KYRO enhanced T&L

[Roger Kohli]

3D Prophet 4800's new 3D processor offers a remarkable assortment of the most up-to-date graphics technology features for key 3D effects in the latest applications. 3D Prophet 4800 stands out with its unmatched enhanced Transform And Lighting technology engine which has been specifically designed by PowerVR for the new generation of KYROII chipsets. It mixes intelligent 3D and CPU resources applied to Transform & Lighting and enables the 3D processing to calculate in real time how light intensity will vary on surfaces, where shadows are positioned in 3D applications. These operations guarantee more realistic scenes without increasing CPU resources overload, which maximizes the frame rates in games. The enhanced T&L engine proves to be up to 15% faster than standard engines in games where T&L causes a bottleneck.

[Kristof]

Lets add a link to the PR

http://europe.hercules.com/mediaroom/press/3dp4800.php

K-

[Roger Kohli]

These operations guarantee more realistic scenes without increasing CPU resources overload

Does this suggest hardware T&L?

[PVR_Extremist]

From the Videologic website for the new Vivid!XS Elite

EnT&L™
To deliver optimal cost-performance KYRO II SE supports the new EnT&L driver technology which unites the advanced features of KYRO II SE with transform and lighting to provide superior performance to cost comparable solutions. EnT&L is optimized for KYRO II SE AGP 4X SBA operation and Implicit Guard Band Clipping.


Doesnt sound like Hardware T&L to me. The rumours sadly were correct. A K2 overclocked to 200Mhz with driver optimisations. I'll pass on judgement when we see some real figures but I'm a little let down by this offering

:cry:

[Lefungus]

Now i hope these drivers can also do their "magic" on older kyro versions

[mboeller]

It seems, the price for the most missleading press-release goes to Videologic and Hercules.

Old wine in an new hose ....

eT&L = only lightning gets an boost (maybe they use the DOT3-unit)

Smarter Rendering Technology = joke (even the old chips had this, it's the base of the PVR-technology)

Textur8 = new word for an KyroI feature

TrueRender™ OnChip FSAA = same here

Bump Map Complete = same here

Internal True Colour = same here ( hyping the same old feature the KyroI already had )


The hercules press-release even suggest that the Kyro is an DX8.1 chip!!!


I'm really really disappointed, even more with the press-release than with the chip itself. :( :(


Manfred

[CMcK]

The two PR's seem to take a different stance. The Herc PR makes it sound like there is HW T&L but the VDO PR suggests driver enhancements.

Is the Kyro II SE actually a new chip? The Herc blurb mentions 'the new generation of Kyro II chipsets'. Did the previous Kyro II chip support AGP 4x and SBA as mentioned above? Was this a feature left disabled by the drivers? The Prophet 4500 I own only supports up to AGP 2x and does not work with SBA either.

I am sort of dissapointed by this news this morning as I was intending to buy a Prophet 4800 when I build my new P4 DDR system next month.

[Ailuros]

I'll have to agree with mboeller on the naming/marketing stuff. I considered ATI's/NVIDIA's feature naming schemes already stupid, they just seem to follow that trend.

After Quincunx, Lightspeed, nFinite, Smoothvision, Smartshader etc etc now this. Bad thing about is the terms don't even offer much room to make fun of them like I used to do with other ones in the past.

I guess I could say though that this is the KYRO RnF(tm) (revamp nFinite) ;)

[Mephisto]

Manfred, this is ordinary marketing, they're just cloning Nvidia!

Aside from this, while Imgtec introduces a software emulation for hardwired TNL, Nvidia already has one for vertex shaders 1.1.

[Dave Baumann]

Is the Kyro II SE actually a new chip? The Herc blurb mentions 'the new generation of Kyro II chipsets'.

It might be worth peeling the heatsink off one. You might find that its just a newer revision of KYROII with a few buggies sorted out (AGP4X?) and a few speed opimisations.

Although the moniker 'STG4800' may suggest more work than a simple respin.

[Randell]

All PR on all cards suggest they are DX8.1 chips. Look at Gf3 and Gf4 PR. Joe Public doesnt know the differnce between 'tech' definitions of 8.0 and 8.1 and compatible/compliant.

Any company would be foolish to highlight on PR 'compliance' when all that matters to sales is compatibility.

[mboeller]

Manfred, this is ordinary marketing, they're just cloning Nvidia!

Aside from this, while Imgtec introduces a software emulation for hardwired TNL, Nvidia already has one for vertex shaders 1.1.


Yea;

BUT Nvidia normaly beefs up the marketing crap with something really new or enhanced (except maybe the new AccuviewAA). Here we have an press-release with new marketing terms and age-old features. Most (if not all) of them where already in the KyroI and they didn't even have improved the features. I imagine that even the eT&L will work with KyroI-cards (maybe renamed with an registry hack). Thats ... :evil: :x :( :(

I suppose tomorrow most of the Internet-community interested in 3D / graphics will laugh at them really hard! "See how long it took them to improve the drivers and increase the speed a mere 25MHz" WOW, that sucks.

I really hope they show the new STG 5500 too (but not behind closed doors only), otherwise they are lost.


Manfred

[Dave Baumann]

I really hope they show the new STG 5500 too (but not behind closed doors only), otherwise they are lost.

Remember, they are in a slightly transitionary period at the moment - I think the best to hope for is an announcement on whether someone has taken over STM graphics; if that occurs then we can start talking about newer products...

[Randell]

[quote=Mephisto]BUT Nvidia normaly beefs up the marketing crap with something really new or enhanced (except maybe the new AccuviewAA). Here we have an press-release with new marketing terms and age-old features. Most (if not all) of them where already in the KyroI and they didn't even have improved the features. I imagine that even the eT&L will work with KyroI-cards (maybe renamed with an registry hack). Thats ... :evil: :x :( :(

Manfred
hmm replace Kyro with Gf3 and Gf3ti and I dont see a difference compared with last years autumn 'refesh' :wink:

[Armunn]

So, is the new enT&L a hardware solution or is it just a software solution?
Either way can someone explain how it will work and appear to programs that support HW T&L? ie. If it is a software solution will it appear as HW T&L to programs such as Max Payne etc?

Also if its only software will it be enabled for earlier Kyro's?

[ronaldo]

EnT&L
To deliver optimal cost-performance KYRO II SE supports the new EnT&L driver technology which unites the advanced features of KYRO II SE with transform and lighting to provide superior performance to cost comparable solutions. EnT&L is optimized for KYRO II SE AGP 4X SBA operation and Implicit Guard Band Clipping.



"EnT&L is optimized for.....Implicit Guard Band Clipping."

Does this mean guard band clipping is enabled whether or not the application enables it? And, do game coders check for this, or do they just assume that if a card lacks full hardware T&L it will not have this feature also?

[darkblu]

EnT&L is optimized for KYRO II SE AGP 4X SBA operation and Implicit Guard Band Clipping

hmm, i wonder what would 'implicit' exactly mean in this case... wouldn't excessive use of guardBand clipping impose too much of a performance hit? how good is the Kyro at that? any first-hand impressions? .. Simon, Kristoff?..

[LittlePenny]

So it is no GeForce 4 killer, we all knew that when Kristof showed us the box entitled 4800. I think some of you are also forgetting how lame the GeForce4MX is, in my opinion eT&L whether it is hardware or not, is going to have advantages over the MX.

Bottom line we want a 3rd party in the high-end, but PVR chose to stay low-end for now. It is better than nothing, and try not to look a gift horse in the mouth.

[Joe DeFuria]

Anyone know the price of the 4800?

[mat]

in austria the retail is 137,34€ (http://www.geizhals.at/?cat=gra64&a=28227), the bulk 121€ (http://www.geizhals.at/?cat=gra64&a=28226)

[Kristof]

EnT&L is optimized for KYRO II SE AGP 4X SBA operation and Implicit Guard Band Clipping

hmm, i wonder what would 'implicit' exactly mean in this case... wouldn't excessive use of guardBand clipping impose too much of a performance hit? how good is the Kyro at that? any first-hand impressions? .. Simon, Kristoff?..

IIRC guardband clipping is part of the tile binning which is done in hardware and thus for free.

K-

[Tompa]

About 120$ / 106$....

/ Tompa

[Gubbi]

"EnT&L is optimized for.....Implicit Guard Band Clipping."

Does this mean guard band clipping is enabled whether or not the application enables it? And, do game coders check for this, or do they just assume that if a card lacks full hardware T&L it will not have this feature also?

I would guess, that the drivers "fake" hardware T&L. Guard Band Clipping is then implicitly done.

Cheers
Gubbi

[darkblu]

EnT&L is optimized for KYRO II SE AGP 4X SBA operation and Implicit Guard Band Clipping

hmm, i wonder what would 'implicit' exactly mean in this case... wouldn't excessive use of guardBand clipping impose too much of a performance hit? how good is the Kyro at that? any first-hand impressions? .. Simon, Kristoff?..

IIRC guardband clipping is part of the tile binning which is done in hardware and thus for free.

K-

silly me! of course. sorry for the waste of forum bandwidth.

[Joe DeFuria]

About 120$ / 106$....

OK, so that should put it in competition with the following products (in the U.S. at least). Pricewatch prices:

Radeon 7500, 64 MB, TV Out, Retail: $80
GF4MX 440, 64 MB TV Out: $90
GeForce3 Ti-200, 64 MB, TV Out, $125
Radeon 8500 LE, 64 MB, TV out, $140

Will be interesting to see the benchmarks. This is a very competitive price range!

[Dave Baumann]

Joe - the converstations have been had numerous times here; US and European prices rarely come close to each other!

[Teasy]

OK, so that should put it in competition with the following products (in the U.S. at least). Pricewatch prices:

Your taking recommended prices and putting them up against actual prices, the Hercules Kyro II 4500 is still $100 recommended but on pricewatch its $50, expect the same sort of thing from the 4800.

[Joe DeFuria]

Your taking recommended prices and putting them up against actual prices....the Hercules Kyro II 4500 is still $100 recommended but on pricewatch its $50, expect the same sort of thing from the 4800.

Has any new Kyro part even been debuted at $50? Do you think that maybe the 4500 prices are considerably lower to make room for the 4800? Is Hercules discontinuing the 4500 and replacing it with the 4800, or are the complimentary products? (Honest questions...)

Also, nobody said anything about those prices quoted to me being recommended or expected street. No source was provided...only one set of prices for UK (Euro), and one set of prices for U.S. No further clarification was given.

That is why I gave a wide range of competing products with price points from $80 to $140. Surely, the 4800 will fit somewhere in there?

Joe - the converstations have been had numerous times here; US and European prices rarely come close to each other!

Which is specifically why I mentioned "in the U.S. at least" in my price lists. :-?

It would help if there were some refernces given for the prices that were quoted for the 4800. Did these come from Hercules? Did they come off of some search engine? Are they just rumored?

I'm not looking to stir anything up here...just looking for facts. :)

[Tompa]

ok sorry I just transfered the prices to US$ that came via the link mat gave, a quick search here in Sweden for the other boards are:

Radeon 7500, 64 MB, TV Out, Retail:$144
GF4MX 440, 64 MB TV Out: $151
GeForce3 Ti-200, 64 MB, TV Out, $192
Radeon 8500 LE, 64 MB, TV out, $211


...so quite a different...(these are then ofcourse with HUGE swedish tax = take off 20% and its taxfree)

// Tompa

[Mephisto]

KYRO II was a good copetitor for GTS/Radeon/MX400 cards. But the KYRO II SE isn't competitive anymore.

KYRO II is 14% faster (both, mem and core). But the competition in this segment gained more! Geforce4 MX has 20% more memory bandwith than a GTS as well as bandwith saving features, which makes at least a 40% increase over the GTS. Radeon 7500 has a 60% fillrate increase and a 25% bandwith increase over the original Radeon. Today, a gamer shouldn't buy anything slower than a R7500 or a GF4MX. The SE also lacks dualhead technology, which makes it even less attractive.

[Joe DeFuria]

Just to brush up on my Kyro specs:

KyroII 4500: Core and Mem at 175 Mhz
KyroII 4800: Core and Mem at 200 Mhz

Is that correct?

On pricing:

I didn't notice that the Austrian prices were actually links to what I assume is a search engine? So in Austria at least, it appears the 4800 falls somewhere between the Radeon 7200 and 7500 in price. And it also falls just below the GeForce MX440 in price.

Will Beyond3D be reviewing the 4800?

[Dave Baumann]

Marco may well get one from Hercules. I'll see if David Harold is predisposed to giving me an Vivid!XS Elite to play around with once he gets back from CeBit.

[Teasy]

Has any new Kyro part even been debuted at $50?

No, Kyro II was supposed to be $150 reccomened and was actually sold at $110 AFAIR, then within a few months it dropped to $90, then quickly to $80 and so on. But I think STM realise that this chip is not a big improvement over Kyro II like Kyro II was over Kyro I and so they can't sell it for a great deal more, I certainly know these cards will not actually sell for $120, nowhwere near.

Also, nobody said anything about those prices quoted to me being recommended or expected street. No source was provided...only one set of prices for UK (Euro), and one set of prices for U.S. No further clarification was given.

Oh ok I wasn't aware of that, I assumed you knew they were reccomened prices.[/quote]

[dksuiko]

Even if it sells at $100, it's still near the price of Gainward's GeForce 3 Ti200 (Or, as Gainward calls it, Ti450) which is $145. Just save up an extra $45 and grab that. 4ns memory and you can overclock it to Ti500 levels. So, why get this when you can get Ti500 level performance for only a bit more?

None that I can see.

[Typedef Enum]

Honestly...

If you buy this thing over a Ti200, you just *must* want to buy anything other than nVidia...This seems like a product without a market.

Please...don't try and suggest that it's all about the low-end, because I have no doubt that it will end up getting smoked in virtually every single aspect by the competition's low-end products (be it sales, performance, features, etc.)

Of course, the absolute kicker is the following...

http://www.voodooextreme.com/#26891

"KyroII SE w/ T&L 6:17 PM - Duane "Cp" Pemberton"

[Ailuros]

Typedef,

When I first heard last year about the 4800 I thought it was a stupid idea back then as today.

I'm not so sure though if your statement can be justified to it's full extend if someone takes MX420's or R7200's or lower into account. Especially when I look at the price/performance ratios of those and the "feature list" of the NV17.

Last year Fu claimed that the reason for the 4800 release would be to yield better OEM deals. While I could have seen some usefullness for that last August, I find it rather tough to believe in today's terms.

Today it rather looks to me as some kind of reminder that they're still around or something like that and hopefully (if I take Fu's old interview as accurate) it should mark a 5500 release "in a couple of months".

Still I'd like to see a 4800 properly reviewed, those ace's "overclocked K2" numbers don't seem to match up. If it's all there really is than it's even a bigger disappointment than I could have imagined.

[mboeller]

Typedef,

When I first heard last year about the 4800 I thought it was a stupid idea back then as today.
...
...
Today it rather looks to me as some kind of reminder that they're still around or something like that and hopefully (if I take Fu's old interview as accurate) it should mark a 5500 release "in a couple of months".


What do You mean with "in a couple of months"

Does this "couple of months" start at the original release timeframe (09/01) or do they start now (03/02)

[Ailuros]

I would guestimate a "couple of months" after the release. Currently we have just an announcement.

Anything beyond the end of this spring would be too late. I'm really curious if VIA will be able to push the envelope as it should.

First I guess we'll have to await VIA's formal announcement in about 2 hours from now, although PR stuff doesn't tell always the real story.

[mboeller]

Eek..

I had hoped you ment "a couple of months after Sept. 01"

This brings the release-date of the STG5500 near the timeframe Joe DeFuria mentioned (Sept 02).
I really hope the STG5500 is an DX8-compliant chip then, otherwise they get smoked.

[Ailuros]

A couple in my definition means two (2) not more.

By the way I thought spring ends in Germany around the same time as here? hehehehe ;)

[Joe DeFuria]

Typedef,

If you buy this thing over a Ti200, you just *must* want to buy anything other than nVidia...This seems like a product without a market.

I agree and disagree. First for some assumptions to set the tone for the rest of this post, which may or may not turn out to be accurate, but are my best guess based on what we know:

1) K2SE is priced a little below the GeForce4 MX 440 and Radeon 7500 levels.
2) K2SE performs a little below those cards as well.

Now, let's get your nVidia-centric thing out of the way. ;) If we assume the street price of the K2SE is within $50 of the Ti-200 AND Radeon 8500, (like the MX 440/460 is) then I would say for a GAMER, the K2SE is not interesting at all. It's not a case of not wanting to buy nVidia, it's a case of wanting to get the best performance / features for the dollar, at a reasonable absolute price.

Note that this also means, that the nVidia GeForce4 MX 440, and certainly the MX 460 are also "products without a market" by your definition.

I basically consider all cards within the price of one game (about $50 U.S.) to be in "competition" for the gamer's dollar. So I do agree that any gamer should find a way to come up with $50 to "step up" to a Radeon 8500 or Ti-200. Sacrifice the purchase of one game, to get a better overall experience with the games you do buy.

But there obviously is a "market" for the K2SE, just as there is a market for the GeForce4 MX. IMO, though, that isn't a market for most gamers. :(

[mboeller]

A couple in my definition means two (2) not more.

By the way I thought spring ends in Germany around the same time as here? hehehehe ;)


Ahh.. I see.

Well my englisch seems not good enough. I translated couple = a few (the dictionary says the same!); and so with the "IMG delays everything" in mind I thought march + 3-5 ( = a couple ) + 2-3 (IMG delay(TM) ) = I got september as the earlist date. :wink:

[Teasy]

Well my englisch seems not good enough. I translated couple = a few (the dictionary says the same!

Yeah thats the informal meaning for a couple but when being strictly accurate a couple means two.

[Joe DeFuria]

For those interested, here's the "Fu Interview" that's being talked about:

http://www.extremetech.com/article/0,2299,s%253D201%2526a%253D2529,00.asp

At the time, June 2001, it was expected that the 4800 would be out "in a couple months." That has turned out to be close to a year. (We're at 10 months now, and the product is not on the shelves yet.)

At the time, he also anticipated the 5500 (Kyro III), to be out by the end of 2001. If we delay that launch by the same amount of time the 4500 was delayed (10 months), that would but the KyroIII out this fall...September. Certainly, that method of estimation is crude. ;)

It's also interesting that spec wise, the 4800 was exactly what he said it would be back in June: 200 Mhz respin of the 4500. So perhaps we can do the same with the KyroIII:

0.13 micron
"3 times" the performance of the "4000" series.
4 pixel pipelines
250 Mhz
Hardware T&L, no mention of "programmable" T&L. (Hints to DX7 compliant part.)
Max of 64 MB DDRAM

Price wise, if this part were to be released today, this part should probably be somewhere around Readon 8500 and GeForce Ti-200 levels: $150 or so U.S.

Performance wise? My guess would be somewhere between a Ti-200 and Ti-500. (Based on a quick look at KyroII benchmarks at fill-rate limited situations over at Anandtech...) That would still be a hard sell for this part if the Kyro lacks DX8 pixel shaders.

[Dave Baumann]

Performance wise? My guess would be somewhere between a Ti-200 and Ti-500. (Based on a quick look at KyroII benchmarks at fill-rate limited situations over at Anandtech...) That would still be a hard sell for this part if the Kyro lacks DX8 pixel shaders.

Probably not.

Most likely KYROIII will be going against the GF4 MX's and Radeon 7500's of this world, both of which are DX7 compliant thmselves. They all may have a tougher time against the lower end DX8 cards of Radeon 8500LE and GF4 Ti4200's (remembering that Ti200's are likely to be phased out once stocks die down).

[king_iron_fist]

Does anyone know what's happening over at cebit at the moment?

BTW I think the kyroIII would be at least GF4ti levels. The sustained fillrate would be over 1000Mpixels which is more than a GF4 and it would be backed up by a very fast T&l engine.

I'm determined to make this card my next upgrade.

[Dave B(TotalVR)]

Price wise, if this part were to be released today, this part should probably be somewhere around Readon 8500 and GeForce Ti-500 levels: $150 or so U.S.


Price wise yeah.

Performance wise? My guess would be somewhere between a Ti-200 and Ti-500. (Based on a quick look at KyroII benchmarks at fill-rate limited situations over at Anandtech...)


Its not just gonna be a 4 piped 250Mhz KYRO II y'know. :wink:

That would still be a hard sell for this part if the Kyro lacks DX8 pixel shaders.

Unless of course it were to come with some frivelous and useless feature such as totally free full scene anti-aliasing or something equally as irrelevant as that. :roll:

As for you crude estimation of a september release for the KYRO III, well its rediculous to assume that because the KYRO II SE was delayed 10 months (not that it was ever officially announced before yesterday) that the KYRO III will be. If the KYRO III were to come out in 10 months then it would be another budget card and I dont think thats what Via wants, do you? its just as likely that they held back the KYRO II SE because the K2 was selling so well and concentrated their work on the KYRO III, in fact I would say its a site more likely.

Dave

[Joe DeFuria]

Most likely KYROIII will be going against the GF4 MX's and Radeon 7500's of this world, both of which are DX7 compliant thmselves.

Feature wise, yes, the KyroIII would be best matched against those parts. But price wise, I'm betting on closer to the Radeon 8500/Ti-200. Mostly because of the memory interface, which AFAIK, still dictates the majority of the cost of these products. Here's a snippet of all the current, relevant chips:

KRYO III: 250 Mhz DDR
Readon 8500: 275 Mhz DDR
Radeon 8500 LE: 250 Mhz DDR
Radeon 7500: 230 Mhz DDR
GF4-MX 460: 275 Mhz DDR
GF4-MX 440: 200 Mhz DDR
GF3-TI-200: 200 Mhz DDR
GF3-TI-500: 250 Mhz DDR

Chip complexity is another cost factor of course, and I'd guess a 4 pixel pipe, DX7 style Kyro chip will sit somewhere between the complexity of the 2 pixel pipe competing DX7 chips, and the 4 pixel pipe DX8 chips.

So looking at all those numbers, I'd say the price should come somewhere about a Radeon 8500 LE, or TI-200.

all may have a tougher time against the lower end DX8 cards of Radeon 8500LE and GF4 Ti4200's

Agreed...at least for the gaming market. Once the DX8 cards hit the $150 barrier, it becomes hard to justify a similarly performing DX7 card if there's less than $50 or so price difference.

remembering that Ti200's are likely to be phased out once stocks die down).

That's a good point. Of course, it's being phased out to introduce the better performing Ti-4200 with MSRP of $199...and who knows where the street price will settle at by the time KyroIII is released....

[Teasy]

At the time, he also anticipated the 5500 (Kyro III), to be out by the end of 2001.

Actually AFAIR he said late 2001 or early 2002.

that method of estimation is crude.

Yep because the release of a product does not have to be based on when nother product is released. The estimated release of late 2001 to early 2002 was unlikely to be like that as to be a certain amount of time after Kyro IISE. It's more likely estimated at that time simply because that's when they expected the chip to be ready (possibly thats when they expected TSMC's 0.13 micron to be finalized). Also the company making those announcements will no longer be residing over the launch of Kyro III so all of what he said pretty much goes out of the window when trying to figure out when Kyro III will be out.

It's also interesting that spec wise, the 4800 was exactly what he said it would be back in June: 200 Mhz respin of the 4500. So perhaps we can do the same with the KyroIII:


0.13 micron

"3 times" the performance of the "4000" series.

4 pixel pipelines

250 Mhz

Hardware T&L, no mention of "programmable" T&L. (Hints to DX7 compliant part.)

Max of 64 MB DDRAM

The "3 times" the performance of the "4000" series is not really valid considerin FU also mentioned that Kyro II was around the performance of a Geforce 2 MX instead of a Geforce 2 GTS as it actually is. Also the specs suggest 4-5 times the performance of 4000 when looking at pure bandwidth/fillrate without considering any other optimisations and features like HW T&L and possibly free AA. I think FU probably meant 3 times the performance of the 4500 series which would make sense when looking at pure specs.

Price wise, if this part were to be released today, this part should probably be somewhere around Readon 8500 and GeForce Ti-500 levels: $150 or so U.S.

A DX7 chip with static HW T&L and 4 pixel pipes, a normal single 128bit DDR bus and 250mhz ram on 0.13 micron.. I don't see why that should be the same price as a Radeon 8500 which has pixel shaders and vertex shaders on a larger process as well as an expensive segmented memory bus. IMO its very unlikely to sell for $150 online. Its reccomended price will be $150 AFAIK (thats according to IMGTEC), meaning actual online prices of more like $120 or less are likely.

[Joe DeFuria]

Its not just gonna be a 4 piped 250Mhz KYRO II y'know.

I know...but the performance estimate according to Fu is "3X" that of the 4000 series. That's what I based my estimation on.

Unless of course it were to come with some frivelous and useless feature such as totally free full scene anti-aliasing or something equally as irrelevant as that.

That's a good point. Something we've been asking the PowerVR team for since, well, forever. ;)

As for you crude estimation of a september release for the KYRO III, well its rediculous to assume that because the KYRO II SE was delayed 10 months (not that it was ever officially announced before yesterday) that the KYRO III will be.

Yeah, it's about as rediculous to estimate a March / April release of the Kyro II SE when Fu said it would be a "couple months" from June, right? :roll:

I would wager that if the KIII was "ready for the shelves" a couple months from now, it would have been debuted at CeBit, along with the 4800.

In any case, if you want a more "based" reason for the September estimate, I'll repeat what I've said since the beginning: all the chip makers seem to have trouble getting a 0.13 part out this spring, and appear to have pushed 0.13 products out to the fall.

If the KYRO III were to come out in 10 months then it would be another budget card and I dont think thats what Via wants, do you?

Is that what STM wanted for the 4800? What a company "wants" is not always what they get. Did STM "want" the 4800 coming out this year in April? It's now "just another budget card".

its just as likely that they held back the KYRO II SE because the K2 was selling so well and concentrated their work on the KYRO III, in fact I would say its a site more likely.

Heh...well, you believe what you want....I don't know why on one hand you say Via "doesn't want just another budget card", and then on the other, you feel it's "likely" that STM "delayed" the KIISE to put it exactly in that position...

[Dave Baumann]

Chip complexity is another cost factor of course, and I'd guess a 4 pixel pipe, DX7 style Kyro chip will sit somewhere between the complexity of the 2 pixel pipe competing DX7 chips, and the 4 pixel pipe DX8 chips.

The effect on price that 'chip complexity' has is usually down to wafer size, in which case the process factors in largely. If KYROIII is .13um then it will have a wafer (per transitor required!) advantage over all the current chips .

Also, despite GF4MX 'only' having two pipes the new AA and other factors increase its complexity quite considerably.

[Teasy]

Feature wise, yes, the KyroIII would be best matched against those parts. But price wise, I'm betting on closer to the Radeon 8500/Ti-200. Mostly because of the memory interface, which AFAIK, still dictates the majority of the cost of these products. Here's a snippet of all the current, relevant chips:

Your forgetting that all those other chips have segmented memory buses which is more expensive then a single bus.

Chip complexity is another cost factor of course, and I'd guess a 4 pixel pipe, DX7 style Kyro chip will sit somewhere between the complexity of the 2 pixel pipe competing DX7 chips, and the 4 pixel pipe DX8 chips.

Kyro was 12 million transistors, I'd be suprised if Kyro III was anything over 25-30 million transistors, all the chips you mentioned thier are in the 40-50 million transistor range (appart from the Geforce 4 MX which is cheap and DX7 anyway) and are on larger processes then Kyro III. Plus IMGTEC have already given a reccomended price of $150, which means less then $150 online at release.

[Joe DeFuria]

The effect on price that chip complexity has is usually down to wafer size, in which case the process factors in largely. If KYROIII is .13um then it will have a wafer (per transitor required!) advantage over all the current chips .

And who's to say that by the time Kyro III is released, that nVidia / ATI won't have 0.13 micron variants of their value parts as well? Isn't that something that they traditionally do?

Problem is, we're comparing "future" Kyro, with "present" ATI/nVidia ones. It's not really valid to consider the costs related to the fab process of a chip that already on the market, with one that is yet to materialize. You would be right if the KyroIII was shipping today.

Also, despite GF4MX only; having two pipes the new AA and other factors increase its complexity quite considerably.

And we know nothing of any "other" features of KryoIII that could increase it's complexity considerably compared to the KyroII. What would "free FSAA" cost in complexity, if implemented? Will they add dual-head support? Alter their memory interface?

[Joe DeFuria]

Your forgetting that all those other chips have segmented memory buses which is more expensive then a single bus.

True, but do we know that KyroIII doesn't have a segmented bus?

all the chips you mentioned thier are in the 40-50 million transistor range (appart from the Geforce 4 MX which is cheap and DX7 anyway)

Well, isn't that what KyroIII is suppossed to be? "Cheap DX7"? Thing is, the most expensive of the "cheap DX7" (MX 460) parts are very close in price to the cheapest of the most expensive DX8 parts.

So it comes down to this -- do you think KyroIII will be priced on par with the "cheap" DX7 parts, or the "most expensive" DX7 parts?

Plus IMGTEC have already given a reccomended price of $150, which means less then $150 online at release.

Again, the key question is WHEN? Even if it's $100 street , if it comes out in september, who knows what the lanscape will be when we currently have sub $150 DX8 cards...TODAY.

[Dave Baumann]

And who's to say that by the time Kyro III is released, that nVidia / ATI won't have 0.13 micron variants of their value parts as well? Isn't that something that they traditionally do?

Thus far NVIDIA haven't done that with the lower end variants - they have in terms of process, but not in terms of product. The 'MX' product lasted in excess of a year and one whole generation for GF2; personally I don't see NVIDIA releasing another MX class product until the second generation of NV30 type products, probably on .10um/.09um. ATi may well have pushed R200 down to .13um but then I'd still expect that to be considerably more complex as well.

What would "free FSAA" cost in complexity, if implemented? Will they add dual-head support

Considering they have levered free FSAA into the low cost / complexity model such as MBX I'd guess not a lot! Remember, NVIDIA are basically using more die space for FSAA to save bandwidth by doing more AA operations on chip; the very nature of PowerVR's architecture already has this one solved.

[Teasy]

And we know nothing of any "other" features of KryoIII that could increase it's complexity considerably compared to the KyroII. What would "free FSAA" cost in complexity, if implemented?

I wouldn't think it would be much, it should basically be MSAA. As for other features.. hmm, well thier will be cube mapping I suppose, but again this shouldn't up complexity very much.

Will they add dual-head support?

Unlikely

Alter their memory interface?

No, a single 128bit DDR bus is what I'd expect.

I'd say when you take Kyro III's specs into account it should be no more complex transistor wise then Geforce 4 MX (less IMO) and considerably less complex then the other chips you mentioned, put that together with a less complex memory bus and you have a cheaper product. $150 reccomended is likely to be its price and that is a long way below a Radeon 8500's recommended price or a Geforce 3's recommended price.

True, but do we know that KyroIII doesn't have a segmented bus?

It wasn't mentioned by fu what bus config it has, but then if it was segmented I'd expect it to be mentioned, after all he's not going to give a spec that says "not a segmented bus" is he. Also considering a tilers bandwidth advantages its unlikely to be top of their list of needed features.

Well, isn't that what KyroIII is suppossed to be? "Cheap DX7"?

that's a fair assumption yes, but its likely to have the feature set of a Geforce 4 MX 460 at a slightly cheaper price (no need for the bandwidth saving tech or complex AA or segmented bus, with slower ram of 250mhz rather then 275mhz and on a smaller process) and much faster.

So it comes down to this -- do you think KyroIII will be priced on par with the "cheap" DX7 parts, or the "most expensive" DX7 parts?

I think it'll be a little cheaper then the most expensive DX7 parts and a whole lot faster, especially with free AA (if implimented).

Again, the key question is WHEN? Even if it's $100 street , if it comes out in september , who knows what the lanscape will be when we currently have sub $150 DX8 cards...TODAY.

Even if its released at a time when Geforce 4 and Radeon 8500 are on 0.13 micron (if that happens anyway, it certainly won't happen for Geforce 3) then it still looks to have a price advantage transistor and mem wise over those chips and so could be sold cheaper if needed.

[Dave Baumann]

Will they add dual-head support?Unlikely

IIRC the block diagram of series 4 showed two RAMDAC's.

[Joe DeFuria]

Teasy,

The "3 times" the performance of the "4000" series is not really valid...

I think ther's just confusion about my use of the "4000 series". I do not mean the STG 4000 part, as I don't think that's what Fu meant. I mean the 4XXX series of cards...4000, 4500, 4800. For my performance estimate (somewhere between the Ti-200 and Ti-500) I used 3X FPS of the 4500 that Anand used in his benchmarks.

[Joe DeFuria]

$150 reccomended is likely to be its price and that is a long way below a Radeon 8500's recommended price or a Geforce 3's recommended price.

Again...right now. I don't expect the graphics landscape to stand still while waiting for the KyroIII release. ;)

Thus far NVIDIA haven't done that with the lower end variants - they have in terms of process, but not in terms of product.

Not sure what you mean by that. nVidia has reduced the process size of the GeForce2 MX. They used to just have one "MX" part, then they went to a new fab and had 2 new GeForce2 MX parts (MX 200 and MX 400). I think it was the same time they introduced the GeForce2 Pro, (Die shrink of GeForce2 GTS) but I'm not sure.

[Dave Baumann]

I'm saying the missed out entire generations of their low end product - the original MX didn't occur until after the high end was refreshed to GeForce 2, and the current MX product missed out a the entire GeForce3 line - which I why I don't see them introducing another low (low) end prodct for some time.

[Teasy]

IIRC the block diagram of series 4 showed two RAMDAC's

Ah yeah I forgot about that.

I think ther's just confusion about my use of the "4000 series". I do not mean the STG 4000 part, as I don't think that's what Fu meant. I mean the 4XXX series of cards...4000, 4500, 4800. For my performance estimate (somewhere between the Ti-200 and Ti-500) I used 3X FPS of the 4500 that Anand used in his benchmarks.

Ah ok, in that case I agree with you more or less. Obviously their could be other speed improvements like free trilinear that would make it more then 3 times as fast as Kyro II (if the Kyro II benches you were looking at used true trilinear) as well as cheaper aniso and possibly free AA, but considering we don't know about that for sure yet 3 times as fast as Kyro II is a fair assumption.

Again... right now . I don't expect the graphics landscape to stand still while waiting for the KyroIII release.

All I'm talking about is right now though, in that quote anyway, I'm just saying that IMO your wrong in your assumption of a $150 price tag.

[Joe DeFuria]

I think it'll be a little cheaper then the most expensive DX7 parts and a whole lot faster, especially with free AA (if implimented).

Well, even if that turns out to be the case, this is where I see the difficulty in selling this part. (Ignoring "Free AA" for the moment...that would indeed be a nice selling point.)

The cheapest DX8 parts are as fast (some cases faster, some slower) than the current most expensive DX7 parts...PLUS they have DX8 shaders. So if we are talking about $50 or so for a difference in price, would you rather have a super-fast DX7 part like the KyroIII, or perhaps a part that might or might not be quite as fast in DX7 (like a Radeon 8500/ GeForce3 ti), but also supports DX8?

That can be a tough decision to make...and I suspect one big factor will end up being how well KyroIII can handle Doom3...

[Dave Baumann]

That can be a tough decision to make...and I suspect one big factor will end up being how well KyroIII can handle Doom3...

It may do it quite well - I believe that PowerVR is the only one that can remove stencil overdraw, IIRC other methods can't (someone correct me if thats not the case!).

[Teasy]

The cheapest DX8 parts are also faster than the most expensive DX7 parts...PLUS they have DX8 shaders. So if we are talking about $50 or so for a difference in price, would you rather have a super-fast DX7 part like the KyroIII, or perhaps a part that might or might not be quite as fast in DX7 (like a Radeon 8500/ GeForce3 ti), but also supports DX8?

I suppose we'll just have to wait for real benches and prices for Kyro III when its released and see how it stacks up to other cards on release.

[Joe DeFuria]

I suppose we'll just have to wait for real benches and prices for Kyro III when its released and see how it stacks up to other cards on release.

Yeah...we should really at least wait unti the part is officially announced, with specs, release date, etc....But then, that's takes all the fun out of wild speculation. ;)

[relativity]

Kyro was 12 million transistors, I'd be suprised if Kyro III was anything over 25-30 million transistors, all the chips you mentioned thier are in the 40-50 million transistor range (appart from the Geforce 4 MX which is cheap and DX7 anyway) and are on larger processes then Kyro III. Plus IMGTEC have already given a reccomended price of $150, which means less then $150 online at release.

Now I know, you know little about KyroIII :wink:
Don't guess. Sit down with paper and pencil, check size of KyroII,
check size of Nvidia's and ATI's chip set and scale for feature, now
what size does it come to. 8) You shouldn't be surprised, but I'm a
tease and can't halp you any further.
BTW, how can IMGTEC give a recommeded price for this device?
Has it been manufactured and has STM quoted a price they will want to
sale these devices at?

[Ailuros]

To be honest while I could make up in my mind a reasonable explanation for the 5500, due to the 0.13um problems at TSMC, I still can't understand why the 4800 wasn't released last year as projected in Aug/Sep or whenever that was.

Maybe the initial idea was/is to get both of them very close to the shelves, but it still doesn't make much sense to me

[Ailuros]

[quote]Yeah...we should really at least wait unti the part is officially announced, with specs, release date, etc....But then, that's takes all the fun out of wild speculation. ;)

Hmmm I can recall David Harold stating that the MBX (emulated) was running at 1/5th of it's speed at 30fps with FSAA on. I guess the MBX should be at 120mhz.

But even doing the math up to 250mhz (5500 has double the pipelines too) it doesn't help me much, because I don't even know what game/application he was talking about. Does that help any? (Of course I can think only of Multisampling).

[Teasy]

Don't guess. Sit down with paper and pencil, check size of KyroII,
check size of Nvidia's and ATI's chip set and scale for feature, now
what size does it come to.

Kyro II's size is irrelivent because Kyro III is not a faster Kyro II. Kyro II was a Kyro modified for far higher clock speed by STM so it needed additional transistors to acheive that. As for looking at Nvidia and ATI's chips, I've done that too, a Geforce 2 GTS has 4 pixel pipes and 2 TU's per pipe with static HW T&L (which is allot like the Kyro III spec that Joe has suggested in this thread) and is 25 million transistors, that's why I suggested a transistor count of around 30 million transistors for the Kyro 3 spec that Joe suggested.

BTW, how can IMGTEC give a recommeded price for this device?
Has it been manufactured and has STM quoted a price they will want to
sale these devices at?

IMGTEC told me that $150 is their target price, and STM won't be selling Kyro III considering their leaving the graphics chip market (you should know that if you know so much about Kyro III).

EDIT: my post was a little harsh towards Relativity because I thought he had deliberately insulted me. But it turns out that was not his intention so I've removed some of my more insulting comments from this post.

[Ailuros]

Uhhhmmmm device??? *snicker*

[Joe DeFuria]

I went back and tracked down (the best I could) the "GeForce" series of chips in terms of release date and micron process. (Mostly from various Anandtech reviews):

Fall '99: GeForce256: 0.22 u
Spring '00: GeForce2 GTS: 0.18u
Spring '00: GeForce2 MX: 0.18 u
Fall '00: GeForce2 Ultra: 0.18u
Fall '00: GeForce2 Pro: 0.18u
Spring '01: GeForce3: 0.15u
Spring '01: GeForce2 MX 200/400: 0.18u
Fall '01: GeForce3 Ti: 0.15u
Fall '01: GeForce2 Ti: 0.15u (?)
Spring '02: GeForce4 Ti: 0.15
Spring '02: GeForce4 Mx: 0.15u

So it looks like I was wrong...nvidia never did a die shrink of the GeForce2 MX, but did the MX "refresh" on a more mature 0.18 process rather than shrinking it down to 0.15. The original GeForce2 MX was on the "brand new" (immature) 0.18 process.

It's hard to say what they might do with the GeForce4 MX though. the 0.15 micron process should be relatively mature by now. So IMO, they either they won't be refreshing the GeForce4 MX line at all and introduce a new "value" part in about a year, or will refresh the GeForce4 MX on 0.13 in about a year.

[Joe DeFuria]

IMGTEC told me that $150 is their target price, and STM won't be selling Kyro III considering their leaving the graphics chip market (you should know that if you know so much about Kyro III).

Well, I think his point was that IMGTECH doesn't set the prices of the chips, so they are a bit removed from the final pricing of the boards. Certainly, IMGTECH should have some idea of what the chips and boards should cost, but as you like to say ;), IMG TECH doesn't make the chips, they don't decide what they will sell for, what market they will go after, etc.

So in short, take IMG's price "projections" with a grain of salt, because they aren't selling the chips, let alone the boards. It would be much better to hear projected prices from the chip-maker. ;)

That being said, $150 MSRP does sound about right to me. I'm just not convinced the initial street prices will be near $100, and think they'll be closer to $150.

(EDIT...) To be clear, I mean closer to $150 if it were released today. The further away from today we get, the lower we can expect the street price to debut at. Of course, competing parts will be lowering in price as well.

[Teasy]

Well, I think his point was that IMGTECH doesn't set the prices of the chips, so they are a bit removed from the final pricing of the boards. Certainly, IMGTECH should have some idea of what the chips and boards should cost, but as you like to say , IMG TECH doesn't make the chips, they don't decide what they will sell for, what market they will go after, etc.

IMGTEC don't decide the price of the chip no but that doesn't mean they don't know what STM had decided, obviously they would know that as they design the chip and also make boards based on that chip.

So in short, take IMG's price "projections" with a grain of salt, because they aren't selling the chips, let alone the boards. It would be much better to hear projected prices from the chip-maker.

IMGTEC do sell the boards, they make the Videologic versions of every desktop PowerVR chip released, so they will decide what price that board sells for. They also make the reference boards for STM AFAIK.

That being said, $150 MSRP does sound about right to me. I'm just not convinced the initial street prices will be near $100, and think they'll be closer to $150.

Past reccomended/actual prices would suggest otherwise, we'll see though.

[relativity]

Now I know, you know little about KyroIII

I'm pretty confident I know more then you about it after reading your post ;)

Don't guess. Sit down with paper and pencil, check size of KyroII,
check size of Nvidia's and ATI's chip set and scale for feature, now
what size does it come to.

Kyro II's size is irrelivent because Kyro III is not a faster Kyro II. Kyro II was a Kyro modified for far higher clock speed by STM so it needed additional transistors to acheive that. As for looking at Nvidia and ATI's chips, I've done that too, a Geforce 2 GTS has 4 pixel pipes and 2 TU's per pipe with static HW T&L which is Kyro III like in raw specs and is 25 million transistors, that's why I suggested a transistor count of around 30 million transistors for the Kyro 3 spec that Joe assumed.

You shouldn't be surprised, but I'm a
tease and can't halp you any further.

I have no idea who you are so I have no reason to assume you know much about the subject.

BTW, how can IMGTEC give a recommeded price for this device?
Has it been manufactured and has STM quoted a price they will want to
sale these devices at?

I thought you knew so much about Kyro III?.. why do you have to ask me any of this if you know everything already? ;)

IMGTEC told me that $150 is their target price, and STM won't be selling Kyro III considering their leaving the graphics chip market (you should know that if you know so much about Kyro III).


I should not have made the comments I did :(

[up]

Anyway, will there be a chance to get benchmark T&L in 3d Mark 2001se with this 'Enhenced T&L' card working?

I really wonder!

[Slashhead]

Reading most of the reactions,
The Kyro 2 SE is an overclocked Kyro 2. When you already owned a Kyro 2, doing a driver update makes the card using EnT&L ?