September? That's literally impossible. There is no possible way that they could qualify silicon for full production release that quickly. October is out of the question as well. Late November is my guess. Possibly early December. My guesses, however, are based on nVidia's past performance and there's always a chance for them to fumble badly this time around.The N30 could be Sept., Oct. or Nov. Hoping Sept. but i won't hold my breath.
Originally posted by: bluemax
Oh that's right... I forgot. ATI can't make drivers. That's right. No ATI owners can play any games at all. Or only a handful of the most popular.... nVidia never makes a mistake and never releases bad drivers. nVidia cards work in all motherboards too. And the best news is that nVidia leaks out a new driver every second week.... all these revisions are for people complaining about ATI problems!!
Yeah!!
![]()
We've heard it all before and it's a pretty thin argument. There's PLENTY of ATI owners that would disagree with you, and rightly so.
The hardware is excellent. The drivers are excellent.
Get over it.
Huh? No it can't. Imtim83, I may be blind when it comes to reading the titles on news articles, but I'm a chip designer. I'm telling you that there is no possible way that they can get silicon back in less than 3 weeks from a fab. It simply is not possible no matter how much money you have. And it takes at least 90 days to qualify silicon. That's the minimum.pm yeah but you are not nvidia. Lots money can speed things up a whole lot.
Originally posted by: pm
Huh? No it can't. Imtim83, I may be blind when it comes to reading the titles on news articles, but I'm a chip designer. I'm telling you that there is no possible way that they can get silicon back in less than 3 weeks from a fab. It simply is not possible no matter how much money you have. And it takes at least 90 days to qualify silicon. That's the minimum.pm yeah but you are not nvidia. Lots money can speed things up a whole lot.
No offense intended, but how much experience do you have in debugging silicon?
Originally posted by: imtim83
pm yeah but you are not nvidia. Lots money can speed things up a whole lot. Wouldn't you all be surprised if Nvidia released their N30 in August or Sept. 😉
Sorry man... pm is definitely right. Semiconductor manufacturers work 24/7 on these things. Manufacturing tools are set aside for projects like this. There is no way throwing a few more bucks at it will speed it up any.Originally posted by: imtim83
pm yeah but you are not nvidia. Lots money can speed things up a whole lot. Wouldn't you all be surprised if Nvidia released their N30 in August or Sept. 😉
Originally posted by: Anand Lal Shimpi
September is out of the question (our AT Forums Fab Engineers - pm & Wingznut - can explain why in greater detail 😉), I've already mentioned when NV30 will be ready in an earlier article...
Take care,
Anand
Chris Malachowski, vice president of engineering at Nvidia, described the GeForce 4, the latest in that company's line of high-end graphics chips. At 63 million transistors and a core clock frequency of 300 MHz, the chip is ambitious by any measure. But considering that 78 per cent of the die is logic places the undertaking in perspective.
Compensating somewhat for the sheer size of the design, the chip is based on an existing architecture. Yet Malachowski said that nearly 50 per cent of the RTL had been modified from the previous family member, so the complexity was not reduced that much by reuse.
....(some chip features described)...
Malachowski said that by their metrics the design had been a great success. First silicon had 19 reported functional problems, only seven of which required repair. All seven were corrected in the metal, allowing the team to meet its target of approximately 9 months to tape out and 100 days between tape-out and production ramp.
Originally posted by: wesman
Before you go around calling people liars, perhaps you should know something about what your talking about. One search on Google of the terms "nvidia tape out to production" brang this article as the first result:
Chris Malachowski, vice president of engineering at Nvidia, described the GeForce 4, the latest in that company's line of high-end graphics chips. At 63 million transistors and a core clock frequency of 300 MHz, the chip is ambitious by any measure. But considering that 78 per cent of the die is logic places the undertaking in perspective.
Compensating somewhat for the sheer size of the design, the chip is based on an existing architecture. Yet Malachowski said that nearly 50 per cent of the RTL had been modified from the previous family member, so the complexity was not reduced that much by reuse.
....(some chip features described)...
Malachowski said that by their metrics the design had been a great success. First silicon had 19 reported functional problems, only seven of which required repair. All seven were corrected in the metal, allowing the team to meet its target of approximately 9 months to tape out and 100 days between tape-out and production ramp.
This is on a chip which was only 50% new design, with half the transistors of the nv30, on a proven .15 process and it took 100 days. 90 days is the shortest time Nvidia has taken, and that was on a simple die shrink, it is not the average time. So to say they always take less than 3 months is bull****.
Originally posted by: Insane3D
Originally posted by: wesman
Before you go around calling people liars, perhaps you should know something about what your talking about. One search on Google of the terms "nvidia tape out to production" brang this article as the first result:
Chris Malachowski, vice president of engineering at Nvidia, described the GeForce 4, the latest in that company's line of high-end graphics chips. At 63 million transistors and a core clock frequency of 300 MHz, the chip is ambitious by any measure. But considering that 78 per cent of the die is logic places the undertaking in perspective.
Compensating somewhat for the sheer size of the design, the chip is based on an existing architecture. Yet Malachowski said that nearly 50 per cent of the RTL had been modified from the previous family member, so the complexity was not reduced that much by reuse.
....(some chip features described)...
Malachowski said that by their metrics the design had been a great success. First silicon had 19 reported functional problems, only seven of which required repair. All seven were corrected in the metal, allowing the team to meet its target of approximately 9 months to tape out and 100 days between tape-out and production ramp.
This is on a chip which was only 50% new design, with half the transistors of the nv30, on a proven .15 process and it took 100 days. 90 days is the shortest time Nvidia has taken, and that was on a simple die shrink, it is not the average time. So to say they always take less than 3 months is bull****.
I think AmdInside was just officially OWNED. 😀 😀 😛