A look at NVIDIA's SLI Multi-OS and new Quadros

Monday 30th March 2009, 11:55:00 PM, written by Arun

NVIDIA introduced a number of new Quadro products today, along with SLI Multi-OS which, amazingly enough, allows for full 3D acceleration in guest OSes for virtualization. A beta version of their CUDA raytracing solution has also shipped to their partners in early March. We won't be covering everything in massive detail, but we did feel quite a few points as well as presentation slides were worth mentioning.

Before we begin, let's have a quick reality check: the professional market is really big, especially for NVIDIA. They had revenue of $693M (in 2008 alone) with very high gross margins, resulting in an operating profit of $322M. this is nearly three times as large as their GPU profit, and more than compensates their highly unprofitable MCP and handheld groups.

Part of the reason for this, of course, is NVIDIA's overwhelming position in the market - notice how their unit sales increased drastically in 2008 despite the major slowdown in the fourth quarter and AMD's unit sales seemingly decreasing below 2005 levels:

Where does that share come from? It's not just one big market, it's many small markets with different requirements and many of them want developer support or specific features. If you create a professional line-up aimed exclusively at the CAD market, you're only addressing a small part of this ~$700M industry; and even in CAD, the brand's reputation and the existing customer relationships mean a lot which explains why AMD hasn't had much success even there despite having had competitive products recently. NVIDIA has a great halo effect from being adopted in mission critical applications, and is currently required and specified by over 90% of Fortune 1000 companies.

NVIDIA gave many examples of niches they target, and they include product & industrial design, seismic analysis and visualisation, medical imaging, broadcast graphics delivery, film & post production, etc. - but that's not what we want to focus on today. Instead, they're introducing a new technology which will allow them to monopolize a different kind of niche, and one which they claim is fairly large: customers who need to run multiple operating systems at the same time. Here's the problem as it stands today:

NVIDIA's solution to this is to use a 'hook driver' that allows the guest OS in a virtualized system to have full access to fully benefit from one of the system's GPUs. This obviously improves productivity as well as saving a lot of money and space because you don't need two boxes, two CPUs, two noisy fans, etc. - meanwhile, NVIDIA's revenue remains identical because you can only expose one GPU per OS, and therefore still need two boards.

In fact, revenue per customer could even go up because the feature is not supported on the lower-end Quadros. Therefore it should come as little surprise that there is no plan to expose this feature on GeForce and that today it's only available on a $899 board based on a massively cut-down GT200b chip. Oh right, we didn't mention that yet, did we? So that brings us to NVIDIA's new Quadro line-up with both existing and new products:

We won't bore you with the too many specifics, but our understanding is that the first three boards are based on GT200b; however the FX3800 only has 192 SPs on a 256-bit memory bus making it substantially slower for bandwidth-limited workloads than the others. The FX1800 has 64 SPs and 192-bit, making it either a G94b or a G92b. The FX580 and FX380 both seem based on the G96b.

In addition to all this, you've also got new Quadro NVS models although some of those were announced a bit earlier. That includes the NVS 450 with four DisplayPort connections on a single bracket, something we first described in late 2007. These cards have had a lot of success for financial trading, but obviously right now most of the sales are in other areas like call centers and digital signage, as well as for general business applications in Vista.

They also talked about a few other things, including NVScale which is multi-GPU scaling solution that works very differently from classic SLI allows you to benefit from all the video memory on each board (which is very useful with massive datasets). However, it requires software modifications so that the driver has some knowledge of what's really happening in the scene. It's pre-integrated in three scene graphs including NVIDIA's own NVSG, but there's also a simple API for third-parties. You can read more about it here.

There's also 3D Vision Pro and SDI, but we won't go into that here. So finally, they also talked about their previously disclosed raytracing solution which will start shipping in the fall, but entered beta in early March. How is this related to the workstation business? Well obviously some customers like a fast but lower-quality raytraced preview before going for the full thing (which still has to be done on the CPU), but perhaps more importantly it can also be used for Real Work(TM). The rays are physically accurate yet can be computed at interactive framerates, and so the results can be used for measurement purposes etc. - for example, PSA in France (aka Peugeot Citroën) uses it for what we understood to essentially be safety engineering.

You can check out NVIDIA's two press releases on their website (1 & 2), and if you've got any comment don't hesitate to use the forum thread.


Discuss on the forums

Tagging

nvidia ± quadro, multios


Latest Thread Comments (14 total)
Posted by Tchock on Tuesday, 31-Mar-09 11:40:22 UTC
Very impressive showing for the virtualized section.I don't think their graphs were right for 08 though- ATI actually got pro marketshare back IIRC. It's 12% (IIRC) for now, probably will stay there since the new Quadro offerings are quite impressive by themselves.Margins have gone down quite some though since the FireGLs and Pros came around, so no more easy lucrative lunch.

Posted by Arun on Tuesday, 31-Mar-09 15:21:05 UTC
Quoting compres
Guest acceleration is the interesting point for me. Too bad they are restricting this to one single product in their line. I have seen active work on this feature in both VirtualBox and VMWare, so it will soon (I hope) be mainstream so the nVidia product will be pointless (I hope given the price).
Yeah, I don't know if there is any real ETA for that though - either way the OEM refresh cycle is now so it doesn't matter for this year, hopefully for AMD it'll be available by next year... :)
Quote
I don't think their graphs were right for 08 though- ATI actually got pro marketshare back IIRC. It's 12% (IIRC) for now, probably will stay there since the new Quadro offerings are quite impressive by themselves.
I don't know, here's what Jon Peddie said in December:
Quoting http://jonpeddie.com/press-releases/details/workstations_and_professional_graphics_markets_post_gains/
Nvidia meanwhile continues to dominate for professional graphics hardware, shipping 90% of overall units in the third quarter, the highest share in JPR’s records. That number may end up marking Nvidia’s peak, however, as competitor AMD is ramping a new set of more competitive products that should pull back some share in coming quarters.
So unless there was a substantial gain in Q4 for AMD, NV's numbers seem relatively credible to me. I'd love to know about any evidence to the contrary though! As for margins, yeah probably, but given their operating profit level I think that's probably also an excuse to say they can't lower their prices any further than anything else... ;)

Posted by Tchock on Wednesday, 01-Apr-09 04:16:00 UTC
http://www.pcpop.com/doc/0/378/378095.shtmlEDIT: looks like it's on JPR itself, lol.http://www.jonpeddie.com/special/Workstation.shtmlnVidia -> 90% to 86.3% (First time net market share loss since 2004, no wonder they didn't show this number :wink:)ATI -> 8.8% to 12.1%Revenue and volume are down too, but I think the midrage FirePros probably sold quite some amount- since the newer cards are starting to substantially shake off the old FireGL incompatibily/buggy stigma (R580GL and back) whilst being extremely frugal in terms of power draw.Might also be nVentory causing problems, didn't consider it to that extent.

Posted by Arun on Wednesday, 01-Apr-09 15:26:51 UTC
Ah yeah, that's Q4 though. NV's numbers are for the full 2008 year - so they're definitely correct, just if you look at the current situation ATI is clearly gaining some share - good! :) I have no idea how much of that might be nVentory issues, but clearly it can't be most of it.

Posted by iwod on Thursday, 02-Apr-09 10:29:41 UTC
Good thing ATI are gaining. Nvidia has been too arrogant and not been producing anything decent. I hope their Next Gen will be the Core2Duo equivalent. I thought the SLI Visualization is interesting, does that mean we could finally play Games on a Virtual Windows XP without much ( >5% ) performance penalty on a Mac?

Posted by bowman on Thursday, 02-Apr-09 11:52:53 UTC
Quoting iwod
Good thing ATI are gaining. Nvidia has been too arrogant and not been producing anything decent. I hope their Next Gen will be the Core2Duo equivalent.

I thought the SLI Visualization is interesting, does that mean we could finally play Games on a Virtual Windows XP without much ( >5% ) performance penalty on a Mac?
No, it means you get OpenGL acceleration for your CAD programs with your 1500 Quadro card. I didn't see any mention of D3D and I doubt they would want to mention it if it was possible.

NVIDIA segmentation at play.

This (http://forums.virtualbox.org/viewtopic.php?f=1&t=16&start=120) is what you might want to keep an eye on for any VM gaming.

Posted by Arun on Thursday, 02-Apr-09 14:18:06 UTC
Quoting bowman
No, it means you get OpenGL acceleration for your CAD programs with your 1500 Quadro card. I didn't see any mention of D3D and I doubt they would want to mention it if it was possible.
Actually, I asked explicitly and it *does* work on Direct3D... ;) However you are right that since it's limited to very expensive cards, it's not very useful in that scenario except for 'retiring' bankers.

Posted by bowman on Thursday, 02-Apr-09 15:22:28 UTC
Quoting Arun
Actually, I asked explicitly and it *does* work on Direct3D... ;) However you are right that since it's limited to very expensive cards, it's not very useful in that scenario except for 'retiring' bankers.
Really? Well, that's something alright.. Definitely.

*goes to reflash card and install Quadro drivers*

Time for some Linux/BSD/Solaris driver makers to quietly reverse engineer and get some 'inspiration' from 'SLI-Multi-OS'..:razz:

Posted by iwod on Monday, 06-Apr-09 03:13:51 UTC
Quoting bowman
No, it means you get OpenGL acceleration for your CAD programs with your 1500 Quadro card. I didn't see any mention of D3D and I doubt they would want to mention it if it was possible.

NVIDIA segmentation at play.

This (http://forums.virtualbox.org/viewtopic.php?f=1&t=16&start=120) is what you might want to keep an eye on for any VM gaming.
To me Intel VT has been proved that it doesn't work much at all........

Posted by BRiT on Monday, 06-Apr-09 04:38:52 UTC
Intel VT along with VT-d (Directed IO) helps significantly with performance. Not all Intel chipsets/motherboards support VT-d even if they support VT.


Add your comment in the forums

Related nvidia News

CUDA 4.0 and Parallel Nsight 2.0 released
NVIDIA Fermi GPU and Architecture Analysis
NVIDIA's Parallel Nsight finally released
NVIDIA GeForce GTX 460 - GF104 breaks cover
PhysX87, ancient tragedy in 5 acts by RWT
So long, Chris, and thanks for all the fish
NVIDIA GF100 graphics architecture details
NVIDIA Fermi: new GPU architecture, starting with GF100
NVIDIA release OpenCL GPU drivers for Linux and Windows
NVIDIA GeForce GTX 275 at $250 to fight HD 4890