ATI Tape Out Three Successful!!!

[Mrvile]

Originally posted by: X
ATI doesn't need a 32 pipe card to compete with Nvidia at this point. If they can crank out a 24 pipe at 600+ mhz, they will have a winner. Great to hear that they are finally able to produce the R520 with acceptable yields.

Agreed. Instead of jumping too far ahead of the competition I think it's smart to stay only a bit ahead, so when they pull ahead you have something to back you up.

 

[Drayvn]

Originally posted by: keysplayr2003
Great News. I hope it arrives soon.

There is word that high speeds were reached. Bad news is, there isn't a high yield.

opinion
My guess (this is strictly my own opinion) is that we will see 32 pipe R520's in very low availability, but will give ATI the performance title. We will however see a 24 pipe (pro) in the same availability the X800pro offered which was pretty good.
/opinion

W00t!

Sweet now i can start pulling my money together and hopefully start comparing these 2 cards soon. Hopefully they will send out sample cards to Anandtech and the like soon and we can see some benchies, maybe?

 

[Killrose]

Originally posted by: HDTVMan
LOL. Two things come to mind.

Where is the OMFG and ATI TAKEOVER statements?

I will gladly take a lowly only 16pipes working off one of the edges.

Now we know why Ati stock went up recently, news of a successful tape-out from the "insiders" caused the stock to go up and spawned the take-over rumors

Grow my little pretties grow!! >Ati @ silicon waffers

 

[Drayvn]

Originally posted by: Killrose

Originally posted by: HDTVMan
LOL. Two things come to mind.

Where is the OMFG and ATI TAKEOVER statements?

I will gladly take a lowly only 16pipes working off one of the edges.

Now we know why Ati stock went up recently, news of a successful tape-out from the "insiders" caused the stock to go up and spawned the take-over rumors

Grow my little pretties grow!! >Ati @ silicon waffers

Those lovely market analysts and guys who are in 'the know' just totally got it right didnt they /sarcasm/

 

[nRollo]

Originally posted by: ZobarStyl
Agreed, with words like 'extreme' pipes being thrown around and R580 being due for first thing '06, I have my doubts on 520 being the 32 pipe monster. Anytime a product is marketed using the word extreme, the consumer gets shafted.

Hey, what about Mountain Dew pop?!

Secondly, hacp I couldn't find your dirt cheap 7800GTX deal from Dell, care to post a link? And you're saying that 8 pipes more was worth 600 bucks for the 7800GTX, but an additional 8 isn't worth that same 600 a month later (assuming 32)? That makes little sense.

It's in Hot Deals:
http://forums.anandtech.com/messageview...atid=40&threadid=1636358&enterthread=y

I'm a bit surprised at everyones shock over a $600 launch MSRP on this card?
A. It has no competition other than 6800GT/U SLI, which cost more.
B. Prices of high enjd cards at launch have been going this direction for a while:
May 2003 high end pricing

At a $499 price tag, the GeForceFX 5900 Ultra is extremely hard to justify, but the $299 and $399 parts may be interesting depending on the final clock speeds that NVIDIA decides upon.

From the ATI camp the $499 Radeon 9800 Pro 256MB, just like the NV35, is a difficult purchase to justify; even more difficult in this case because the GeForceFX 5900 Ultra does outperform it in a number of tests.

October 2000

If you have around $500 (USD) to spend, there is nothing faster than the Ultra, however do keep in mind that this will change in the next 4 months.

So high end cards have been launching at $500 for five years. You didn't think that would ever change?

 

[Keysplayr]

Originally posted by: Creig

Originally posted by: keysplayr2003
And, I am at a loss about what the bolded statement above means. Can you be a little more detailed? 16 pipe? Edges? Not sure what that means.

I think he means he'd be happy with a 16 pipe card made from this newest process.

Ah ok. Thanks.

 

[Keysplayr]

Originally posted by: X
ATI doesn't need a 32 pipe card to compete with Nvidia at this point. If they can crank out a 24 pipe at 600+ mhz, they will have a winner. Great to hear that they are finally able to produce the R520 with acceptable yields.

X, not to rain on the parade just yet, but it was not specified if the poor yields were just for a particular piped card. 32 or 24. Just said yields were not that great but did not specify. So, theoretically, if the R520 was intended to be a 24 pipe card all along, then that would mean poor yields, although high clockspeed, on a 24 pipe R520. We need at least a glimpse of what the actual specs for R520 really are and were always intended to be by ATI. So, I am hoping they are only referring to a 32 pipe poor yield, but I have doubts of course.

 

[Killrose]

Originally posted by: keysplayr2003

Originally posted by: HDTVMan
LOL. Two things come to mind.

Where is the OMFG and ATI TAKEOVER statements?

I will gladly take a lowly only 16pipes working off one of the edges.

I believe that's another thread. This one is about ATI's successful tape out number 3.
Care to comment on the thread topic?

And, I am at a loss about what the bolded statement above means. Can you be a little more detailed? 16 pipe? Edges? Not sure what that means.

By the way, this doesn't mean that the R520 will get here any sooner than we discussed in the other thread. It means that the tape out is done and successful. We still have about 120 days to wait. Give or take.

I think he meant a cheap version of the R520 which has 16pipes and was "gotten" off the edge of the silicon waffer?


Did I win!!?

 

[Killrose]

Originally posted by: keysplayr2003

Originally posted by: X
ATI doesn't need a 32 pipe card to compete with Nvidia at this point. If they can crank out a 24 pipe at 600+ mhz, they will have a winner. Great to hear that they are finally able to produce the R520 with acceptable yields.

X, not to rain on the parade just yet, but it was not specified if the poor yields were just for a particular piped card. 32 or 24. Just said yields were not that great but did not specify. So, theoretically, if the R520 was intended to be a 24 pipe card all along, then that would mean poor yields, although high clockspeed, on a 24 pipe R520. We need at least a glimpse of what the actual specs for R520 really are and were always intended to be by ATI. So, I am hoping they are only referring to a 32 pipe poor yield, but I have doubts of course.

Only pure speculation on my part, but With a total of (3) tape-outs, I tend to think the first two were poor designs with non-working features or something, not just poor yeilds. I think R520 would have been shown more behind closed doors at E3 and Comdex(?, or whatever the other show was) but was'nt because it was not totally working.

 

[Killrose]

Originally posted by: Schadenfroh
What is an "extreme" pipe?

I think it's a pr0n industry term... :shocked:

 

[imported_X]

Originally posted by: keysplayr2003

Originally posted by: X
ATI doesn't need a 32 pipe card to compete with Nvidia at this point. If they can crank out a 24 pipe at 600+ mhz, they will have a winner. Great to hear that they are finally able to produce the R520 with acceptable yields.

X, not to rain on the parade just yet, but it was not specified if the poor yields were just for a particular piped card. 32 or 24. Just said yields were not that great but did not specify. So, theoretically, if the R520 was intended to be a 24 pipe card all along, then that would mean poor yields, although high clockspeed, on a 24 pipe R520. We need at least a glimpse of what the actual specs for R520 really are and were always intended to be by ATI. So, I am hoping they are only referring to a 32 pipe poor yield, but I have doubts of course.

As I read the article, it was poor yields that drove the retaping processes. Since the headline says the third retaping was successful, it seems logical that yields are now up to acceptable levels.

 

[biostud]

Originally posted by: Killrose

Only pure speculation on my part, but With a total of (3) tape-outs, I tend to think the first two were poor designs with non-working features or something, not just poor yeilds. I think R520 would have been shown more behind closed doors at E3 and Comdex(?, or whatever the other show was) but was'nt because it was not totally working.

Not knowing anything about production of chips, but I think I read something about that once the chips is designed they get a first sample that runs MUCH slower than final specs, probably a few Khz. They use this to find flaws and whatever you need to improve. They then continue with new revisions until they have a chip that works as it should without errors. Then they have a sample for the final production line and they then need to improve the producoction without too much wafer loss.

 

[bunnyfubbles]

If it is indeed more than 600MHz it does make it hard to believe its more than 24 pipes - although 24+8 or some odd combo - but 32 and 600+MHz doesn't seem likely, you'd think it would flat out destroy the 7800GTX, even an Ultra would most likley be a futile counter attack.

600+MHz and 24 pipes with working and available crossfire solution upon launch seems the most likely/logical bet. A 24pipe part @ 600+MHz should give them the single card advantage, of which a 7800Ultra would feature a clock increase to close that gap. Then there'd be Crossfire to claim the multi GPU advantage nVidia has had with SLI. The only need for 32 pipes would be to attack SLI pretty much without Crossfire, especially at 600+MHz.

Although then there's the problem of such low yeilds, it doesn't seem likely they'd have so much trouble if the card wasn't going to be a beast. However more than 24 pipes and more than 600MHz sounds too good to be true, although if it is the price will definately come to match, I would expect over $600, $700-800 even... yikes.

 

[HDTVMan]

Originally posted by: keysplayr2003

Originally posted by: HDTVMan
LOL. Two things come to mind.

Where is the OMFG and ATI TAKEOVER statements?

I will gladly take a lowly only 16pipes working off one of the edges.

I believe that's another thread. This one is about ATI's successful tape out number 3.
Care to comment on the thread topic?

And, I am at a loss about what the bolded statement above means. Can you be a little more detailed? 16 pipe? Edges? Not sure what that means.

By the way, this doesn't mean that the R520 will get here any sooner than we discussed in the other thread. It means that the tape out is done and successful. We still have about 120 days to wait. Give or take.

Just like keysplayr2003 I wouldnt mind taking a 16pipe version of the card I dont need the top of the line.

 

[HDTVMan]

Originally posted by: Killrose

Originally posted by: keysplayr2003

Originally posted by: HDTVMan
LOL. Two things come to mind.

Where is the OMFG and ATI TAKEOVER statements?

I will gladly take a lowly only 16pipes working off one of the edges.

I believe that's another thread. This one is about ATI's successful tape out number 3.
Care to comment on the thread topic?

And, I am at a loss about what the bolded statement above means. Can you be a little more detailed? 16 pipe? Edges? Not sure what that means.

By the way, this doesn't mean that the R520 will get here any sooner than we discussed in the other thread. It means that the tape out is done and successful. We still have about 120 days to wait. Give or take.

I think he meant a cheap version of the R520 which has 16pipes and was "gotten" off the edge of the silicon waffer?


Did I win!!?

Yes one ATTABOY!.

 

[HDTVMan]

Originally posted by: bunnyfubbles
If it is indeed more than 600MHz it does make it hard to believe its more than 24 pipes - although 24+8 or some odd combo - but 32 and 600+MHz doesn't seem likely, you'd think it would flat out destroy the 7800GTX, even an Ultra would most likley be a futile counter attack.

600+MHz and 24 pipes with working and available crossfire solution upon launch seems the most likely/logical bet. A 24pipe part @ 600+MHz should give them the single card advantage, of which a 7800Ultra would feature a clock increase to close that gap. Then there'd be Crossfire to claim the multi GPU advantage nVidia has had with SLI. The only need for 32 pipes would be to attack SLI pretty much without Crossfire, especially at 600+MHz.

Although then there's the problem of such low yeilds, it doesn't seem likely they'd have so much trouble if the card wasn't going to be a beast. However more than 24 pipes and more than 600MHz sounds too good to be true, although if it is the price will definately come to match, I would expect over $600, $700-800 even... yikes.

24 or 32 it wont matter as long as there is something to challenge the 7800 then we can hope to see some price drops. The INQ also goes on about the 7800 going to 500 shortly too and a lower version of the 7800 street pricing at 400 meaning we can see some 6800 price drops coming also. Im even seeing the 6600gt cards going to 150 yesterday after rebate.

This is great I am looking forward to getting a new video card soon.

 

[Keysplayr]

Originally posted by: X

Originally posted by: keysplayr2003

Originally posted by: X
ATI doesn't need a 32 pipe card to compete with Nvidia at this point. If they can crank out a 24 pipe at 600+ mhz, they will have a winner. Great to hear that they are finally able to produce the R520 with acceptable yields.

X, not to rain on the parade just yet, but it was not specified if the poor yields were just for a particular piped card. 32 or 24. Just said yields were not that great but did not specify. So, theoretically, if the R520 was intended to be a 24 pipe card all along, then that would mean poor yields, although high clockspeed, on a 24 pipe R520. We need at least a glimpse of what the actual specs for R520 really are and were always intended to be by ATI. So, I am hoping they are only referring to a 32 pipe poor yield, but I have doubts of course.

As I read the article, it was poor yields that drove the retaping processes. Since the headline says the third retaping was successful, it seems logical that yields are now up to acceptable levels.

Ah, I see what your thinking. But a successful tape out does not automatically mean acceptable yield as the article says.

As it states: "IT TOOK ATI three tape-outs of R520 silicon to make it right but it turned out to be third time lucky. The first R520 silicon worked at high speeds but only few chips worked, we hear."

So, you can have a 100% successful tape out, but that does not mean good yields are guaranteed.

 

[Creig]

Originally posted by: keysplayr2003
Ah, I see what your thinking. But a successful tape out does not automatically mean acceptable yield as the article says.

As it states: "IT TOOK ATI three tape-outs of R520 silicon to make it right but it turned out to be third time lucky. The first R520 silicon worked at high speeds but only few chips worked, we hear."

So, you can have a 100% successful tape out, but that does not mean good yields are guaranteed.

No, it doesn't necessarily guarantee good yields. But from the statement about the first tapeout "but only few chips worked" to "third time lucky" it could be inferred that ATI is now satisfied.

I'm just crossing my fingers and toes that there isn't a FOURTH. I'd like to see what this card is all about sometime in the near future and how it stacks up against the 7800GTX.

 

[Keysplayr]

Originally posted by: Creig

Originally posted by: keysplayr2003
Ah, I see what your thinking. But a successful tape out does not automatically mean acceptable yield as the article says.

As it states: "IT TOOK ATI three tape-outs of R520 silicon to make it right but it turned out to be third time lucky. The first R520 silicon worked at high speeds but only few chips worked, we hear."

So, you can have a 100% successful tape out, but that does not mean good yields are guaranteed.

No, it doesn't necessarily guarantee good yields. But from the statement about the first tapeout "but only few chips worked" to "third time lucky" it could be inferred that ATI is now satisfied.

I'm just crossing my fingers and toes that there isn't a FOURTH. I'd like to see what this card is all about sometime in the near future and how it stacks up against the 7800GTX.

God a fourth?!? If word got out of a 4th tape out, you would see stock prices drop by the second. I have doubts there will be any more delays. Here's hoping.

 

[Creig]

Originally posted by: keysplayr2003
God a fourth?!? If word got out of a 4th tape out, you would see stock prices drop by the second. I have doubts there will be any more delays. Here's hoping.

I have a feeling you're right. News of a fourth would have the letters "WTF" popping up on website forums by the thousands. But by the sounds of it, three was enough.

 

[HDTVMan]

The article says it appears to have a lot of headroom for over 600mhz so with that being fixed even if they dont get good yields it means the chips design works. Just a little tweeking from here to get yields up.

 

[thecoolnessrune]

I thought 100% yields were impossible. I thought because things were produces so fast, there would always be some that didn't work. Just think, there may be hundreds of AMD X2 4800+ that could be sold for $250 because they ran 100 Mhz slower Or Pentium D 840 EE for $300. Or FX-57 for $400. Or 7800GTX for $150. Drools into supplied cup. Empties cup. repeats.

 

[Creig]

Originally posted by: thecoolnessrune
I thought 100% yields were impossible. I thought because things were produces so fast, there would always be some that didn't work. Just think, there may be hundreds of AMD X2 4800+ that could be sold for $250 because they ran 100 Mhz slower Or Pentium D 840 EE for $300. Or FX-57 for $400. Or 7800GTX for $150. Drools into supplied cup. Empties cup. repeats.

I don't think they meant they were getting 100% yields. As I read it, they meant their test yields are now high enough to support whatever price they have intended for the card.

 

[Concillian]

Originally posted by: TStep
Can anyone explain in layman's term what exactly is the "Tape out" process. Just a week ago, the third go around had just begin and it was going to delay shipment for month's and cost millions. Now it's announced that it is a success in a little over a week's time. How can this cost millions? Is there extensive modification required in the manufacturing tools that will cost time and money following the tape out, or does that 4-5 million dollar figure include projected lost profits? Confused.

I believe the 'tape out' process is the process of making all the masks necessary for the photoresist developing. These determine the topography of the chip.

They couldn't possibly go from taping out to finished product in a week given the complexity of the chip. It most certainly takes more than 7 days from start to finish of a wafer of chips of this caliber, probably more on the order of 2-3 weeks. However, who knows how far along in the process they were when the Inq published their last article.

The 'tape out' process nowadays is simply uploading a computer file to a machine that makes the masks. I would guess that the masks aren't incredibly expensive either, but that the primary cost comes in terms of the rental of TSMC fab time, labor and resources... and the wafers themselves.

I would presume the cost of a 'tape out' estimated by the Inq in the previous article includes:
- design costs for making the new revision
- the real 'tape out' process (making the masks, etc...)
- cost of TSMC resources to make the 'test batch'
- the cost of all involved reliability and yield testing necessary for the 'test batch'

I don't know for sure, but those are my guesses.

 

[Cooler]

All i can say is this card will cost at least $700-$800when ever it comes out and $900-$1000 for the 580 monster .The days of the cpu being the part that costs the most is coming to an end. If there is a fourth tap out then cost will also increase.