Brian Santo and Sally Adee write an article on IEEE Spectrum discussing who would win the GPGPU race. Nvidia, whose Tesla chip was first to market and is now present in hundreds of thousands of laptops, or Intel, whose Larrabee has so many admirable attributes that won’t be real for another 12 months?

The authors believe that Larrabee is a winner—because of the one feature that it alone offers: C++ programmability. “There is an elephant in the room: x86 cores that will populate the Larrabee-based chips. This is the architecture today’s developers grew up with; it’s what they learned to code using the most ubiquitous programming languages, a capability that Intel says none of the competing products will have. A chip as programmable as an x86 CPU could tilt the field to Intel’s advantage.”

CUDA’s disadvantage: CUDA is proprietary language for proprietary hardware. At this point, proprietary approaches are frowned upon.

Full Story

Related Posts
Larrabee: A Many-Core x86 Architecture for Visual Computing [Whitepaper]
CUDA, Supercomputing for the Masses
Larrabee vs. Nvidia, MIMD vs. SIMD
How to Integrate CUDA with Visual C++