+1 607 252-6647 Email Questions

GPU databases are coming of age

  • Published in News
  • Hits: 164

Video: Cryptocurrency mining raises GPU prices, causes shortage

GPUs are that obscure object of desire right now. Originally created to provide better performance for gamers, now everyone from crypto miners to deep-learning experts wants a piece of them.

Read also: Nvidia's Titan V giant: $3,000 buys you 'most powerful PC GPU ever'[1]

Increased demand for cryptocurrency mining and competition for memory modules has created a perfect storm driving GPU prices to skyrocket[2]. That's bad news for users, but great for GPU manufacturers like Nvidia.

We have elaborated on ZDNet on how Nvidia has gone from gamer's delight to AI powerhouse[3]. Just looking at the agenda at GTC[4], Nvidia's GPU Technology Conference taking place this week in Silicon Valley, confirms this transition.

But why should you care about GPUs if you're not into AI, gaming, or crypto? Because GPUs can also accelerate your databases, and there's not a single organization today not using one.

Massive parallelism through GPUs

GPUs greatly accelerate operations that can be parallelized. This approach has been in use in masively parallel architectures such as Hadoop or Spark for a while now. The idea is to combine an array of database instances, each on a separate server, and then to use a master node that delegates subqueries to each one.

Read also: Google releases Cloud TPU beta, GPU support for Kubernetes[5]

The individual servers execute their subqueries in parallel, get the result sets back to the master node, which combines them and sends a single one back to the client. GPUs make the same divide-and-conquer approach possible within individual servers, with CPUs taking the role of the master node.

gpu-acceleration.jpgGPUs can greatly accelerate

Read more from our friends at ZDNet

Contact us

By Mail

PO Box 5613

Katy, TX 77491

USA

Social: twitter facebook

Phone: +1 607 252-6647

Fax: +1 866 573-1096

Email: info [AT] synapticweb [DOT] co