Reed's Ruminations: A Blog by Dan Reed

Eudora, You Got the Love?

As I was unpacking boxes of books recently, as part of my move to Microsoft, I opened my copy of the collected stories of Eudora Welty. This awakened memories of my southern childhood and two anecdotes about Ms. Welty, one technical and another cultural.

HPC Procurements and NRE

In the current issue of HPCWire, John West has some thoughtful comments on the HPC procurement process. In an article entitled, "HPC Innovation in the Era of 'Good Enough'," he analyzes the competitive pressures on vendors and procurements and the small margins available to fund non-recurring engineering costs (i.e., vendor research and development).

In the article, Jon references my Congressional testimony on the universality of computing as an intellectual amplifier. I recently reprised some of those comments in an essay for SIAM News, discussed in this blog entry. John also quotes me as saying one cannot build a national strategy on a series of point procurements. Let me expand on that observation.

I believe we need to recognize that innovation has real costs, which must be jointly borne by academia, industry and government. We also must view hardware procurements in a larger context, where their acquisition is driven by both a coherent R&D strategy and by an innovation-driven deployment rationale.

The "mine's bigger than yours" bragging associated with machoFLOPS is counter-productive. Let's measure new systems by the innovation they enable, in new technology, scientific discovery and competitiveness. More to the point, let's integrate over periods longer than the latest benchmarks and deployment milestones.

Random Musings

Like many of you, I give lots of public (and not so public) presentations, on a variety of topics. A couple of those were recently captured and placed on the web. The first was one of the opening talks at the Big Data Symposium, recently held at Yahoo!, as part of the Computing Community Consortium (CCC) big ideas series. If you are struggling to sleep, you can catch the video here.

The second was an open-ended discussion on Microsoft's Channel9. I rambled on about multicore processors, big data center design challenges and a bit of web history. If the first video didn't put you to sleep, you can get the double feature effect here

Salishan, Exascale and Heterogeneous Multicore

Update: The proccedings from the meeting are now online.

Every year, the three U.S. Department of Energy (DOE) weapons laboratories (LANL, LLNL and SNL) organize a workshop on the state of high-performance computing and computational science. By long tradition, the meeting is held at the Salishan lodge on the Oregon coast. The attendees are drawn from the three weapons laboratories, the DOE Office of Science laboratories, other computing-intensive elements of the U.S. government (e.g., the NSA and DoD HPC Modernization Program), the NSF supercomputing centers, key academic researchers and industry high-performance computing leaders. I've been attending for many years, both as the former NCSA director and as a federal science policy wonk.