Feeds

Nvidia fires off Fermi, pledges radical new GPUs

Three billion-transistor HPC chip, anyone?

Top 5 reasons to deploy VMware with Tegile

Nvidia last night introduced the new GPU design that will feed into its next-generation GeForce graphics chips and Tesla GPGPU offerings but which the company also hopes will drive it ever deeper into general number crunching.

While the new chip is dubbed 'Fermi', so is the architecture that connects a multitude of what Nvidia calls a "Streaming Multiprocessor". The SM design the company outlined yesterday contains 32 basic Cuda cores - four times as many found in previous generations of SM - each comprising one integer and one floating-point maths unit. It is able to schedule two groups of 32 threads - a group Nvidia calls a "warp" - at once.

Nvidia Fermi chip

Nvidia's Fermi: each of the 16 green strips is...

The networked cores connect to 64KB of shared L1 cache, also used by four Special Function Units (SFUs) which handle complex maths formulae such as sines and cosines.

Fermi itself packs in 16 SMs - that's 512 Cuda cores in total - which tap into shared 768KB L2 cache and can reach out to a maximum of 6GB of GDDR 5 memory over a 384-bit interface and with ECC support

This is only the first Firmi GPU design. It's aimed at science and engineering GPGPU apps rather than game graphics, so future Fermi-based GeForce chips will likely sport less complex layouts. GT300, Nvidia's next GPU core, will be derived from Fermi, but don't expect it to show off all the superlatives Nvidia has been claiming for the Fermi chip.

Stream Multiprocessor

...one of these 32-core Stream Multiprocessors

The first Fermi design uses three billion transistors. It supports 64-bit addressing, double that of the previous generation GT200 architecture, the one used in GeForce GTX 200-series GPUs. It can handle 256 double-precision floating point ops per clock and 512 single-precision ops, up from GT200's 30 and 240, respectively.

And the key fact Nvidia didn't mention: when the Fermi-sourced GeForces will go on sale. ®

Beginner's guide to SSL certificates

More from The Register

next story
It's Big, it's Blue... it's simply FABLESS! IBM's chip-free future
Or why the reversal of globalisation ain't gonna 'appen
IBM storage revenues sink: 'We are disappointed,' says CEO
Time to put the storage biz up for sale?
'Hmm, why CAN'T I run a water pipe through that rack of media servers?'
Leaving Las Vegas for Armenia kludging and Dubai dune bashing
Microsoft and Dell’s cloud in a box: Instant Azure for the data centre
A less painful way to run Microsoft’s private cloud
Facebook slurps 'paste sites' for STOLEN passwords, sprinkles on hash and salt
Zuck's ad empire DOESN'T see details in plain text. Phew!
Windows 10: Forget Cloudobile, put Security and Privacy First
But - dammit - It would be insane to say 'don't collect, because NSA'
prev story

Whitepapers

Cloud and hybrid-cloud data protection for VMware
Learn how quick and easy it is to configure backups and perform restores for VMware environments.
A strategic approach to identity relationship management
ForgeRock commissioned Forrester to evaluate companies’ IAM practices and requirements when it comes to customer-facing scenarios versus employee-facing ones.
High Performance for All
While HPC is not new, it has traditionally been seen as a specialist area – is it now geared up to meet more mainstream requirements?
Three 1TB solid state scorchers up for grabs
Big SSDs can be expensive but think big and think free because you could be the lucky winner of one of three 1TB Samsung SSD 840 EVO drives that we’re giving away worth over £300 apiece.
Security for virtualized datacentres
Legacy security solutions are inefficient due to the architectural differences between physical and virtual environments.