Skip to main content

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

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.

Recommended Videos

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.

Adrian Diaconescu
Former Digital Trends Contributor
Adrian is a mobile aficionado since the days of the Nokia 3310, and a PC enthusiast since Windows 98. Later, he discovered…
The RTX 5060 will be Nvidia’s most important GPU, and I’m worried about it
Two graphics cards sitting on top of each other.

Nvidia just finished revealing its range of new RTX 50-series GPUs, the first of which will arrive in just a couple of weeks. They're some of the best graphics cards ever made, according to Nvidia, and for the flagship RTX 5090 that clocks in at $2,000, I believe the company. Lower down the stack, however, I'm concerned.

For the past couple of years, there's been a growing issue surrounding graphics cards with 8GB of VRAM, which is something we've seen on full display with games like Indiana Jones and the Great Circle. Despite backlash in the previous generation concerning releases like the RTX 4060 Ti, I'm worried that Nvidia will repeat the mistakes of the past when the RTX 5060 inevitably rolls around.
It'll be popular

Read more
Nvidia may have a complete monster GPU in the works
Nvidia's Titan RTX GPU.

Nvidia must be feeling pretty secure, sitting atop the list of the best graphics cards in this generation. That trend is likely to continue, what with AMD possibly stepping down from the high-end GPU race -- but Nvidia might still surprise us. According to RedGamingTech, Nvidia is working on a GPU referred to as "Titan AI," and it sounds like the most monstrous card we've ever seen. Another reputable leaker just confirmed that theory.

The YouTuber shed some light on the performance figures we might see in the RTX 50-series, focusing on how much each GPU will outperform its predecessor. These numbers refer to straight-up rasterization with no accounting for ray tracing, and RedGamingTech wasn't sure whether they came from gaming tests or a synthetic benchmark.

Read more
Nvidia is the ‘GPU cartel,’ says former AMD Radeon manager
A hand holding the RTX 4090 GPU.

AMD's former senior vice president and general manager of Radeon has come out with some strong words against Nvidia. Scott Herkelman called Nvidia "the GPU cartel" in response to a story from the Wall Street Journal in which Nvidia's customers claim that it delays GPU shipments in retaliation for those customers shopping with other suppliers.

The accusation in question comes from Jonathan Ross, CEO of AI chip startup Groq, who said, "a lot of people that we meet with say that if Nvidia were to hear that we were meeting, they would disavow it. The problem is you have to pay Nvidia a year in advance, and you may get your hardware in a year, or it may take longer, and it's, 'Aw shucks, you're buying from someone else, and I guess it's going to take a little longer.'"

Read more