The Coalition for Academic Supercomputing (CASC) is an educational nonprofit dedicated to advocating the use of advanced computing technology to accelerate scientific discovery. Last September, CASC had its 20th anniversary meeting. Academic and industry leaders gathered in Washington DC to discuss the impact of HPC on science and engineering. Dell Global Solutions Engineering director Reza Rooholamini participated in a panel discussion entitled "HPC: The Next 20 years."

Reza's talk focused on his vision for HPC in the next 20 years. He believes that 20 years ago, the focus was on components. People discussed systems in terms of CPU speed and RAM capacity. Today, the community has a system focus. The popularity of system rankings such as the Top 500 list certainly attest to this. Reza articulated a vision for the next 20 years where the community's focus would turn from the system to the users and usage models. The presentation notes that accompany his slides describe the specifics of his vision.

I agree with Reza. The great story of HPC in the next 20 years will be that the capability we now call "High performance computing" will become so commonplace it is no longer interesting. 20 years ago computer manufacturers advertised a computer's network interface. Now networking is assumed. In fact, it is difficult to find a computer that can't be networked. Although networking in and of itself is no longer interesting, networking has given rise to ecommerce, social media, outsourcing, and many other commonplace uses that were difficult to imagine 20 years ago. In the next 20 years, massive ensemble parallelism will be synonymous with computing.

What willt he world look like when school children have access to PetaFLOP machines?