Nvidia GRID is a family ofgraphics processing units (GPUs) made byNvidia, introduced in 2008, that is targeted specifically towardscloud gaming.[1] The Nvidia GRID includes bothgraphics processing andvideo encoding into a single device which is able to decrease the input to display latency of cloud basedvideo game streaming.[2] It is used by Nvidia'sGeForce Now, a paid cloud gaming service.
While many of Nvidia’s cards are known for gaming, there has been a recent growth ofbusiness applications that are GPU-accelerated.[timeframe?] The Nvidia GRID K1 and K2 are being integrated withSupermicro server clusters for use with 3D-intensive applications such as graphics andcomputer aided design (CAD).[3] In 2015, Microsoft began including Nvidia GRID as part of itsAzure Enterprise cloud platform targeted towards professionals such as engineers, designers and researchers.[4]
| GRID K1 | Grid K2 | |
|---|---|---|
| Microarchitecture | Kepler | |
| Number of GPUs | 4× GK107 | 2× GK104 |
| Number ofCUDA cores | 4× 192 | 2× 1536 |
| Memory site | 4× 4 GB DDR3 | 2× 4 GB DDR5 |
| Max power | 130 W | 225 W |