Dear HPC Users, We have been observing and monitoring the usage of the HPC cluster closely recently, and we will be making changes to the current Quality of Service (QoS) system which we feel is necessary. The new changes will change the way users submit their jobs and use the HPC cluster, Read more
Dear DICC users, There will be a scheduled power maintenance work on 4 Jun 2021, 10.00pm in KPPI building, thus the power supply to the server room will be affected. All existing servers will be power off so the service will not be accessible during the maintenance. The maintenance work is Read more
Dear DICC Users, There was a major power outage in our HPC data center since 19 May 2021, around 10am. The power outage is currently causing all DICC servers to power off and all DICC services are affected. All the DICC services will not be accessible during the power outage. We will be updating again once the power issue Read more
Dear DICC users, We are experiencing a major power outage in our HPC data center since 4th April, around 7.20 am. The power outage has caused most of the servers in DICC to power off and affected all DICC services. We have recovered most of the operation of our services around 9.45 am, 5th April. For Read more
Dear all HPC users, Due to the heavy loads observed on the CPU compute machines in the HPC, we have decided to reserve 2 out of 64 CPUs for the system uses, in order to prevent system instability when all the CPUs in the machines are heavily loaded. Therefore, the new available Read more
Dear HPC Users, The scheduled server maintenance on gpu02 has been successfully completed. The server is now available for job execution with 4 GPU cards (Titan X, 2 * Titan Xp, GTX 1080Ti). Meanwhile, cluster-info output in the umhpc node has been updated with a more organized display layout. If you encounter Read more
Dear all HPC Users, There was an incident where one of the CPU compute nodes in the HPC pool, cpu06 crashed due to high CPU load caused by some processes stuck in the machine indefinitely. This incident has caused all the jobs running in cpu06 to fail as the worker daemon was not Read more