Intel Graphics In The Next Decade
In a resounding recognition of the importance of GPU-computing principles, Intel made a commitment to the development of Larrabee. The chip consists of multiple P54C cores, and is intended to provide both a robust scientific computing platform and a high-performance enthusiast-level gaming product. But the cancellation of Larrabee as a consumer product demonstrates the difficulty in developing a flagship GPU.
Larrabee will still be released as a product for scientific computing, where the development community is responsible for developing and optimizing code. This suggests that the issue Intel faced/faces lies in developing an optimized graphics driver and shader compiler, and the relatively-poor price/performance ratio compared to AMD and Nvidia’s offerings, rather than a fundamental issue with the hardware.
Nvidia’s early successes were due in no small part to its excellent software team, led by Dwight Diercks. Under his watch, the company developed its Unified Driver Architecture and established design and testing methodologies that form the foundation of CUDA. While far from perfect, there is no question that taken as a whole, Nvidia’s drivers have historically been very stable. AMD similarly has Ben Bar-Haim. After being recruited to ATI in 2001, he launched the Catalyst program in 2002, which is credited as bringing ATI’s Radeon drivers up to a level competitive with Nvidia. Both of these teams have been able to evolve their practices and know-how over successive generations of hardware. Intel has no such experience. It does not have the same experience in developing 3D graphics drivers, and it doesn't have a software team that has been able to evolve in tandem with the hardware development. The technical expertise to develop high-performance graphics drivers on Larrabee-type architectures is something that remains to be seen from Intel. As with Itanium, there is a good chance that the hardware is ready too far in advance of the supporting software ecosystem.
Still, Intel has a broadest set of resources to succeed and the deepest pockets to allow for a long-term investment. It succeeded with Itanium, and it will succeed with Larrabee (albeit eventually). However, as with Itanium, success will be measured only with profit and in specific niches, and there is no guarantee that the company will succeed with Larrabee in the high-end gaming market. I remain cautiously optimistic.