Nvidia's Mightly Tesla K80 Accelerator Packs Two GPUs, 24GB of GDDR5 Memory

[[Coi] Mr.CLuBBeR]

Meet the world's fastest accelerator

If there are any kids within earshot, send them off to play or cover their ears before reading any further, we wouldn't want their little ears being exposed to excited obscenities that may follow. As in, "Holy sh*t, how much RAM!?" Try 24GB of GDDR5 memory, which is how much Nvidia decided to use on its Tesla K80 dual-GPU accelerator, the new flagship offering in the Tesla family.
According to Nvidia, the Tesla K80 offers nearly double the performance and memory bandwidth of its predecessor, the Tesla K40. It also boasts ten times higher performance than today's fastest CPUs, as it was designed for the most difficult computational challenges around -- astrophysics, genomics, quantum chemistry, data analytics, and so forth.
With two GPUs on board, 24GB of GDDR5 memory, and 4,992 CUDA parallal processing cores, the Tesla K80 boasts 480GB/s of memory bandwidth, 8.74 teraflops of single-precision peak floating point performance, and up to 2.91 teraflops of double-precision peak floating point performance. For the sake of comparison, Nvidia's Maxwell-based GeForce GTX 980 offers 5 teraflops of single-precision performance.
The Tesla K80 has begun shipping to server manufactures -- no word on price.
Follow Paul on Google+, Twitter, and Facebook


More...