dgemm_lp64.o): definition of dgemm_

Follow us on Twitter

Follow all the latest news on HPC within the Supercomputing Lab and at KAUST, on Twitter @KAUST_HPC.

Previous Announcements

Previous Tips