NVIDIA Pascal to offer 4 teraflops of double-precision computing power?

Posted on Wednesday, February 17 2016 @ 15:05 CET by Thomas De Maesschalck
A slide from a presentation by NVIDIA CUDA Fellow Manuel Ujaldón reveals that the company's upcoming Pascal architecture promises up to 12 teraflops of single-precision and up to 4 teraflops of double-precision computing power.

Both figures are roughly 3 times higher than the specifications of the GK110 Kepler-based Tesla K20X card. The newer GM200-based Tesla M40 delivers about half the single-precision performance, but scores pretty bad in terms of double-precision.

AMD vs NVIDIA DP gigaflops

Source: TPU

About the Author

Thomas De Maesschalck

Thomas has been messing with computer since early childhood and firmly believes the Internet is the best thing since sliced bread. Enjoys playing with new tech, is fascinated by science, and passionate about financial markets. When not behind a computer, he can be found with running shoes on or lifting heavy weights in the weight room.

Loading Comments