In the latest installment of my "Microsoft Big Brains" series focusing on the company's technical fellows, I profile someone who is focused as much, if not more, on hardware than software: Systems architecture pioneer Chuck Thacker.
Last year I launched this series -- "Microsoft Big Brains" -- to help remedy that shortcoming. In the coming weeks, I am hoping to profile as many of the company's tech fellows as to whom I can get access.
Microsoft's Technical Fellows came to the company via a variety of different routes. Some of them run divisions inside the company; some focus on particularly thorny technical issues that may span a variety of product units. Regardless of where they sit in the organization, the fellows all have been charged with helping Microsoft craft its next-gen products and strategies, much the way that Gates used his regular "Think Weeks" to prioritize what Microsoft needed to do next.
This Week's 'Big Brain': Chuck Thacker
Claim to Fame: Helped establish Microsoft's Cambridge, UK, research lab and, later, worked on developing the first hardware prototype for the Tablet PC.
How Long You've Been With Microsoft: 11 years
More About You: Before Microsoft, worked for Xerox's Palo Alto Research Center (PARC) and the Digital Equipment Systems Research Center. Was chief designer on Alto, "the first personal computer to use a bit-mapped display and mouse." In 2004, received the Charles Stark Draper Prize for the development of the first networked, distributed PC. In 2007, received the IEEE John Von Neumann medal.
Your Biggest Accomplishment (So Far) at Microsoft: Helping to develop and make available to academics field-programmable gate-array (FPGA) technology.
Team(s) You Also Work With: Microsoft Research, Windows, Xbox, Dryad (parallel/distributed system management).
Why Stay at Microsoft? "Leverage. You have the opportunity to do game-changing things."
Over the last 15 years, computer architecture research has gotten really boring, according to Microsoft Technical Fellow Chuck Thacker.
Back in the heyday, "if you wanted to build a new computer, you could. But now the cost of building a chip is astronomical -- it's kind of like building an operating system," Thacker said.
That's why Thacker is focused on helping build field-programmable gate arrays (FPGAs), which are semiconductors that can be custom-configured after they're manufactured. Thacker is teaming with other industry and academic researchers on the Research Accelerator for Multiple Processors (RAMP) consortium.
One of Thacker's pet project's, the BEE3 (Berkeley Emulation Engine version 3) -- a four-FPGA system that is used for computer architecture research and is a target for RAMP -- is starting to be licensed to academics and businesses so they can prototype all kinds of hardware platforms more cheaply. BEE3 is designed to help researchers more quickly prototype processors with hundreds or even thousands of cores and figure out new ways to program these massively parallel processors. The latest version of BEE3 was designed with a lot of help from Microsoft and contract manufacturer Celestica. Celestica also builds a lot of Microsoft's Xbox 360s, Thacker said.)
BEE3 "lets you run real software," Thacker explained. "Architectural research has tended to use software simulators. But with (that approach), it could take you a week to boot an operating system."
Even though Microsoft is a software company, not a computer maker, the company has a keen interest in computer and systems architecture. The Xbox group -- where Thacker did a six-month stint a few years back -- is keenly interested in FPGAs. The technology could be applied by the Microsoft Mobile unit (and mobile phone makers), PC and netbook makers -- any company or division interested in "what-if" design scenarios, Thacker said.
Thacker said even though he is "of retirement age," he has no intentions of retiring any time soon. Currently, he is an individual contributor to the Microsoft Research Silicon Valley Lab, which is heavily focusing on distributed computing and systems architecture. Thacker is no longer invovled with Microsoft's Tablet PC work; he's all about large-scale distributed systems work these days.
"We're accelerating algorithms that don't fit into traditional computing," Thacker said. "We can change the structure of the computing element." And those changes could affect everything from financial modeling, to CAD, to PCs and systems futures, he said.