In this newsletter:
- Eid Holidays
- RCAC meeting
- Tip of the week: OpenMP 5.0 Environment Variables
- Follow us on Twitter and YouTube
- Previous Announcements
- Previous Tips
Eid Holiday: 16-23rd July 2021
KAUST will be on holiday from July 16th until 234e due to the EID Al-Adha Holiday. Please do not expect to receive replies to support requests during this period, nevertheless, Shaheen and Neser will be operating. We encourage users to continue submitting jobs and take advantage of the resources available during this period.
The project submission deadline for the next RCAC meeting is July 31st 2021. Please note that the RCAC meetings are held once per month. Projects received on or before the submission deadline will be included in the agenda for the subsequent RCAC meeting.The detailed procedures, updated templates and forms are available here: https://www.hpc.kaust.edu.sa/account-applications
Tip of the week: OpenMP 5.0 Environment Variables
The runtime display OpenMP thread affinity feature is enabled with the environment variable OMP_DISPLAY_AFFINITY. This feature, included in the OpenMP 5.0 standard, allows more portable and standard thread affinity display info across all compilers (Intel compiler (18.0.5 and newer), and will be available soon for gcc (9.0 and newer) and CCE (9.0 and newer), without the need to use the runtime API inside your code.
Setting this to true will display affinity information for all OpenMP threads when entering the first parallel region and when any thread affinity information changes in subsequent parallel regions.
You can also set the following runtime environment to obtain affinity information as part of the job stdout with:
- Intel compiler : export KMP_AFFINITY=verbose
Cray CCE compiler export CRAY_OMP_CHECK_AFFINITY=TRUE
Please note that results from each compiler have different formats. Make sure that you adequately use the number of threads by exporting the variable OMP_NUM_THREADS and using the srun command to validate your runs with the desired number of threads.
Follow us on Twitter and YouTube
Follow all the latest news on HPC within the Supercomputing Lab and at KAUST, on Twitter @KAUST_HPC.
Our KSL training recordings are now available for you to browse on-demand in our KSL YouTube channel , Subscribe and hit the notification button to keep up to date with our latest material.