KYRO enhanced T&L

[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
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]

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 ?