NVIDIA's Tesla business unit product manager Sumit Gupta doesn't consider Intel's MIC architecture as a threat. He points out that developing a new GPU architecture costs $500 million to $1 billion a year and doesn't see how Intel can make this an economic investment without having a graphics business:
After Intel Corp. failed to develop its own discrete graphics processor code-named Larrabee, it said that it would concentrate on creation of many-core chips aimed specifically at HPC market. But according to Nvidia, whose Tesla compute boards power three out of top five supercomputers in the world, the high-performance computing (HPC) is not the primary market for graphics chips. As a result, it hardly makes sense to develop a chip specifically to power supercomputers.
"I do not see the economic model [with MIC]. We are able to produce those [Tesla] GPGPUs because the ultimately there is one GPU for GeForce consumer graphics, Quadro professional business. It costs $500 million to $1 billion to develop those new products every year, it is a hyge investment. Unless you have that [consumer and professional] economic engine in the background, I cannot imagine how one could make a GPU without having a graphics business," said Mr. Gupta.
Use Disqus to post new comments, the old comments are listed below.
Re: NVIDIA sees no danger from Intel HPC accelerator by Anonymous on Sunday, November 21 2010 @ 16:14:58 CET
Just remember the long, long list of things Nvidia has said are "impossible" over the years, that later became possible. I'm not saying this business model isn't true, but Intel isn't new to the business of making money...