First Followers

I recently saw Derek Sivers video of “How to Start a Movement” and it caused me to pause and consider what it must feel like to be a “first follower”.

In the video, a “lone nut” is in the middle of crowd jumping and waving his arms about. My first thought is “what a dope” (how judgmental and narrow-minded am I?). I give the guy credit because that is a pretty big matzo ball to be hanging out there. But what about the first to follow and join the lone nut.

Derek makes the point that the first follower turns the lone nut into a leader. More specifically, that first follower is the one that makes it “safer” for others to join in and creates an environment that makes the movement possible.

I have never been a first follower and after seeing Derek’s video, I wish I had been.

You don’t get many opportunities to be the first follower. If you happen get one, take it. I certainly will.

Two Strong Oxen or 1024 Chickens?

Is it Getting Hot in Here?

Microsoft’s recent announcement that they are ending support for the Intel Itanium processor on the Windows HPC Server product got me thinking again about specialized processors versus low-cost commodity processors for high-performance computing (HPC) in general and specifically, HPC in the cloud.

Low-cost, general purpose processors have made the Cloud possible, not only from an economic standpoint but also due to their broad support for various programming languages, compilers and tools. The tools for specialized processors are most often special-purpose and limited which require highly trained resources. This of course results in a significantly higher Total Cost of Ownership. However, there are certainly some performance advantages which in some cases make the trade-offs worth it.

Plus, there is not anything more sexy (calm down, I’m talking computers here) than an ultra-scale High Performance Computer running Itanium or Tile-Gx specialty processors. The harmonics of the heat sinks as they dissipate the inferno created from 100 screaming cores annihilating billions of complex calculations per second, is music to the ears. Add NVIDIA’s Tesla GPU’s to this powerhouse and you have got yourself one serious Ox capable of pulling a plow through 6 feet of mud.

From Multiple Processors to Multi-tenant

Alas, the sex appeal of the specialty processor has been diminished by the economic realities of low cost commodity processors. In addition to significantly lower capital and operational costs, the technical expertise necessary to run a “generic” shop are far more plentiful and less expensive also.

It’s the Ford truck of computing models; “Never runs great but runs forever.” This approach has a long history of stable and reliable performance which dates back to the 1960’s when computer design was largely focused on adding as many instructions as possible to the machine’s CPU.

It was also at this time when “parallel computing” emerged and along with it came the multiple-processor, general purpose computer design. The system divided the workload up by distributing parts of the problem to each CPU and consolidating all the results into a single answer.

In 1965, in an effort to capture market share in the scientific field, Burroughs picked up where Westinghouse left off with their Solomon high performance computing initiative. In a shared-risk project, Burroughs teamed up with the University of Illinois as a development partner to build what would become the last generation of the ILLIAC family. Given that the systems computational resources would far exceed what the University could use, they decided they would “rent” capacity to commercial customers. This may have been the first true example of a multi-tenant cloud computing model.

Time has proven the ILLIAC’s design to be effective for technical computing applications. Today, supercomputers are almost universally made up from large numbers of commodity computers, precisely the concept that the ILLIAC pioneered. What the Burroughs engineers did not realize was that they were laying the foundation for the mega data centers that power cloud computing today.

Does Technical Computing Require a Dedicated Cloud?

There remains a question as to whether the Ford truck design will be sufficient for applications that require high-performance computing. The Cloud was not designed with technical or scientific computing applications in mind they were designed for reliability and steady, predictable performance. The biggest challenge is that not all HPC applications lend themselves to this type of processing and extracting “high-performance” from this type of design was and still is, problematic.

The Cloud presents some interesting possibilities for HPC and there appears to be a divide forming between traditional cloud models and those that are designed specifically for high performance computing applications.

SGI recently introduced their Cyclone HPC in the Cloud service which is comprised of some of the world’s fastest supercomputing hardware architectures, including Intel Xeon and Itanium processor-based SGI Altix scale-up, Altix ICE scale-out and Altix XE hybrid clusters. The Cyclone also incorporates high performance SGI InfiniteStorage systems for scratch space and long-term archival of customer data, another pre-requisite for HPC.

The technology at Cyclone’s core is highly specialized and designed exclusively for HPC workloads, something that traditional Cloud designs are lacking. While traditional Cloud computing designs can impersonate an HPC environment, they do not possess the true performance characteristics that are necessary for complex scientific and technical computation.

As Seymour Cray once remarked, “If you were plowing a field, which would you rather use? Two strong oxen or 1024 chickens?”

It is my opinion that true HPC workloads will require specialized Clouds and we will see more models like SGI’s in the near future. As a result the division between low-cost commodity and specialized Clouds will become clearer as HPC and non-HPC workloads are better defined.

PLATO: A Living Tribute to the Societal Impact of Technology

Background

Built originally by the University of Illinois in 1960, PLATO (Programmed Logic for Automated Teaching Operations) was the first computer assisted instruction system offering elementary through university coursework to UIUC students, local schools, and other universities.

Donald Bitzer, a laboratory assistant at UIUC, is considered the Father of PLATO. At the time of its conception, 10 character-per-second teletypes were the standard yet even then Bitzer recognized that in order to provide quality computer-assisted instruction, graphics would be critical.

PLATO 1 operated on an ILLIAC 1 computer and included a television set for display and a special keyboard for navigating the system’s function menus. In 1961, PLATO 2 introduced concurrent user capabilities. By 1972, PLATO was in its 4th generation and used an orange plasma display designed by Bitzer that supported bitmapped graphics. His plasma display also included an infrared touch panel that provided the ability for students to answer questions by touching the screen.

PLATO also introduced revolutionary “collaboration” capabilities that we take for granted today. PLATO was the first system to provide instant messaging, e-mail, chat rooms, forums, message boards, remote screen sharing, online testing and yes, even multi-player games.

The stewardship over PLATO changed numerous times over the years but it continued to actively function for 46 years, an astonishing accomplishment by any measure. One of its earliest, longest and staunchest supporters was Control Data Corporation President, William Norris.

While a shrewd businessman, he was more concerned by the unrest of the late 1960’s than he was in the commercial market for PLATO (or at least equally so). Norris felt that much of the unrest was due to social inequalities and PLATO offered a solution by providing higher education to segments of the population that would otherwise never be able to afford a university education.

Global Societal Impact

PLATO’s reach extended well beyond the borders of the UIUC and the United States. In the 1980’s, Madadeni College in South Africa was a major user of the system. What makes the installation interesting from an anthropological point of view is that University had approximately 1,000 students of which  99% were of Zulu ancestry.

Madadeni was a teacher preparation institution and was extremely primitive compared to other learning institutions elsewhere in the world. None of the classrooms had electricity and there was only one telephone for the entire college, which had to be cranked for several minutes before an operator may come on the line. PLATO’s term-talk was oftentimes the only way students could communicate with the outside world.

Most of the Madadeni students came from very rural areas and the PLATO terminal was the first time they encountered any kind of electronic technology. Skeptics were vocal over their concerns that PLATO would be of any use to these students but within hours most had become proficient at using the system and were learning math and science skills. A few students used online resources to learn TUTOR, the PLATO programming language, and some even wrote lessons on the system in the Zulu language.

CDC invested heavily in the development of an entire secondary school curriculum on PLATO, but unfortunately as the curriculum was nearing the final stages of completion, CDC began to falter in South Africa partly because of financial problems in the U.S., partly because of growing opposition in the United States to doing business in South Africa, and partly due to the rapidly evolving microcomputer, something that CDC failed to anticipate.

Norris continued to be a staunch supporter and as late as 1984, he announced that it would be only a few years before PLATO represented a major source of income for CDC. The PLATO service was slowly killed off when Norris stepped down as CEO in 1986. The last production version of PLATO continued to actively function until shortly after Norris’ death in 2006.

Donald Bitzer’s baby had arms that reached around the world and PLATO still stands today as an enduring legacy of the enormous societal impact of technological innovation.

Experience PLATO

PLATO still has a thriving online community that was spawned by its PLATO Notes (Pnote) and other revolutionary communication features. Apply for a free PLATO account at Cyber1 and send me a Pnote at mbaylor\cerl3.

Celebrate PLATO’s 50th Anniversary

Attend the 2 day conference June 2-3, 2010 celebrating the 50th anniversary of PLATO at the Computer History Museum in Mountain View, CA.

Special guests: Dr. Donald Bitzer, Father of PLATO and Ray Ozzie, Chief Software Architect, Microsoft Corp.