We have already written about iLO and its capabilities. However, it is worth getting more attention.

When deploying smaller or larger clusters, we start hardware configurations by setting iLO (server name, network configuration or adding the user). For smaller deployments, we proceed normally by logging in to each server manually and making necessary changes on the Website. But what if the implementation includes 100, 500 or 1000 servers? The mere thought of manually configuring so many machines can be a headache!

Continue →

One of the most important tasks for every data center and computing cluster administrator is to manage and monitor the existing infrastructure. Often you need a lot of utilities, hardware, and software in order to do this. With HP Advanced Power Manager, you can simplify and hp_apmconsolidate the management and monitoring processes into one device and location.

Continue →

MEGATEL company, as a MEGATEL & ACTION consortium leader participates in installation of two of biggest HPC clusters in Poland. Each of the HPC cluster will exceed a magic threshold of 1 PFlops.

First HPC cluster will be located at AGH UST in the ACK CYFRONET datacenter in specially built new facility in Cracow. The latest cooling technology called hot water cooling will be used for cooling. The cluster will be built of more than 1,700 2P Intel Haswell (E5-26xx v3) connected with the Infiniband FDR network. The total computing performance (Rpeak) will be 1.6+ PFlops.

The second HPC cluster will be located at Gdansk University of Technology in CI TASK datacenter. This time, it will be the air-cooled system. It will also be built of more than 1,300 2P Intel Haswell (E5-26xx v3) nodes connected with Infiniband FDR network. The total computing performance (Rpeak) will be 1.2+ PFlops.

You can find more information in our PROJECTS section of the home page.

HPC cluster Prometheus

HPC cluster Tryton