14 DAY TRIAL // AMD is definitely not happy with ATI's R600 delay. But, in order to keep those disappointed fans drolling, AMD put together an Accelerated Computing platform that delivers over 1 teraflops of processing power. All this happened at a press event in San Francisco, California, where AMD demonstrated a "Teraflop in a Box" system running a standard version of Microsoft Windows XP Professional that was equipped with one AMD Opteron dual-core CPU coupled with two next-generation AMD R600 Stream Processors capable of performing more than 1 trillion floating-point calculations per second using a general "multiply-add" (MADD) calculation. The showcased system includes GPGPU-based technologies that perform ten times faster then today's high-performance server platforms, which are able to deliver at most 100 billion calculations per second.
One trillion floating point operations per second is enough to enable stream processing technology in order to leverage sophisticated, massively parallel processors, generally used for 3D graphics applications, solving complex real-world problems.
"The technology AMD demonstrated... is just one example of how the 'New' AMD is changing the game for our industry," said Dave Orton, executive vice president of visual media business at AMD. "Today, teraflop computing capability is largely reserved for the supercomputing space. But now that 'Teraflop-in-a-Box' is a reality, AMD can deliver an order of magnitude increase in performance."
The future Accelerated Computing systems will integrate unified processing units made up of specialized "co-processors" merged with x86 or X64 microprocessors to provide efficient and flexible acceleration for specific applications. AMD/ATI's Stream processors should benefit a wide range of energy, financial, environmental, medical, scientific, defense and security applications around the world by offering the intensive computing power they require to conduct research and deliver solutions significantly faster than any previous solution.