General questions
PH!: Good day! I am Marton Balog from the Hungarian computer website PROHARDVER! First of all, I would like to thank you very much for taking the time and the effort to do this interview.
XGI: Hi Marton, it's my pleasure to conduct this interview with you. My name is Andy Chang and I am the Marketing Director at XGI Technology Inc. It's my honor to represent XGI and to say that we are now one of the top three competitors in the market.
Andy Chang - Marketing Director, XGI
General questions
PH!: please give us a little company brief about XGI. What markets are you targeting, how many engineers are working for XGI, what is your relationship with SiS, what are your main goals?
XGI: XGI was founded in June 1, 2003 and merged Trident's Graphics Division in July 1, 2003. The short term goal of XGI is to focus on delivering high quality graphics products which satisfy the needs of the customers. After the product launch on September 15th, XGI became one of the three top-to-bottom, full product line suppliers in both the mobile graphics and discrete graphics market.
Hirdetés
Today, there are more than 250 engineers working in XGI and the number is rapidly growing. As to the relationship between SiS and XGI, I do have to clarify again that XGI is an indepedant company and SiS is one of XGI's very important investors and owns about 30% of XGI's total shares.
PH!: in what position do you see XGI in a year, on the VGA market? How long product cycles are you targeting for?
XGI: XGI president, Chris Lin has very clearly stated that by the end of 2004, XGI is targeted to grab 5-10% market share in discrete graphics market and we are not planning to reach this goal by cutting prices. We are going to achieve this goal by delivering high quality products which satisfy the true needs of end users.
PH!: Xabre was a highly anticipated product at last years CeBIT, SiS was very enthusiastic about it and presentations were very confident and forward-looking. The final product wasn't bad eigther, but came to market quite late, not with the performance everybody was hoping. Nevertheless, it did help to generate a brand for SiS (XGI, later on). Everyone was looking forward to "Xabre II". Why did you opt for a new brand instead?
XGI: The truth is that the Xabre products and the Xabre brandname is the property of SiS and this is why a new brandname and was created for a newly founded company.
PH!: is the Xabre brand completely abandoned now, or are you planning to use it somewhere?
XGI: I really cannot comment on the future of the Xabre brand because it belongs to SiS and not XGI.
PH!: please describe the VGA market in its current state. Where do you see ATI, nVidia, XGI and S3? What do you think went wrong with nVidia regarding true DirectX 9 performance and how will XGI avoid this pitfall?
XGI: At the current state, I really don't want to comment on our competitors, because the goal of XGI as a company is to deliver high quality products which satisfy the customers' needs. What I can say is that from our past experiences, only a supplier with a complete product line could compete in this very competitive market. This is why we have shown the world that we are serious about this market by launching Volari Duo Series for enthusiasts, Volari V8 Series for High-end, Volari V5 Series for main-stream and Volari V3 for entry level graphics.
PH!: Gabe Newell from Valve gave a quite strict presentation at ATI Shader Day about driver "optimization" done nowadays (mainly targeting nVidia with his critique). What is XGI's stance on this matter?
XGI: Tell me a company whom did not optimize their products! The question shall be - Is it a generic optimization from which the overall performance benefits, or a per benchmark optimization which only accelerates the given benchmark? In XGI, we have limited resources, we could only focus in generic optimization which benefits overall performance.
Technical questions
PH!: would you please explain your multi-chip technology called BitFluent? It seems there should be some sort of order between GPUs, at least at display data path. What about at rendering level, how do you allocate rendering jobs between GPUs?
XGI: For a more in-depth information, you check check on XGITech.com under the product section, there shall be a white paper explaining clearly how it works. Simply put, the two GPU works as follows: The master GPU is connected to the AGP interface and the Slave GPU is connected to the master GPU. Each of the two GPUs has its own local frame buffer, which is what we called DRAM. Basically, the master GPU will process frame 1, 3, 5, ... and slave GPU will process frame 2, 4, 6, ... and so on.
From our studies, this is the most efficient way of putting two GPUs together. The overall efficiency is about 1.7* the performance of one GPU.
XGI Volari V8 Duo
PH!: still BitFluent: how is the GPU's memory access? Each GPU has its own memory area or they can see each others'?
XGI: That's correct, each has one set of a 128 bit wide, indepedent memory bus that it can access for highest efficiency.
PH!: Some 3DMark 2003 scores have been circulating on the web (originating from Anandtech's forum), regarding Volari's performance. They are:
- Volari Duo V8 Ultra - 5600+
- Volari Duo V5 Ultra - 4000+
- Volari V8 Series - 3000+
- Volari V5 Series - 2000+
- Volari V3 Series - 1000+
Can you confirm these numbers? If so, has any driver optimizations been taken for 3DMark 2003? If yes, can they be considered "legal" (meaning: no image quality degradation, no pre-rendering or calculating methods, etc.) techniques?
XGI: As the drivers get more mature, I believe there will be some changes to these performance figures.
XGI Volari V8 Duo
PH!: do you implement bandwidth-saving techniques in Volari-series chips? How effective is BroadBahn, how does it compare to solutions from ATI and nVidia?
XGI: ...
PH!: important question: how much power is needed for these chips? How much is the typical power consumption of the dual-GPU chip/board? Is there an external power connector like on high-end Radeon and Geforce FX cards?
XGI: The typical power consumption is about 70W. Actually there are two external power plugs needed for this board. This is to push the revolutionary 16 pipeline architecture.
PH!: how much is the transistor count, - at least roughly - in V8, V5, V3 respectively? What manufacturing process is XGI using to produce these chips?
XGI: It's based on UMC's 0.13 um process.
XGI Volari V8 Ultra
PH!: we have done several detailed image quality testings with GeForce FX and high-end Radeon cards in regards to FSAA and anisotropic filtering. In the end, ATI's true multi-sampling 6X FSAA was clearly the winner, but anisotropic filtering was also dominated by ATI. Please describe Volari's FSAA and AF techniques and options. Is Volari using pure multi-sampling, or mixed multi- and super-samping FSAA?
XGI: ...
Miscellaneous questions
PH!: there are rumors about your possible product announces: codenamed XG40 chip (aka V8) will be launched at Comdex, together other two products. Is this true? If so, are these two 'others' the V8 Ultra and the V8 Duo?
XGI: XG40 is Volari V8/V8 Ultra. As for other two products, its codenamed XG41 and XG42. I currently do not have a time table on when it will be launched. I will update you on that once I have the information.
PH!: can you give us a brief schedule about Volari-releases? When can we see the V5/Ultra, the V8/Ultra and the Duo boards on the store shelves? Will we see an XG42 (aka V3)?
XGI: I would expect Volari Duo/V8/V5 to reach the shelf around end of Nov or early Dec.
PH!: in what price segments are you targeting the Volari Duo, the V8 and the V5 boards?
XGI: I think I shall not answer the questions for our partners such as Club3D, Gigabyte and PowerColor
Thank you for the interview!
This is it for now. Although the interview was relatively short, we hope it made a good read. Should we have any new information from XGI about the new Volari cards, we shall definitely be there to tell you about it.
Marton Balog / PROHARDVER!
