Nvidia Expands From Gaming to High-Performance Chips
Nvidia, known for graphics processors designed for video gaming, is expanding into the market for high-performance computing processors.
Nvidia today introduced the Tesla line of processors, which it bills as making high-density parallel processing capabilities available in workstation computers.
The Tesla graphics processing unit (GPU) features 128 parallel processors and delivers up to 518 gigaflops of parallel computation. A gigaflop refers to the processing of a billion floating point operations per second. Nvidia envisions the Tesla being used in high-performance computing environments such as geosciences, molecular biology or medical diagnostics.
Nvidia also will offer Tesla in a workstation, which it calls a "Deskside Supercomputer," that includes two Tesla GPUs, attaches to a PC or workstation via a PCI-Express connection, and delivers up to 8 teraflops of processing power. A teraflop is the processing of a trillion floating point operations per second.
A Tesla Computing Server puts eight Tesla GPUs with 1,000 parallel processors into a 1U server rack.
The list price for the Tesla GPU would start at US$1,499 and the deskside computer at $7,500. Both will be available beginning in August. Qualification samples of the Computing Server, with a list price of $12,000, will be available in September. The product will be fully available in the November-December time frame, Nvidia said.
"Scientists will know how to use this and produce results," said Jen-Hsun Huang, president and CEO of Nvidia, at a preview event for journalists last month at the company's headquarters in Santa Clara, California. "They will be able to do simulations in days, not months, seconds, not minutes."
A number of enterprises see promise in the new Nvidia processors, including Headwave, which analyzes geophysical and seismic data to discover underground oil deposits and is interested in the Tesla line. The oil exploration industry needs better tools to analyze data from its search efforts, said Steve Briggs, vice president of system integration for Headwave.
"If it costs you $150 million to drill a hole, you don't want a dry hole," Briggs said at last month's event.
The Tesla is the third major product line from Nvidia, whose GeForce GPUs deliver high-end PC graphics. Its Quadro processor line enables computer-aided design in the creation of digital content, including 3-D graphics. It also released in February a beta version of software it calls CUDA, for compute unified device architecture, which enables software code to be written to use a computer's GPU as well as the CPU (central processing unit) for added processing power. A general availability of CUDA is expected in the second half of this year.
The company is hosting an analysts' day today. One analyst, Doug Freedman of American Technology Research, still maintains a "Neutral" rating on Nvidia's stock, but raised his forecast price target to $40 a share.
"We believe the company continues to execute well," Freedman said in a note to investors. He thinks the threat from the acquisition of competitor ATI Technologies by Advanced Micro Devices "did not materialize."
However, Nvidia may face a stronger competitive threat from Intel, if the rumors are true that Intel plans to enter the GPU market in 2008, he said. Intel didn't immediately respond to a request for comment about this matter.