Outage to Migrate File Systems to New Hardware -- December 4, starting at 8 am
Posted: November 25, 2013
Duration: All day, starting at 8am
On December 4, 2013, starting at 8am we will be doing the final migration of the file systems listed below from off the CHPCFS hardware that is being retired. In addition, we will be moving the ASTROFS file system to new hardware. While this move will not impact all of CHPC users, it is CRITICAL that each user determine if they will be impacted and prepare accordingly.
To check which file system your home directory is in, while in your home directory, do a “finger UNID”
- if your directory starts with “/uufs/astro.utah.edu” you are in ASTRO_HOME and will be affected
- If your directory has “sdss_home” in its path you will be affected
- If your directory starts with “/uufs/chpc.utah.edu” then do a “df | grep UNID” and if you see one of the file systems listed below you will be affected
If you will be impacted, please be sure to prepare for this outage before 8am on December 4 by:
- Logging off of the interactive nodes AND any desktops that mounts any of these file systems
- Do not have jobs running/queued as any job that starts or stops during this time will be affected
We expect to have all file systems listed below with the exception of CHPC_HPC available in their new location by around noon. CHPC_HPC will be unavailable most if not all of the day. An “all clear” message will be sent to users when the file systems become available.
Home directories on the following file systems will be migrated:
The following group spaces will be migrated:
If you have any questions, please contact us at issues.
Reminder - MPI workshop registration ends on Friday
Posted: November 20, 2013
The registration for the MPI workshop that will take place December 4-5 ends this Friday (11/22), due to time needed to create the attendees accounts and the upcoming Thanksgiving holiday.
If you are planning to attend this workshop and haven't registered yet, please, do so in the next few days. We are willing to accommodate those who did not get time to register on a walk in basis but in this case you will not get an account on the machine where the hands on assignments will be done.
To register, choose the University of Utah as a site on the XSEDE Portal Registration pages:
Please visit the workshop page for more information:
XSEDE HPC Workshop at the CHPC - December 4,5 2013 - MPI
Posted: November 11, 2013
CHPC will be a satellite site for next month's XSEDE HPC two-day workshop covering MPI. The workshop is run by Pittsburgh Supercomputing Center and the Texas Advanced Computing Center and CHPC will provide interactive telecast.
This workshop is intended to give C and Fortran programmers a hands-on introduction to MPI programming. Both days are compact, to accommodate multiple time zones, but packed with useful information and lab exercises. Attendees will leave with a working knowledge of how to write scalable codes using MPI ? the standard programming tool of scalable parallel computing.
This workshop is NOT available via a webcast.
Please choose the University of Utah as a site on the XSEDE Portal Registration pages:
The tentative agenda given below is subject to change.
Tuesday, December 3
All times given are MST
9:15 Computing Environment
10:00 Intro to Parallel Computing
11:00 Lunch break
12:00 Introduction to MPI
1:30 Introductory Exercises
2:30 Scalable Programming: Laplace code
3:00 Adjourn/Laplace Exercises
Wednesday December 4
All times given are Eastern
9:00 Laplace Exercises
10:00 Laplace Solution
10:30 Lunch break
12:30 Outro to Parallel Computing
1:30 MPI Debugging and Profiling
Please visit the workshop page for more information:
Ember and Kingspeak core service interruption
Posted: November 5, 2013
Around 3:30 p.m. this afternoon a core service machine that supports both kingspeak and ember experienced an outage. CHPC staff have recovered the service and all should be returned to normal over the next few hours. All nodes are being swept currently to make sure there are no problems. We will send an ALL CLEAR once we have verified all nodes.
ALL CLEAR: 4:26 p.m. Please report any questions or problems to firstname.lastname@example.org
Retirement of turretarch1 (linux statistics box) - Dec 1, 2013
Posted: November 4, 2013
Effective Dec 1, 2013 CHPC will no longer be maintaining turretarch1.chpc.utah.edu, the linux statistics machine. There are a number of reasons for this decision.
- This box has had very limited use since the start of the year
- CHPC has in place a windows statistics box, Kachina. Information on Kachina, available software, and how to access can be found in the Kachina User Guide
- Linux version of some of the packages available on Kachina are accessible on the CHPC clusters
If you need to discuss the impact of this decision on your research, please send in a request to email@example.com.
OpenACC programming workshop
Posted: October 18, 2013
CHPC will be a satellite site for an XSEDE workshop presented by the Pittsburgh Supercomputer Center that focuses on OpenACC. OpenACC is the accepted standard using compiler directives to allow quick development of GPU capable codes using standard languages and compilers. It has been used with great success to accelerate real applications within very short development periods. This workshop assumes knowledge of either C or Fortran programming. It will have a hands-on component.
The workshop will take place on November 5, 2013 in INSCC Auditorium (INSCC 110) from 9am to 3pm. To register, follow https://portal.xsede.org/course-calendar/-/training-user/class/152/session/269.
There is no registration fee for this workshop.
Please address any questions to the CHPC help desk at firstname.lastname@example.org.
XSEDE HPC Monthly Workshop – OpenACC
Tuesday November 5
All times are given are MDT
9:15 Computing Environment
9:45 Parallel Computing & Accelerators
10:15 Intro to OpenACC
11:00 Lunch break
12:00 Introduction to OpenACC (cont.)
1:00 Using OpenACC with CUDA Libraries
2:30 Advanced OpenACC and OpenMP 4.0
Ember now available
Posted: October 17, 2013
Access to Ember is now available. Please take note of the information listed below before you start using the cluster. We consider this first few days of access as a testing period, as it is impossible for CHPC to thoroughly test all possible running conditions. We will be monitoring the nodes and will offline any nodes if we see an issue. If you run into any problems please send a report to issues.
Below is some very important information about changes
- The cluster is now running RHEL6 and has new versions of the batch scheduler and usage accounting software; it is now the same as what is running on Kingspeak.
- The batch policies should be identical to what they were before ember was relocated.
- The node numbering has changed -- very important for those who ssh to the nodes. A new listing of the node numbers is available on this CHPC wiki page
- SSH keys have changed. You will get messages and not be able ssh to the nodes until you have either deleted your .ssh/known_hosts or edited this file to remove all entries for the ember interactive and compute nodes by searching and removing keys for ember, ember*, em*, and 172.17.4*.*
- You need to check if there is a new RH6 build of any other package/library (e.g., OpenFoam, python,netcdf) before running – these are indicated by a _rhel6 or _rh6 after the version number. While CHPC has tested many of the builds, we may have not caught all the ones that need rebuilt for the new OS --- please let us know of any we may have missed.
- You need to check your codes to see if they need rebuilt. We strongly recommend that you no longer use any packages/libraries in /uufs/arches/sys location; we will not be maintaining this file system moving forward. It is important that you use the RH6 version of the compilers (listed below):
- PGI: /uufs/chpc.utah.edu/sys/pkg/pgi/std_rh6
- GNU: /usr/bin/gcc (4.4.7) OR /uufs/chpc.utah.edu/sys/pkg/gcc/4.7.2_rh6 (also gfortran)
- INTEL: there is no change for the path to the intel compilers
- In the/uufs/ember.arches/sys/pkg application tree, the std, std_intel, std_pgi links for MVAPICH2 and OPENMPI point to the RHEL6 versions
- New ember specific builds of FFTW, BOOST, AMBER12, GROMACS can be found /uufs/ember.arches/sys/pkg; the old ones have permissions set so they are not accessible/executable. New ember builds of QE and LAMMPS are being worked on.
- For GPU node use – we have updated CUDA to 5.5 (/usr/local/cuda)
New Allocation Usage Tracking pages Available
Posted: October 9, 2013
New General Allocation Pool Usage pages are now online
With the change to a general allocation pool instead of individual allocations on ember and kingspeak, new allocation usage tracking pages have been created.
Here are the links:
As a reminder, here are the corresponding links for the usage on updraft and sanddunearch:
- Updraft Usage by Project
- Sanddunearch Usage by Project
- Updraft Usage by User
- Sanddunearch Usage by User
Finaaly for usage of prior quarters see Allocation Usage.
If you have any questions about these pages, please email email@example.com
DOWNTIME -- Oct 14 starting at 6:30am
Posted: October 3, 2013
Duration: All day, starting at 6:30am
Overview: During this downtime the quarterly cooling maintenance on the Komas Datacenter will be performed, the Redbutte File Server will be relocated from the SSB Datacenter to the Downtown Datacenter, the /uufs/chpc.utah.edu/sys application file system will be moved to new hardware, and system updates will be applied to the HOMERFS file system.
Detailed Impact to Users:
- Updraft and Sanddunearch clusters will have their batch queues drained by 6:30am in preparation for the clusters to be shut down for the cooling maintenance in the Komas Datacenter. They will be brought back online once the maintenance is complete.
- Telluride, Apexarch and Turretarch clusters will have their batch queues drained by 6:30am in order to move the application file system to new hardware. These clusters will be brought back once this move has been completed.
- The protected environment file system, HOMERFS, will have firmware updates applied. This means that Apexarch and SWASEY will be unavailable until this is completed and returned to service.
- The Redbutte file server will be moved from SSB to the Downtown Datacenter. Our goal is to have this up before the end of the day (but it will most likely be late). While we do not expect any problems with this move CHPC recommends that any critical data in the GROUP spaces, which are either not backed up or only backed up with quarterly archives, should be moved or copied elsewhere as a precaution. Many groups have space on other the salt flat or dry creek file servers; another alternative for temporary storage would be one of the scratch file systems. The following groups are impacted:
- HOME directory: Baron, Cheatham, Cliu, Garrett, Gregg, Horel, Jenkins, Jiang, Krueger, Lin, Mace, Paegle, Perry, Reichler, Smithp, Steele, Steenburgh, Strong, Whiteman, Yandell, Zhdanov, Zipser, and Zpu.
- GROUP spaces: cliu-group1, garrett-group1, horel-group, krueger-group1, mace-group1, steenburgh-group1, lin-group1, reichler-group1, strong-group1, whiteman-group1, zpu-group1, cheatham-group1, cheatham-group2, avey-group1, baron-group1, gregg-group1, sandick-group1, steele-group1, stoll-group1, voelk-group1, and yandell-group1
- Note that kingspeak (and ember if it is back in service by this time) will not have their queues drained or be shut down. HOWEVER, if you are in one of the groups with a HOME directory listed in the previous impact item, any running jobs and any interactive sessions will hang when the file server is turned off for the move. We recommend that users in these groups log out of any interactive sessions, and plan on having their running jobs exit before 6:30am on Oct 14. Any idle jobs in the batch queue should have batchholds placed on them.