Thomas Piazza, Intel Architecture Group Director, Graphics Architecture, spoke honestly about the failings of Intel's Larrabee graphics architecture at this year's IDF.
At a group panel discussion with the Intel Fellows, essentially some of the smartest people at Intel, Intel's head graphics honcho was quizzed about Larrabee.
When asked if they ever expected to see a Larrabee-based graphics part coming out at all, the entire panel looked directly at Piazza, as he hunkered down in his stool.
"I honestly thought i'd get through two days without someone asking me that..." he said, followed by a simple, "I don't think so."
The Larrabee project was Intel's great hope of creating a serious consumer graphics card. For years Intel kept hinting at the power and ultra-programmable design of the thing, even going so far as to show a rather weak demo at last year's IDF in San Francisco.
Performance-per-Watt nightmares
The project was canned due to numerous delays and poor performance, meaning that even if it finally did appear it would be several generations behind the GPUs of Nvidia and AMD.
When asked why Piazza thought it had failed though he was surprisingly candid. "I just think it's impractical to try to do all the functions in software in view of all the software complexity," he explained. "And we ran into a performance per watt issue trying to do these things."
"Naturally a rasterizer wants to be fixed function." Piazza went on. "There is no reason to have the programming; it takes so little area for what it does relative to trying to code things like that."
It turned out that it was a problem of trying to balance out what they were doing, trying to find "what's the right level of programmability and what's the right level of fixed function."
Unfortunately with the Larrabee project Intel tried to make everything programmable.
