PowerVR 5?

[Nappe1]

Joke? What joke?

yeah, what joke??

did you know that _xxx_ works for Porsche AG... His duty is check if pac-man hidden as eastern egg in Cayenne Injection System controller unit works correctly.

(couldn't remember any other manufacturers in Stuttgart area. )

 

[_xxx_]

Mercedes!!!

(and I do happen to work there...)

 

[Nappe1]

Mercedes!!!

(and I do happen to work there...)

great!

now I know who to contact when I make my 5th billion Euro. (I have planned to buy original 300SL then. )

 

[Geo]

thop: after Bitboys moved to market where they are now, community needs another "soon here killing the competition with magic touch" company.

I think you tyop'ed there. . s/b "magic tech".

 

[Ailuros]

PowerVR, where's the MBX2?

What is MBX2?

Those who have NDA know, but can't tell. I eventually started to call PowerVR next generation hand held / mobile core as MBX2, though the marketing name eventually would be something else.

I am not quite sure about PowerVR's cycle, but Bitboys have quite clear 12 month cycle between generations:
- In 2003, they presented G10,G20,G30 in late July and announced them available to be licensed.
- before end of 2003, G20 was already dropped from availability.
- In early August 2004 they announced G32,G34 and G40. Again all available to be licensed. G10 dropped.
- again, before year changed to 2005, G30 and G32 vanished from their web pages.

last 2 years Bitboys have been profittable and even right now they have 7 job places open. I don't see any reason at the moment why they would not present 3 next generation cores on this year. To company that visited on very edge in early 2002, situation looks very good right now.


gosh... now I feel like thread hijacker. so, let's foget everything I just said and go back to subject.

I can see the PDA/mobile market moving with the speed of a turtle this far when it comes to 3D. I'm not even sure whether a 12-month or even more aggressive design cycle is actually needed this far. MBX has been licensed by Intel, Sunplus, Samsung, Philips, TI, Sharp, Renesas, Sammy etc and according to the last AGM statement there seems to be another top10 semiconductor committed, not yet announced though. As Loewe pointed out already, products from those partners are for the time being, still quite few.

Only time will tell which marketing strategy benefits each competitor most. So far "serious" competition seems to originate only from the elder continent and ATI/NVIDIA have been also too quiet about their future plans considering that market.

That said IMG isn't dealing with just one core IP or addressing just one specific market. Joint ventures with companies like Frontier Silicon seem more than simply successful lately. Last time I checked the DAB sollution powered by IMG's IP held recently over 70% of the global market share.

 

[Nappe1]

what's the situation of DAB in europe and america anyway? at least in here basically no one listens DAB. it's broadcasted only in very small area and most of average joes have never even heard about it. if I go to near by home electronics store and look for DAB radios, I find zero of them. with asking, I get answer of two, maybe even three models, that could ordered and the price is about double compared to tradional FM RDS, which I can listen in 98% of places, while DAB signal is avaible less than 10% coverage.


if the situation is the same everywhere, no wonder IMG can have 70% of the markets. the market is so small.

 

[Simon F]

what's the situation of DAB in europe and america anyway?

I don't know figures etc, but a quick google turned up http://www.worlddab.org/cstatus.aspx

 

[Dave B(TotalVR)]

Personally, I think series 5 is being held back by a lack of somebody willing to build it into a PC card. I guess they consider it 'high risk'.

Plus they are probably waiting for some kind of standardisation of the unified shader model. Series 5 blatantly has unified shaders IMO.

 

[jvd]

I think the best jumping in point will be with wgf 1.0

If they can get a card out that supports it at the same time or before nvidia/ ati do they can make big waves again

However right now isn't a good time as the r3x0 , r42x tech has stable and fast drivers . Same with the 6800s .

So it would be hard for them to bring new tech into the market right now .

 

[Dave B(TotalVR)]

TBH, the KYRO drivers were alwyas excellent. Never had as many problems (sorry read any) with them as with both Nvidia and ATi.

 

[nAo]

No offence, but IMHO, Kyro drivers..sucked badly

 

[KimB]

TBH, the KYRO drivers were alwyas excellent. Never had as many problems (sorry read any) with them as with both Nvidia and ATi.

I remember hearing that the drivers for the Kyro were very poor for a while after release, though I also remember hearing that by the time the Kyro II rolled around, they were very stable and reliable.

 

[Ailuros]

what's the situation of DAB in europe and america anyway? at least in here basically no one listens DAB. it's broadcasted only in very small area and most of average joes have never even heard about it. if I go to near by home electronics store and look for DAB radios, I find zero of them. with asking, I get answer of two, maybe even three models, that could ordered and the price is about double compared to tradional FM RDS, which I can listen in 98% of places, while DAB signal is avaible less than 10% coverage.


if the situation is the same everywhere, no wonder IMG can have 70% of the markets. the market is so small.

A snippet from Frontier Silicon's PRs:

In digital radio (DAB), the company’s chips are found in the world’s leading brands including Bush, Cambridge Audio, Goodmans, Grundig, Hitachi, Ministry of Sound, Philips, PURE Digital, Roberts Radio, Sharp, Sony and TEAC.

http://www.frontier-silicon.com/news/pressreleases/04_september/MillionChorus.htm

Frontier Silicon was established in 2001, and is privately funded. Key shareholders include Apax Partners and Alta Berkeley, as well as Digital One, operator of one of the world's largest DAB digital radio networks, and Imagination Technologies, a leading supplier of semiconductor intellectual property for the multimedia and communications market.

http://www.eetuk.com/bus/news/showArticle.jhtml?articleID=20900398

The value of the digital radio market is expected to rise from £90m at the end of 2004 to almost £500m by 2008.

http://news.bbc.co.uk/1/hi/entertainment/tv_and_radio/3723138.stm

http://www.frontier-silicon.com/news/pressreleases/04_october/REVOInCarDigitalRadio.htm

http://www.brandrepublic.com/mediabulletin/news_story.cfm?articleID=223216&Origin=MB29092004

Now apart from those you may also add DVT-B based cores like Logie:

http://www.frontier-silicon.com/factsheets/Logie FS5021 Factsheet.pdf

Logie uses IP from all three of IMG's subdivisions (PowerVR/Ensigma/Metagence). Multimedia including TV broadcasting on small embedded devices is already showing up on 3G phones.

70% of the existing DAB market (if the numbers are true) isn't exactly small. If you sell IP for 1M cores for the DAB market alone, then it's still better than nothing.

IMG offers from all the IP companies the widest range of IP for handheld embedded devices. 3D alone isn't going to cut the cake; especially mobile phones constantly incorporate more and more features and I expect to see even GPS functionalities anytime soon (whether they're "useful" is an entire chapter of it's own; consumers obviously want them).

If there's such a thing like "MBX2" there's also obviously "UCC2" and "META2" under development.

 

[Ailuros]

I think the best jumping in point will be with wgf 1.0

If they can get a card out that supports it at the same time or before nvidia/ ati do they can make big waves again

However right now isn't a good time as the r3x0 , r42x tech has stable and fast drivers . Same with the 6800s .

So it would be hard for them to bring new tech into the market right now .

I never thought I'd come to a point to even spell out such a thing, yet I think that by now and with the workload IMG is putting up supporting the markets they already are or plan to expand, it would be wiser to forget making a comeback to the PC graphics market, especially with no potential fabless semiconductor on their side.

After ST M abandoned the graphics market, there must have been negotiations for a cooperation between S3/VIA and IMG/PowerVR, which never worked out for whatever reason. Such a partnership would be interesting in the least, yet presupposition would still be to deliver products to the market in a timely fashion.

Small vendors' chances to penetrate the cut-throat PC gaming market - especially with giants like ATI/NVIDIA - are extremely small. A joint venture between two second tier players might have a much higher potential, especially if a fabless semiconductor is involved. Just my humble opinion and not based on anything possibly being negotiated in the background.

 

[Dave B(TotalVR)]

Normally I would agree Ailuros, but the potential advantage available with PowerVR outweighs that IMO. They hadn't released a card for ages yet when they released the KYRO II it was beating much more expensive cards in many benchmarks - particularly the high detail variety (at the time) like serious sam.

I remember it performing better than a GF2 pro in that game, not bad for a little budget card which had an unusually high profit margin (i.e. they could have sold it cheaper and still amde money).

One day they might just release a card with comparable raw specs as ATi/Nv offerings and wipe the floor with them.

 

[KimB]

Normally I would agree Ailuros, but the potential advantage available with PowerVR outweighs that IMO. They hadn't released a card for ages yet when they released the KYRO II it was beating much more expensive cards in many benchmarks - particularly the high detail variety (at the time) like serious sam.

Okay, two things.
1. They released the Kyro, didn't they?
2. At that time, there were essentially zero memory bandwidth and overdraw reduction techniques in action.

There's no reason to expect that PowerVR can produce a video card that supports modern shaders, is performance-competitive with them, and can produce solid, stable drivers on release.

One day they might just release a card with comparable raw specs as ATi/Nv offerings and wipe the floor with them.

This would be likely if ATI and nVidia currently had nothing more than higher-clocked GeForce 256's with more shader capabilities. Now, not so much.

 

[Scott C]

Well, a PowerVR type GPU would do MSAA for free.
Perhaps 4x or even 8x at the same speed as no MSAA and ATI and NVidia can't keep up with that, bandwidth saving techniques or not.

The bandwidth saving techniques (early z, heirarchical z, and frame buffer compression) still don't outweigh a deferred renderer's advantage of being able to output only at the final resolution, with one write per pixel, even without MSAA enabled, though it is much closer than in the GF2 days.

 

[Ailuros]

There's no reason to expect that PowerVR can produce a video card that supports modern shaders, is performance-competitive with them, and can produce solid, stable drivers on release.

There's no reason to expect otherwise also. Only a real product could eventually tell the true story. Lack thereof, each extreme side of that twisted logic is baseless.

DaveB(TotalVR),

I'm looking at the other segments they're dealing with and in most if not all of them the current IP model is ideal. When it comes to licensing deals in the PDA/mobile market they've swept the floor this far and it's merely just one example.

Not only is the PC graphics market too demanding, an IP business scheme can be called as "weird" at best, but I can see also a much lower potential when it comes to royalty income from it. Compared to the amount of sold units of the MBX family it would be essentially peanuts. Granted the royalty income of one MBX should be miniscule compared to a highly complex PC graphics chip, yet development costs are also higher and thus the margins fall rather in favour of anything MBX.

Somehow I'd say it would be a strange business decision at best to not continue to struggle to keep/further strengthen their position in the PDA/mobile market and divert valuable resources to a highly risky and cut-throat market where they'll not only start from scratch again when it comes to building a brand name, yet would also compete against giants like ATI/NVIDIA.

Last spring I was almost certain it would be ready to roll; I haven't the vaguest idea what or why it never happened, I'm just trying to think what would be the wisest and safest business decision from their perspective. Many proposed in the past IMG to switch to a fabless semiconductor; I still think it's too risky and it would mean that they'd play russian roulette with the existence of the company.

One can always hope of course, but with the market penetration and size of ATI/NVIDIA (and yes that includes resources and what not) I find it extremely hard to believe that any second tier vendor will ever reach that easily to seriously compete with them. Win impressions most likely yes if a product is fast enough; they did win some with the KYRO2 but it was sadly enough "only" a budget/mainstream offering.

A potential third competitor and insert any name you please, would have to have the resources to write up red numbers for a significant amount of time and release in a timely fashion a full top to bottom line of products with at least 6 official driver sets per year. There was one recent attempt last year, which I'm still expecting to become a "market leader".

IMHO I'd rather see a very potential high end offering to win as much impressions as possible from IMG or nothing. We've had mainstream/budget offerings from them before.

 

[KimB]

Well, a PowerVR type GPU would do MSAA for free.
Perhaps 4x or even 8x at the same speed as no MSAA and ATI and NVidia can't keep up with that, bandwidth saving techniques or not.

No. You still get an increase in fillrate requirements at each triangle edge, and the required increase in depth resolution will put more strain on the depth-sorting part of the chip. The performance drop will be based upon different factors than with a traditional renderer, but it probably won't be much different than a modern video card that supports framebuffer compression and has enough video memory that you don't become texture limited once FSAA is turned on.

 

[Xmas]

and the required increase in depth resolution will put more strain on the depth-sorting part of the chip.

What required increase in depth resolution? What depth-sorting part?

Edit: Ah, now I see what you mean. Of course more samples means more Z-checks, but considering Kyro did 32 Z-checks per clock (though not comparable to IMR Z-checks per clock), I think it would be relatively cheap to bump that capability up so it won't be a bottleneck. And even a TBDR could employ hierarchical Z to reduce the required amount of Z testing.