NVIDIA novinky

[Masster]

NVIDIA First To Deliver High-Definition Video Processing For All Desktop and Notebook PC Market Segments

link http://www.nvidia.com/object/IO_29956.html

A tady je seznam toho, co ktera karta zvlada.
http://www.nvidia.com/page/purevideo_support.html

Samozrejme jsou potreba nove ovladace, ktere najdete tady

[ace960]

6800GT (AGP) aj ine su nejako mimo... H.264 a aj inde

[no-X]

6800GT (AGP) aj ine su nejako mimo... H.264 a aj inde

NV40 a NV45 nemají plně funkční VPE (videoprocesor), proto na nich akcelerace některých náročnějších formátů nefunguje. Ostatní čipy by měly být v pohodě.

[Masster]

Toshiba touts NVIDIA's GeForce Go 7900 GS

“We didn’t issue our own release for the GeForce Go 7900 GS. Instead, we decided to let our partners Toshiba make the announcement. We have a new launch coming with our new flagship notebook GPU. We will definitely make an official announcement for that GPU,” said Rick Allen, a spokesperson for Nvidia Corp.

Nvidia GeForce Go 7900 GS is produced using 90nm process technology and is based on the recently introduced GeForce 7900-series graphics processing units (GPU). The GeForce 7900 GS has 20 pixel processors, 7 vertex processors and is clocked at 375MHz, a relatively low clock-speed, something which should ensure very moderate power consumption of the new GPU. Nvidia recommends to use 256MB of 1000MHz GDDR3 memory with 256-bit along with the new mobile graphics chip.

http://www.xbitlabs.com/news/mobile/...328120127.html

[no-X]

Takže je definitivně potvrzeno, že G80 nebude hardwarově unifikovaná:

http://babelfish.altavista.com/babelfish/trurl_pagecontent?lp=ja_en..../2006/0419/kaigai262.htm

(originální znění: http://pc.watch.impress.co.jp/docs/2.../kaigai262.htm)

[Masster]

NVIDIA's transition to unified shaders will be gradual?

Nvidia Corp.’s chief scientist David Kirk has once again reaffirmed his stance on the unified shader processors by claiming that shortly from now there may be no point to implement them and said that the company would be “gradually” going to the unified architecture, the approach taken by arch-rival ATI Technologies.

“The vertex shader, pixel shader, ROP (rasterizing operation), tesselator, other hardware units [of the contemporary graphics processors] will probably evolve into something that can execute everything. But time is required for, [such evolution] is not possible at one time. Change probably will happen progressively,” said David Kirk in an interview with Japanese PC Watch web-site (please note that the quote was translated from Japanese – X-bit labs).

http://www.xbitlabs.com/news/video/d...418170458.html

[Haste]

Kuuurnik ted se zacne lamat chleba Vazne bych rad videl vysledky G80/R600 na necem jako Crysis

[Masster]

Additional members of the GeForce 7 family?

Today we had the chance to speak with a very reliable, unofficial source who is very familiar with some of Nvidia’s plans. The same source gave us some news regarding additional members of the GeForce 7 family. Since this source is unofficial, consider the following information as a rumor. So here is what we have heard:

GeForce 7900 GS
According to our source, Nvidia is planning to extend the 7900 family with a GS member. Like the other GS products, it will be a bit slower then the GT. We still don’t know if it will be released to the AGP market like the 7800GS or to PCI Express.

GeForce 7600 GTX
I’ve been very surprised to hear about a GTX version of the 7600 series. Nvidia did very well with their 6600 series, and it seems that the new successor, the 7600 will get its own GTX version. As it sounds, we guess it will be faster then the 7600 GT.

GeForce 7600 LE
The LE version seems to be the slowest member of the 7600 series. So we can guess that it will also be the cheapest version. Update: Our source is not sure about the 7600LE.

GeForce 7300 GT
This one is already confirmed and the media reported about it today. I guess you already have all the details about it. According to the other websites, the release date for the 7300 GT is the 15th of May. According to our source the GeForce 7300 GT will be based on G73.

http://www.ngohq.com/home.php?page=a...read&arc_id=80

[Masster]

NVIDIA G80 scheduled for September?

WE LEARNED that Nvidia G80 should be seen the face of the planet in late Q3 or early Q4. It could be ready for the end of Q3 but only if the first tape out goes well.

We still cannot confirm the status of the G80's tape out - if it's going well, September. If not you can easily add an additional two months to the projected date.

This chip has every chance to end up faster than ATI's upcoming R580+ fall refresh chip but this one will get R600 beast to compete with. It is still too early for clocks and final specs but we will start digging this one

http://www.theinquirer.net/?article=32385

Je mozne kolik si tam Fuad dela mista na omyl? Bud v zari nebo az za dva mesice, nejspis bude rychlejsi nez R580+...to by asi mela....takovy clanek, ktery nic nerekne by tu dokazal napsat asi kazdy

A bonbonek na konec

All we could confirm at this time is that the chip will be DirectX 10 compliant of course but it won't have the full implementation of Shader Model 4.0. It won't do the unified Shader but it will be Vista ready. Most of the chips out today are Vista ready at least the high end ones.

[Masster]

No tak a ted novinky z realneho sveta, ktere nam dokonce neco reknou

J.P. Morgan Tech Conference, May 24th 2006

When's your next gen part? A: "Well, you know GPUs are getting so large and so complex the timing of it is almost one of those things that the timing of it is 'it comes out when it comes out'. . .as much as you try to plan it for a certain event it really is on a schedule that says 'when it's done it's done'. . .now the reason why that works, at least for the high-end. . .the first high-end gpu that comes out. . .is because it is going to get purchased by enthusiasts who really don't care if it is Christmas, the middle of summer, or spring. If it has a discernible advantage over the last gpu, they'll buy it. So our schedule right now on the next generation GeForce [Hmm, that's the first time we've heard them confirm it is still 'GeForce'?] is going to be second half, and the objective is to hit it for 'back to school'. But fundamentally we're really just targeting second half. Which means that the current GeForce 7 family, with the exception of the high-end, is really the family you're going to see in the back to school cycle. [So what I got out of that: if next spin goes well, they hit 'back to school' for a high-end part. If not, it'll be later. And no full family simultaneous launch.] But this one is. . .we kind of describe it inside the company as. . . 'this is probably the biggest architectural change in the company's history from one generation to the next' [Hmm!] I'll give you a little bit of insight. . .this device is going to be over half a billion transistors large. It will, without doubt, be the most complex device being built in the semi-conductor business today. So the current schedule right now is to have it in the second half. And we'll do typical, which is a 'hard launch', which means we'll launch it when it's actually available in retail.

Cutting wafer production? A: 'We manage wafer starts all day long'. Very comfortable with current inventory. We look at quality of inventory more than quantity. Stopped producing GF 6, and inventory of them is very low. Will be moving GF7 high-end inventory down in preparation for "GeForce 8" [Bingo, another public confirmation of name]. MCP sales were somewhat lower, but quality of inventory is very fresh.

Zbytek interview zde

[Haste]

Takze ona zprava, ze oba chipy (G80 i R600) budou mit kolem 500mil. tr. se zda byt pravdiva a tim padem bude asi taky pravdiva zprava o 300W na jednu grafiku... God help us ...

[no-X]

OT: v souvislosti s R600 se párkrát zmínilo číslo 450mil. Ale to už ostatně není rozdíl.

[Masster]

Tak podle vseho lze zapojit 7950GX2 do SLI s jednou 7900GT/GTX.
Prisel na to jeden uzivatel nVnews fora tady.

Je tam i vysledek z benchmarku ve FEAR.

[Masster]

A dalsi podobny pokus, tentokrat vsak jde o 7300GT ve SLI s 7600GT

As the 7300GT is so similar to the 7600 range of cards, I decided to do some experimentation. Using RivaTuner I modified the device ID of the 7300 GT from 393 to 391. This tricked the system in to thinking that the card was in fact a 7600 GT. This doesn't unlock any pipelines (which nVidia has managed to restrict quite well in the seven series). However, when a real 7600 GT was put in to the system along side it, it actually worked in SLI – despite the pipeline differences.

http://www.trustedreviews.com/articl...ge=7224&head=0

[Masster]

NVIDIA's G80 has taped out? And other rumours

WE HEAR Nvidia has been beavering away fo meet the DirectX 10 specification.

And the firm decided it doesn't need a unified Shader for its upcoming G80 chipset. Instead, it decided that you will be fine with twice as many pixel Shader numbers as geometry and vertex Shaders.

AS we understand it, if a Nvidia DX10 chip ends up with 32 pixel-Shaders, the same chip will have 16 Shaders that will be able to process geometry instancing or the vertex information.

http://www.theinquirer.net/default.aspx?article=32769

WE CAN now confirm that mighty Nvidia taped out its first G80 chip.

The first successful silicon turned up from the fab a couple weeks ago now, it seems. This puts the company bang on the schedule for its Septembrish launch.

http://www.theinquirer.net/default.aspx?article=32768

[no-X]

A co tohle



http://arith17.polito.it/foils/11_2.pdf
http://arith17.polito.it/final/paper-164.pdf

Autor toho dokumentu, Stuart Oberman, původně pracoval v AMD a navrhl FPU Athlonu...

btw. zajímavý jsou i poslední dvě stránky - týká se toFSAA. Řekl bych, že to souvisí s tímhle patentem

---------------------

/edit:

The G80 from Nvidia will, finally, have a completely new Antialiasing engine.

DirectX 10 et GPUs from Hardware.FR

[no-X]

Třetí díl seriálu: The People Behind DirectX 10: Part 3 - NVIDIA's Tony Tamasi

http://www.extremetech.com/article2/...1986937,00.asp

If you assume that the competitors will be bound by the same laws of physics and economics, that alone would put one competitor in a dramatically better position. Would consumers be willing, for example, to pay twice as much for a graphics card that delivered the same performance as another, just because a particular graphics card was unified, or to pay the same price, but run at ½ the performance just because it offered some new architectural block diagram? I doubt it.

Docela se cejtí

Nvidia has been working on DX10 for many years, and as we were with Shader Model 3, expect to be the leader with DX10.

[Haste]

Nvidia has been working on DX10 for many years, and as we were with Shader Model 3, expect to be the leader with DX10.

No, rekl bych, ze akcie tomu prohlaseni moc neodpovidaji. Teda aspon zatim. Ten propad NV je vazne neuveritelny. Uz 3. mesic prudce klesaji a sou POD pulrocnim minimem. Viz.: http://finance.yahoo.com/q/bc?s=ATYT...z=m&q=l&c=nvda

[no-X]

NVIDIA's G80 to make use of 'Multi-function Interpolators'?

http://www.elitebastards.com/cms/... ...83&Itemid=29

[Masster]

NVIDIA G80 to stay a 90 nanometre chip?

We wrote before that the new G80 will feature 32 pipelines and 16 vertex + geometry Shader but now we've also learned that the chip will be developed on the older 90 nanometre process.

Nvidia doesn't want to risk the shrinkage to 80 nanometre. Its experiences with its own NV30 taught it not to take the unnecessary risks with chip shrinkage on such important chips.

http://www.theinquirer.net/default.aspx?article=33260

[Haste]

NVIDIA G80 to stay a 90 nanometre chip?
http://www.theinquirer.net/default.aspx?article=33260

Jestli Fuad zase nemlzi, tak to je pekne na prd. Co to je za upgrade, kdyz to bude mit stejny vyrobni proces

[Q]

no tak jestli tam ma bejt kolem 500mil. tranzistoru, tak to teda bude peknej macek...

[Haste]

no tak jestli tam ma bejt kolem 500mil. tranzistoru, tak to teda bude peknej macek...

500mil. tranzistoru na 1 chip s 90nm ? Tady neco nehraje Leda ze by to jelo na nejakych 350MHz nebo tomu dali dusik v zakladnim baleni....

[mraky]

No a hlavne rozmerove by to bylo obrovske.

[Masster]

No tech 560mil. tranzistoru je porad jenom dohad a taky nikdo rozhodne nevi odkud Inq. to info o 90nm ma. Ze se jednou za cas trefi, neznamena vubec nic

Jinak nevim jestli jsem na tom s anglictinou blbe ja nebo vy, ale ja tuhle vetu

Nvidia has been working on DX10 for many years, and as we were with Shader Model 3, expect to be the leader with DX10.

chapu tak, ze jako prvni uvedli SM3 kartu, nic jineho....takze v tomhle maji pravdu, protoze G80 vyjde driv jak R600.