NASA's Outdated Supercomputers Cause Mission Delays: Time for a Refresh?
NASA's current supercomputers are outdated and underpowered, with many using 18,000 CPUs and only 48 GPUs. The agency's HEC operations are not centrally managed, leading to inefficiencies and a lack of a cohesive strategy for using on-premises versus cloud computing resources. The audit found that the security controls for the HEC infrastructure are often bypassed or not implemented, increasing the risk of cyber attacks. Transitioning to GPUs and code modernization is essential for meeting NASA's current and future needs, as GPUs offer significantly higher computational capabilities for workloads involving parallel processing. NASA needs to refocus its efforts on supercomputing to keep pace in space exploration. The agency's current supercomputing capabilities are overburdened and vulnerable. Decentralized management of high-performance computing (HEC) assets hinders the agency's ability to efficiently allocate resources and adapt to changing mission needs. The agency's reliance on outdated computing capabilities will directly impact its ability to meet its exploration, scientific, and research goals.
Related reads
- NASA missions are being delayed by oversubscribed, overburdened, and out-of-date supercomputers - The Register
- NASA IG Calls For Supercomputer Reforms
- NASA's old supercomputers are causing mission delays — one has 18000 CPUs but only 48 GPUs, highlighting dire need for update
- NASA needs to refocus on supercomputing to keep pace in space, watchdog says