
NVIDIA has announced its new flagship in the scientific computing field, the Tesla K80, powered by two brand new GK210 GPUs (Kepler architecture).
Here are the main specs of the beast:
- GPU: 2 x GK210, base clock: 562MHz, boost: 875MHz, TSMC: 28nm
- CUDA cores: 4992 (2 x 2496)
- Memory: 24GB (2 x 12GB) GDDR5 @ 5GHz effective, 2 x 384-bit
- TDP: 300W
- FP32 TFLOPS: 8.74
- FP64 TFLOPS: 1/3 FP32
- Compute Capability: 3.7
Links:
- (Press Release) NVIDIA Unveils World’s Fastest Accelerator For Data Analytics And Scientific Computing
- Tesla Server Solutions @ NVIDIA
- NVIDIA Launches Tesla K80, GK210 GPU @ AnandTech
I think you’ll find the compute capability is TeraFLOPS, not GigaFLOPs.
Thanks for pointing out the typo, of course it’s TFLOPS and not GFLOPS 😉
http://www.asus.com/Graphics_Cards/GTX970DCMOC4GD5/
ASUS GeForce® GTX 970 DC Mini