[THREAD UFFICIALE] Aspettando Nvidia GTX 480 e GTX 470

Originariamente inviato da michelgaetano

non era larrabee

ah si?
vabbè più o meno è uguale dai..resta sempre un nome strano

[michelgaetano]

Originariamente inviato da Mister Tarpone

ah si?
vabbè più o meno è uguale dai..resta sempre un nome strano

Controllato sì, è Larrabee

Chissà come andrà, non sarebbe male avere un altro competitor

Originariamente inviato da michelgaetano

Controllato sì, è Larrabee

Chissà come andrà, non sarebbe male avere un altro competitor

quoto... se venisse fuori ai livelli delle schede ati e nvidia lo prenderei..

[HaRdCoRe GaMeR]

Originariamente inviato da Mister Tarpone

dico solo una cosa = labaree Black Editon...e via

E che sarebbe?

Originariamente inviato da HaRdCoRe GaMeR

E che sarebbe?

top secret

[nico88desmo]

It looks like nVidia is dead set on calming the PR storm the competitors are releasing, and the mood in the company is more relaxed. nVidia is certain they have a winner on their hands, but only time will tell whether they managed to pull it through or not.

We already gave you details on the architectural side. GT300 or G300 or NV70 is consisted out of 512 cores [or Shader Processors, whatever you like], features a 512-bit memory controller connecting to GDDR5 memory and well, it is a beast. nVidia packed everything in around 2.4 billion transistors using TSMC's 40nm high-performance process [yes, the one with currently sucky yields]. Given that the original GT200 packed 240 shaders in 1.4 billion trannies, one could argue that nVidia did some heavy dieting on its own architecture and managed to get a body builder shader power in a size zero body. GT300 packs 512 MIMD-capable cores and yet it uses "just" one billion transistors extra. I'll be first to admit that I wondered how GT300 packs at least three billion transistors, but according to our highly confidential source, the 2.4 billion transistors are packed in just 495mm2.

Yes, you've read that correctly. 2.4 billion in less than 500mm2 will put sweat on both ATI and Intel's forehead, since this chip could be profitably manufactured and yet pack performance to potentially blew the competition out of the water. Each of original 65nm GT200 chips took 576mm2 of wafer space, while 55nm refresh GT206/GT200b eats up 490mm2.

In comparison, Intel's high-end Larrabee part is manufactured in 45nm and takes around 600mm2.

Now, if you are wondering why nVidia created a single-PCB GTX295, think again. This part is more than an engineering exercise - but let us put it in this perspective - if nVidia managed to put 2.4 billion transistors in less than 500mm2, with an interesting performance delta between GT200-GT300 in clock-per-clock comparison… we could say that Jen-Hsun definitely opened a can of whoop-ass on its competitors.


fonte: http://www.brightsideofnews.com/news...-larrabee.aspx

[HaRdCoRe GaMeR]

Originariamente inviato da nico88desmo

It looks like nVidia is dead set on calming the PR storm the competitors are releasing, and the mood in the company is more relaxed. nVidia is certain they have a winner on their hands, but only time will tell whether they managed to pull it through or not.

We already gave you details on the architectural side. GT300 or G300 or NV70 is consisted out of 512 cores [or Shader Processors, whatever you like], features a 512-bit memory controller connecting to GDDR5 memory and well, it is a beast. nVidia packed everything in around 2.4 billion transistors using TSMC's 40nm high-performance process [yes, the one with currently sucky yields]. Given that the original GT200 packed 240 shaders in 1.4 billion trannies, one could argue that nVidia did some heavy dieting on its own architecture and managed to get a body builder shader power in a size zero body. GT300 packs 512 MIMD-capable cores and yet it uses "just" one billion transistors extra. I'll be first to admit that I wondered how GT300 packs at least three billion transistors, but according to our highly confidential source, the 2.4 billion transistors are packed in just 495mm2.

Yes, you've read that correctly. 2.4 billion in less than 500mm2 will put sweat on both ATI and Intel's forehead, since this chip could be profitably manufactured and yet pack performance to potentially blew the competition out of the water. Each of original 65nm GT200 chips took 576mm2 of wafer space, while 55nm refresh GT206/GT200b eats up 490mm2.

In comparison, Intel's high-end Larrabee part is manufactured in 45nm and takes around 600mm2.

Now, if you are wondering why nVidia created a single-PCB GTX295, think again. This part is more than an engineering exercise - but let us put it in this perspective - if nVidia managed to put 2.4 billion transistors in less than 500mm2, with an interesting performance delta between GT200-GT300 in clock-per-clock comparison… we could say that Jen-Hsun definitely opened a can of whoop-ass on its competitors.


fonte: http://www.brightsideofnews.com/news...-larrabee.aspx

Quindi? non ne capisco molto di ste cose

[Kharonte85]

Originariamente inviato da nico88desmo

It looks like nVidia is dead set on calming the PR storm the competitors are releasing, and the mood in the company is more relaxed. nVidia is certain they have a winner on their hands, but only time will tell whether they managed to pull it through or not.

We already gave you details on the architectural side. GT300 or G300 or NV70 is consisted out of 512 cores [or Shader Processors, whatever you like], features a 512-bit memory controller connecting to GDDR5 memory and well, it is a beast. nVidia packed everything in around 2.4 billion transistors using TSMC's 40nm high-performance process [yes, the one with currently sucky yields]. Given that the original GT200 packed 240 shaders in 1.4 billion trannies, one could argue that nVidia did some heavy dieting on its own architecture and managed to get a body builder shader power in a size zero body. GT300 packs 512 MIMD-capable cores and yet it uses "just" one billion transistors extra. I'll be first to admit that I wondered how GT300 packs at least three billion transistors, but according to our highly confidential source, the 2.4 billion transistors are packed in just 495mm2.

Yes, you've read that correctly. 2.4 billion in less than 500mm2 will put sweat on both ATI and Intel's forehead, since this chip could be profitably manufactured and yet pack performance to potentially blew the competition out of the water. Each of original 65nm GT200 chips took 576mm2 of wafer space, while 55nm refresh GT206/GT200b eats up 490mm2.

In comparison, Intel's high-end Larrabee part is manufactured in 45nm and takes around 600mm2.

Now, if you are wondering why nVidia created a single-PCB GTX295, think again. This part is more than an engineering exercise - but let us put it in this perspective - if nVidia managed to put 2.4 billion transistors in less than 500mm2, with an interesting performance delta between GT200-GT300 in clock-per-clock comparison… we could say that Jen-Hsun definitely opened a can of whoop-ass on its competitors.


fonte: http://www.brightsideofnews.com/news...-larrabee.aspx

Se fosse vero:

[HaRdCoRe GaMeR]

Che prestazioni avrà allora la singola gtx380? Come uno sli di gtx285?

[ArCH85]

Originariamente inviato da HaRdCoRe GaMeR

Che prestazioni avrà allora la singola gtx380? Come uno sli di gtx285?

penso sia un po' presto per dirlo, non sappiamo praticamente nulla

[HaRdCoRe GaMeR]

Secondo me dalla gtx280 alla gtx380 ci sarà un'incremento prestazionale minimo del 50%

edit: Just bring on the GTX-380 on schedule like this June, that would make it officially one year after the GTX-280 and perfect time for the 380 to come out. The GTX-280 was about 75% faster than 8800GTX it's replacement.

So if nVidia is still on schedule we should see a GTX-380 this June and be approx 75% faster than GTX-280, anything less than that and not on time will blow for them waiting for no reason.

[halduemilauno]

Originariamente inviato da HaRdCoRe GaMeR

Che prestazioni avrà allora la singola gtx380? Come uno sli di gtx285?

qui c'è un'utile confronto/riepilogo a quanto si sa ora...
http://www.hardware-infos.com/news.p...2944&sprache=1

[okorop]

http://www.tomshw.it/news.php?newsid=18074

[Gabriyzf]

Originariamente inviato da Ratatosk

Non mi sembra propriamente IT

infatti

[appleroof]

Originariamente inviato da nico88desmo

It looks like nVidia is dead set on calming the PR storm the competitors are releasing, and the mood in the company is more relaxed. nVidia is certain they have a winner on their hands, but only time will tell whether they managed to pull it through or not.

We already gave you details on the architectural side. GT300 or G300 or NV70 is consisted out of 512 cores [or Shader Processors, whatever you like], features a 512-bit memory controller connecting to GDDR5 memory and well, it is a beast. nVidia packed everything in around 2.4 billion transistors using TSMC's 40nm high-performance process [yes, the one with currently sucky yields]. Given that the original GT200 packed 240 shaders in 1.4 billion trannies, one could argue that nVidia did some heavy dieting on its own architecture and managed to get a body builder shader power in a size zero body. GT300 packs 512 MIMD-capable cores and yet it uses "just" one billion transistors extra. I'll be first to admit that I wondered how GT300 packs at least three billion transistors, but according to our highly confidential source, the 2.4 billion transistors are packed in just 495mm2.

Yes, you've read that correctly. 2.4 billion in less than 500mm2 will put sweat on both ATI and Intel's forehead, since this chip could be profitably manufactured and yet pack performance to potentially blew the competition out of the water. Each of original 65nm GT200 chips took 576mm2 of wafer space, while 55nm refresh GT206/GT200b eats up 490mm2.

In comparison, Intel's high-end Larrabee part is manufactured in 45nm and takes around 600mm2.

Now, if you are wondering why nVidia created a single-PCB GTX295, think again. This part is more than an engineering exercise - but let us put it in this perspective - if nVidia managed to put 2.4 billion transistors in less than 500mm2, with an interesting performance delta between GT200-GT300 in clock-per-clock comparison… we could say that Jen-Hsun definitely opened a can of whoop-ass on its competitors.


fonte: http://www.brightsideofnews.com/news...-larrabee.aspx

secondo questi rumors allora Nvidia insisterebbe sulla strada del chippone. E' chiaramente una strada rischiosa perchè per guadagnare a quel punto devi puntare sempre sul vantaggio prestazionale rispetto alla concorrente (ancor più se si pensa al segmento alto o medio-alto) -tipo g80/g92 vs rv670-così appunto si giustifica un ipotetico divario di prezzo sul mercato che invogli gli utenti all'acquisto e garantisca un certo margine di guadagno

inoltre mi chiedo come facciano ad usare un chip così grande per le derivate di fascia bassa e medio-bassa, usando gli scarti? O peggio saltando ancora una volta i derivati di gt300@40nm in attesa dello shrink @ 32nm (insomma, la storia che avremmo visto con gt200)?

sui numeri ventilati non c'è che dire se non una parola sola: IMPRESSIONANTE

ovviamente per tutto quello che ho scritto si ragiona solo su rumors...

[FreeMan]

Originariamente inviato da okorop

http://www.tomshw.it/news.php?newsid=18074

facciamo che i prossimi post OT e flammosi porteranno a pesanti sospensioni.

>bYeZ<

[Gabriyzf]

Originariamente inviato da appleroof

secondo questi rumors allora Nvidia insisterebbe sulla strada del chippone. E' chiaramente una strada rischiosa perchè per guadagnare a quel punto devi puntare sempre sul vantaggio prestazionale rispetto alla concorrente (ancor più se si pensa al segmento alto o medio-alto) -tipo g80/g92 vs rv670-così appunto si giustifica un ipotetico divario di prezzo sul mercato che invogli gli utenti all'acquisto e garantisca un certo margine di guadagno

inoltre mi chiedo come facciano ad usare un chip così grande per le derivate di fascia bassa e medio-bassa, usando gli scarti? O peggio saltando ancora una volta i derivati di gt300@40nm in attesa dello shrink @ 32nm (insomma, la storia che avremmo visto con gt200)?

sui numeri ventilati non c'è che dire se non una parola sola: IMPRESSIONANTE

ovviamente per tutto quello che ho scritto si ragiona solo su rumors...

secondo me vedremo qualcosa di nuovo e tutti i rumors si riveleranno infondati, come alla vigilia di G80

[michelgaetano]

Originariamente inviato da Gabriyzf

secondo me vedremo qualcosa di nuovo e tutti i rumors si riveleranno infondati, come alla vigilia di G80

Per un nuovo g80 ci metto la firma, purchè non costi 650 €

[Athlon 64 3000+]

bisogna vedere se è vero che faranno ancora un chip da quasi 500 mm^2 e che potenza avrà rispetto alla GTX285.
GT300 se sarà davvero un'altro mega chippone dovrà anche essere molto più potente di GTX285 perchè penso che RV870 in versione single gpu sarà più veloce della HD 4870x2 e la versione dual gpu potrebbe dare parecchio filo da torcere a GT300.

[Defragg]

Originariamente inviato da Kharonte85

Se fosse vero:

Fighissimo