Nvidia’s Tesla K80 is a dual-GPU monster made to master fields like physics, and engineering

Nvidia's Tesla K80 dual-GPU card makes your current graphics chip look like child's play

nvidia reveals tesla k80 dual gpu server card

Now that Nvidia has seized the undisputed desktop and laptop graphics speed crowns recently with the launch of its 900 and 900M-series GPUs, Nvidia has its sights set on conquering the world of supercomputing.

With that goal in mind, Nvidia has just taken the wraps off the Tesla K80, a dual-GPU card which is meant for use in fields like data analytics, scientific computing, and more.

Whereas the consumer-oriented GeForce GTX 980 can barely deliver five teraflops of single-precision computing performance, the K80 reaches top speeds of just under nine teraflops.

A teraflop, mind you, refers to a trillion floating point operations per second. Yes, a trillion. Per second.

Now, wipe the drool from your chin.

The Tesla K80 juggles two Kepler GK210 GPUs, and supports up to 12GB of GDDR5 memory on each graphics processing unit for a grand total of 24GB. That’s some obscenely powerful hardware.

According to Nvidia, the above specs, plus 480 GB/s of memory bandwidth, 4,992 CUDA parallel processing cores, and custom technologies like Dynamic Nvidia GPU Boost, and Dynamic Parallelism allows the K80 to heavily outpace the best hardware around. Nvidia says that the Tesla K80 is ten times faster than the best CPU as well.

According to a graph on Nvidia’s website, the Tesla K80 significantly out-guns its predecessor, the Telsa K40. The graph also compares the two against an Intel Xeon E5-2697 processor, which currently costs over $2,500.

Benchmark performance shows that the K80 is in a league of its own, whether you’re talking about disciplines like chemistry, and physics, or fields like machine learning. Simply put, the K80 dominates in all of these areas, but it will be up to independent testing to verify its prowess.

Designed to work in heavy duty areas including astrophysics, genomics, and quantum chemistry research, Nvidia hopes to super-charge countless servers with the Tesla K80 dual-GPU card. Machines equipped with K80s could help propel scientific discovery even further forward.

A multitude of companies that make servers, including Asus, Bull, Cirrascale, Cray, Dell, Gigabyte, HP, Inspur, Penguin, Quanta, Sugon, Supermicro and Tyan, will sell Nvidia’s beast of a graphics card.

Pricing details aren’t public yet, but servers with the Tesla K80 inside should go on sale sometime in the near future.