Data Centre

HPC

Amazon supercharges GPU power, spits out Nvidia-backed G3

Get your office benchmarking Crysi- *cough* I mean, working

By Andrew Silver

2 SHARE

Amazon has rolled out its latest GPU computing box instance line, G3.

It comes in three flavours: g3.4xlarge (1 GPU), g3.8xlarge (2 GPUs), and g3.16xlarge (4 GPUs). The line is meant for 3D modelling, visualisation, video encoding and other graphics-intensive apps.

Amazon's G2 line first came out in 2013. The high-horse, introduced later on in 2015, was the g2.8xlarge, which came with four Nvidia Grid GPUs with 4GB of video memory and 1,536 CUDA Cores each. You could encode four 1080p video streams or eight real-time 720p video streams, Amazon said in a blog post.

The GPUs in the new G3 family come with 8GB of GPU memory, 2,048 parallel processing cores, multi-monitor support, enhanced graphics-rendering effects, Nvidia GRID Virtual Workstation features, and enhanced networking. You could record 10 H.265 (HEVC) 1080p30 streams and up to 18 H.264 1080p30 streams, Amazon said in another blog post.

To compare to the previous g2.8xlarge with 60GiB of memory and 32 vCPUs (because why not compare the best to the best), the new g3.16xlarge instance comes with 488 GiB of main memory and 64 vCPUs.

The g2.8xlarge cost $2.808 hourly on demand with Linux in Ireland, whereas g3.16xlarge costs $4.84, according to Amazon's current price list.

So if you want the grunt, it'll cost you. ®

Sign up to our NewsletterGet IT in your inbox daily

2 Comments

More from The Register

Like the Architect in the Matrix... but not: Nvidia trains neural network to generate cityscapes

GPU biz also open sources PhysX and teases beefy graphics card

Nvidia just can't grab a break. Revenues up, profit nearly doubles... and stock down 20%

Ongoing Bitcoin woes left the channel holding all the cards, and that's not a good thing

Nvidia adds nine nifty AI supercomputing containers to the cloud

Now you can splash out on tons of GPUs if you really need to

AI caramba! Nvidia devs get a host of new kit to build smart systems

Kubernetes for GPUs, a PyTorch extension, TensorRT 4, and much, much more

AI, AI, Pure: Nvidia cooks deep learning GPU server chips with NetApp

Pure Storage's AIRI reference architecture probably a bit jelly

Try our new driverless car software says Nvidia, as it suspends driverless car trials

Post crash test hits share price

Looking to nab Nvidia's GeForce chips? You need cash and patience

GPU shortage equals four-month wait time for buyers

Nvidia quickly kills its AMD-screwing GeForce 'partner program' amid monopoly probe threat

GPU giant rails against rumors of stiffing sellers

Amazon's sexist AI recruiter, Nvidia gets busy, Waymo cars rack up 10 million road miles

Roundup Your two-minute guide to this week in machine-learning world

Nvidia shrugs off crypto-mining crash, touts live ray-tracing GPUs, etc

Roundup Also, how Apple's Siri uses your location to improve its speech recognition