Non-uniform memory access (NUMA) systems are servers made up a single planar board (motherboard) with more than one CPU socket. On such servers, each CPU socket is directly connected to part of the system main memory but can also use parts of the main memory to which it is not directly connected via a crossbar or interconnect.
A hearty happy new year to everyone. It’s that time of the year that we hear from folks about their resolutions for new year’s. But rather than talk about me purchasing a gym membership, I’d like to share my thoughts on a new year’s resolution for HPC.
As users of HPC look to build new workflows that go beyond traditional simulation and modeling, cloud native development models that rely upon Kubernetes (K8s) and Docker are front of mind.
We live in a results-driven world. Whether it’s an aerodynamicist waiting on simulation results to determine the efficiency of their latest model, or a doctor waiting on genomic pipeline results to determine next steps for a patient, results make the world go round.
I love it when a plan comes together! And this time, I’m not referring to a daring rescue by the A-Team, but rather something just slightly more mundane - network attached storage (NAS).