vacancies advertise contact news tip The Vault
EPIC HEXUS COMPETITION: Win a Moto 360 or Omate X smartwatch.! [x]
facebook rss twitter

NVIDIA reveals VGX virtualised graphics cards, the K1 and K2

by Alistair Lowe on 18 October 2012, 09:45

Tags: NVIDIA (NASDAQ:NVDA)

Quick Link: HEXUS.net/qabnwz

Add to My Vault: x

It was back in May when NVIDIA first revealed its intentions to bravely enter the cloud with its new VGX processor line-up and now, the firm has officially unveiled its first two models.

The NVIDIA VGX K1 is constructed from four low-end cores to achieve the maximum possible performance-per-watt ratio, whilst supporting 16GB of DDR3 RAM, the focus, of course, is to maximise the number of users that can be simultaneously virtualised on the card and to reduce the power footprint of each one. The K1 is targeted at large firms with a high number of users to cater to and, is capable of handling up to 100 clients.

The VGX K2, on the other-hand, features two high-end Kepler cores, not dissimilar to an underclocked GeForce GTX 690, however with 8GB of GDDR5 RAM, enabling a greater client count, which NVIDIA claims is a maximum of 64. The K2's focus is on delivering superior per-client performance, at the expense of power efficiency.

NVIDIA VGX K1 and K2

NVIDIA VGX K1 NVIDIA VGX K2
Number of GPUs 4 x entry Kepler GPUs 2 x High-end Kepler GPUs
Total NVIDIA CUDA cores 768 3072
Total memory size 16GB DDR3 8GB GDDR5
Max power 130W 225W
Board length 10.5in 10.5in
Board height 4.4in 4.4in
Board width Dual Slot Dual Slot
Display IO None None
Aux power 6-pin connector 8-pin connector
PCIe x16 x16
PCIe generation Gen3 (Gen2 compatible) Gen3 (Gen2 compatible)
Cooling solution Passive Passive

It's interesting to note that NVIDIA has been able to passively cool both boards and is using this fact to promote high 24x7 reliability, though, just how clock speeds have suffered in exchange remains to be seen.

With a little quick math and of course, assuming outrageously optimistic operating conditions and bottlenecks; at maximum user-loads, virtualised clients could expect the equivalent performance from their cards:

(768 | 16) / 100 = 7.68 cores |  160MB RAM

(3072 | 8) / 64 = 48 cores |  125MB RAM

Of course, the real magic behind virtualisation is that it's unlikely all users will be active or at full-load at any one time and so those needing performance should be able to claim a larger slice of the pie, at least for a while, though, games design firms or a CG houses should perhaps consider running fewer clients off a single VGX card!

Virtualisation is all well and good, however, access still typically requires a thin-client and, with a plentiful supply of efficient APUs on the market, it's a shame to see this power go to waste.



HEXUS Forums :: 6 Comments

Login with Forum Account

Don't have an account? Register today!
It's interesting to note that NVIDIA has been able to passively cool both boards and is using this fact to promote high 24x7 reliability


Jammed in a 1U chassis with a dozen 40mm stupid-rpm fans at the front maybe?
DDY
It's interesting to note that NVIDIA has been able to passively cool both boards and is using this fact to promote high 24x7 reliability
Jammed in a 1U chassis with a dozen 40mm stupid-rpm fans at the front maybe?


You must remember that server environment is not quite as the standard user occupied room. They might lower the temps of the whole room to close to 0C and provide enough airflow so the cards would work without any trouble. I am sure NVidia has many options and suggestions.
The K1 ..., is capable of handling up to 100 clients.

The VGX K2, ..., enabling a greater client count, which NVIDIA claims is a maximum of 64.

I didn't drink my 'morning' coffee yet, but something seems wrong with the numbers there, doesn't it? :O
Looking at the specs, K1 takes lots of users but with pretty low end performance - i.e. generic desktop users. K2 is for power users (CAD types, Google Earth, video editing and so on)
Nvidia is on the right track but still have a long way to go until cloud gaming will be worth it. Maybe if Nvidia maxed out the k2's load at 32 or 16 people you would get to being able to play games.