September 10, 2010
Andrew Keane, General Manager, Tesla High Performance Computing at NVIDIA published a rousing call to arms in All Things Digital with his treatise on the “Crisis in Computing” and its effects on the American economy. Echoing the Council on Competitiveness and its statement that HPC is a cornerstone of economic well-being and leadership, Keane suggests that America is lagging behind in the key areas it once dominated, and that once we have fallen back, climbing back to the top is a laborious, if not nearly impossible task.
On a more refined level (and harkening back to NVIDIA’s aims as well) Keane argues, “the traditional CPU-based technology that once put America in the lead is now the anchor holding us back. Our legacy computing is no longer scaling cost-effectively and power-efficiently enough. The effects of this lost leadership will soon be severely felt in every aspect of American business and economic life unless we decide to do something about it.”
This is a common sentiment but the problem he identifies in terms of “legacy” computing does not have a simple solution, in part because HPC is so broadly-encompassing and scattered across academia and industry. Keane states that it’s now “past time to for private industry and the public sector to get our HPC act together, before other nations steal the show” but this is certainly easier said than done.
It’s difficult to counter conjecture that America is, indeed, quickly falling behind in terms of HPC-enabled development. The most commonly proffered example to represent the dwindling competitive edge is China, with its swift developments—all made on our processors. In Keane’s view, coming as he does from the world of GPUs, China (and Europe, for that matter) are “jumping straight into next-generation, hybrid HPC by adding graphics processing units (GPUs) to drive far better price, efficiency and performance.” The result is that competitors are able to deploy tremendous capability at a lower price.
Keane is stating in no uncertain terms that GPU computing is a key to improving, refining, and building upon the systems and developments of the past—but that the past systems are the only thing still lurching us forward. This is a bold statement to make but it’s certainly not without significant merit. Supercomputing capacity matched with bleeding edge visualization is the key to emerging research and developments that are reliant on visualization, simulation and modeling but if we rely on what we have already (and there are good reasons for that, of course since HPC is…duh…incredibly expensive) and do not expand our horizons, the knowledge economy that is beginning to sustain us now more than any other time in American history will crumble. Like will, not might. It’s down to the wire.
As Keane notes…
“To sustain and extend our lead in high performance computing, we don’t have to revive the decades-old debate about industrial policy and the government picking winners through massive bets on industry sectors. We just need to spend smarter to get cost-effective hybrid HPC on the national agenda, and equip our best minds with the computing capacity they need to innovate and create jobs.”
Full story at All Things Digital
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?