In a recent blog post, HPC community member and CTO of PBS Works at Altair Engineering, Inc. Dr. Bill Nitzberg, traces the recent history of computing from 1980 through the end of the present decade, to illustrate the trends that best characterize the coming exascale era.
The four decades are depicted in a slide broken down by systems, data and business trajectories with circles around the areas most relevant to the needs of exaflops-class systems:
“Exascale infrastructure will require advances in four areas: scale, speed, resilience, and power management,” writes Nitzberg. “From the trends I mentioned before, the need to support ever-increasing scale and to work around ever-decreasing resilience is clear.”
This week was also the timing for a big announcement from the engineering software company behind PBS Works, Altair’s suite of HPC workload management and cloud enablement products that includes PBS Professional. On Wednesday, Altair released the latest version of its high-performance computing workload management and job scheduling software, PBS Professional 13.0.
Meeting the needs of exascale was a big focus of the release, says Nitzberg. He provides the following bullet points to support the position that “the underlying architecture [of PBS Pro 13.0] is the right foundation [for] exascale.”
- The new TPP layer provides exceptional scale.
- Performance improvements, including a new asynchronous job startup, provides a 10x improvement in speed.
- The new 100% health check framework provides the basis for exceptional resilience.
- Concurrent with the PBS Pro 13.0 release, we have also released new power management facilities for SGI and Cray systems.
“One final thought: the focus on bigger and faster doesn’t just benefit those with massive computing infrastructures; everyone benefits from faster, more resilient infrastructure – the small, the medium, and the really big,” he adds.