R520 has 16pipelines

Page 4 - Seeking answers? Join the AnandTech community: where nearly half-a-million members share solutions and discuss the latest tech.

Gamingphreek

Lifer
Mar 31, 2003
11,679
0
81
Originally posted by: KeepItRed
Ok? You just restated the whole thread...

Same thing i was thinking lol.

I dont know what looks good to you Intelia. At those clock speeds i highly doubt that this chip is going to be as efficient as past chips. They will (and probably are) dealing with power leakage, and huge power consumption. Moving to a 90nm architecture is not a miracle move, there are problems.

The fact is we dont know enough concrete detail to make any judgements yet. For all we know it could be 8 pipes (99% sure it isn't but, it is a rather extreme way to prove my point).

-Kevin
 

malG

Senior member
Jun 2, 2005
309
0
76
LOL...16-pipes...no wonder they aren?t even paper launching. The news is too disappointing. I can see the throngs of ATI fanboys, turning away after receiving the Word from Mount R520, returning to their keyboards to punch the "place order now" buttons after making a 7800GTX selection
 

kylebisme

Diamond Member
Mar 25, 2000
9,396
0
0
Originally posted by: malG
high MHz = high heat = dual slot cooling = high power consumption

And the fact that it is built on a smaller process; how does that add into your correlations?

Also, let us not forget:

This also comes as somewhat of a surprise since original leaked ATI documents claimed R420 would utilize 8 "Extreme" pipelines.

http://www.anandtech.com/video/showdoc.aspx?i=2018

So all you people jumping to conclusions might be wise to take a note from history and wait and see how things pan out.

 

kylebisme

Diamond Member
Mar 25, 2000
9,396
0
0
Originally posted by: malG
LOL...16-pipes...no wonder they aren?t even paper launching. The news is too disappointing. I can see the throngs of ATI fanboys, turning away after receiving the Word from Mount R520, returning to their keyboards to punch the "place order now" buttons after making a 7800GTX selection

Only for fools that don't understand that how many pipes a card has is only one of the many factors that determain overall performance. A one pipe card could kick everything elses ass assuming they figured out a way to make it run with a high enough frequency.
 

Gamingphreek

Lifer
Mar 31, 2003
11,679
0
81
Originally posted by: TheSnowman
Originally posted by: malG
LOL...16-pipes...no wonder they aren?t even paper launching. The news is too disappointing. I can see the throngs of ATI fanboys, turning away after receiving the Word from Mount R520, returning to their keyboards to punch the "place order now" buttons after making a 7800GTX selection

Only for fools that don't understand that how many pipes a card has is only one of the many factors that determain overall performance. A one pipe card could kick everything elses ass assuming they figured out a way to make it run with a high enough frequency.

A little bit extreme there eh
 

malG

Senior member
Jun 2, 2005
309
0
76
Originally posted by: TheSnowman
Originally posted by: malG
high MHz = high heat = dual slot cooling = high power consumption

And the fact that it is built on a smaller process; how does that add into your correlations?

A smaller process means zilch, just look at PressHot - 90nm and it's still hot and inefficient. Bear in mind that Intel is 1000 times bigger than ATI and Intel took sometime to master the 90nm process.

 

malG

Senior member
Jun 2, 2005
309
0
76
Originally posted by: TheSnowman
Originally posted by: malG
LOL...16-pipes...no wonder they aren?t even paper launching. The news is too disappointing. I can see the throngs of ATI fanboys, turning away after receiving the Word from Mount R520, returning to their keyboards to punch the "place order now" buttons after making a 7800GTX selection

Only for fools that don't understand that how many pipes a card has is only one of the many factors that determain overall performance. A one pipe card could kick everything elses ass assuming they figured out a way to make it run with a high enough frequency.

That was a joke, only fanboys like you would've felt offended

 

coldpower27

Golden Member
Jul 18, 2004
1,676
0
76

I don't think anyone had problem free transistions to the 90nm process, the process has been quite a letdown for CPU manufacturers in terms of how much clock frequency it could push out.

AMD doesn't really count as they benefited greatly from the experiences IBM had on their 90nm transistion. Who's helping ATI on their 90nn transition? I hope NV doesn't have too many problems with their transistion, hopefully build mainstream / budget parts on this process will give them good experience with it.

Intel was able to eke out 400MHZ more from a Prescott 3.8GHZ from Northwood C 3.4 GHZ.
Intel was able to eke out 526MHZ more from Dothan 2.26 GHZ from a Banias 1.7GHZ which is decent, but not awe dropping.

AMD so far has been able to eke out 200MHZ from a Athlon FX 57 San Diego vs Athlon FX 55 Clawhammer. Though AMD 90nm process is gonna be used for some more time by the looks of things.

If the R520 is so cool, why the rumors of a refererence design Dual Slot cooler? Since ATI is the first to transistion to 90nm I don't expect it to be problem free. But there is always hope.
 

Sentential

Senior member
Feb 28, 2005
677
0
0
What what I do know it wasnt an issue of the process but the tools building them. I belive Intel has almsot fully re-tooled which is why their .65nm process is much better and supposedly their .45nm process "fixed" the leakage issue
 

kylebisme

Diamond Member
Mar 25, 2000
9,396
0
0
Originally posted by: malG
Originally posted by: TheSnowman
Originally posted by: malG
high MHz = high heat = dual slot cooling = high power consumption

And the fact that it is built on a smaller process; how does that add into your correlations?

A smaller process means zilch, just look at PressHot - 90nm and it's still hot and inefficient. Bear in mind that Intel is 1000 times bigger than ATI and Intel took sometime to master the 90nm process.

The 90nm procces obviously wasn't enough to keep the Prescott cool, but the exception doesn't define the rule. Quoted for an article right here at Anandtech:

By shrinking the process, less heat is produced at higher clock speeds.

http://www.anandtech.com/printarticle.aspx?i=1406

 

coldpower27

Golden Member
Jul 18, 2004
1,676
0
76
Originally posted by: Sentential
What what I do know it wasnt an issue of the process but the tools building them. I belive Intel has almsot fully re-tooled which is why their .65nm process is much better and supposedly their .45nm process "fixed" the leakage issue

From the rumors Intel has reduced greatly leakage problems on the 65nm process, with the 45nm process having "fixed" the leakage issue. This probably means they have reduced leakeage to neligible levels on the 45nm process, as leakage us always there, it just isn't a problem when itis at really low levels.
 

jasonja

Golden Member
Feb 22, 2001
1,864
0
0
Originally posted by: coldpower27

I don't think anyone had problem free transistions to the 90nm process, the process has been quite a letdown for CPU manufacturers in terms of how much clock frequency it could push out.

AMD doesn't really count as they benefited greatly from the experiences IBM had on their 90nm transistion. Who's helping ATI on their 90nn transition? I hope NV doesn't have too many problems with their transistion, hopefully build mainstream / budget parts on this process will give them good experience with it.

Intel was able to eke out 400MHZ more from a Prescott 3.8GHZ from Northwood C 3.4 GHZ.
Intel was able to eke out 526MHZ more from Dothan 2.26 GHZ from a Banias 1.7GHZ which is decent, but not awe dropping.

AMD so far has been able to eke out 200MHZ from a Athlon FX 57 San Diego vs Athlon FX 55 Clawhammer. Though AMD 90nm process is gonna be used for some more time by the looks of things.

If the R520 is so cool, why the rumors of a refererence design Dual Slot cooler? Since ATI is the first to transistion to 90nm I don't expect it to be problem free. But there is always hope.

How about TSMC? Considering they are making it I'm betting they are helping ATI with it Last I checked they knew a thing or two about making ASICs.

It hasn't been problem free! They've been delayed signficantly to overcome issues that's why they were late to the party. But who's to say that everything hasn't been hashed out now and things are kicking?
 

kylebisme

Diamond Member
Mar 25, 2000
9,396
0
0
Originally posted by: malG
Originally posted by: TheSnowman
Originally posted by: malG
LOL...16-pipes...no wonder they aren?t even paper launching. The news is too disappointing. I can see the throngs of ATI fanboys, turning away after receiving the Word from Mount R520, returning to their keyboards to punch the "place order now" buttons after making a 7800GTX selection

Only for fools that don't understand that how many pipes a card has is only one of the many factors that determain overall performance. A one pipe card could kick everything elses ass assuming they figured out a way to make it run with a high enough frequency.

That was a joke, only fanboys like you would've felt offended

Jokes are funny when they have truth to them, your "joke" is comptetly void of that.
 

malG

Senior member
Jun 2, 2005
309
0
76
Originally posted by: coldpower27


If the R520 is so cool, why the rumors of a refererence design Dual Slot cooler?

It's not a rumour, it's a fact. Here are photos from ATI Launch Event in Sydney (yesterday) showing an actual R520 in dual slot. :thumbsdown:

 

kylebisme

Diamond Member
Mar 25, 2000
9,396
0
0
Perosnally, I don't see any reason not to go dual slot when most motherboards these days don't even have a socket for the slot under the videocard. I'd rather kick any heat off the video card directly out of my case instead of letting it add to the rest of the system.
 

KeepItRed

Senior member
Jul 19, 2005
811
0
0
Originally posted by: malG
Originally posted by: coldpower27


If the R520 is so cool, why the rumors of a refererence design Dual Slot cooler?

It's not a rumour, it's a fact. Here are photos from ATI Launch Event in Sydney (yesterday) showing an actual R520 in dual slot. :thumbsdown:

I'm quite weiry about that. I couldn't tell a single difference between the X850 > X850XTPE by looking at it. Besides there's still rumours the R520 will look similar to the X850, so I think those are just X850's in Crossfire. (could be wrong though)
 

malG

Senior member
Jun 2, 2005
309
0
76
Originally posted by: KeepItRed
Originally posted by: malG
Originally posted by: coldpower27


If the R520 is so cool, why the rumors of a refererence design Dual Slot cooler?

It's not a rumour, it's a fact. Here are photos from ATI Launch Event in Sydney (yesterday) showing an actual R520 in dual slot. :thumbsdown:

I'm quite weiry about that. I couldn't tell a single difference between the X850 > X850XTPE by looking at it. Besides there's still rumours the R520 will look similar to the X850, so I think those are just X850's in Crossfire. (could be wrong though)

Perhaps you're right but the R520 dual slot cooler is also confirmed by AT: http://www.anandtech.com/video/showdoc.aspx?i=2501

 

coldpower27

Golden Member
Jul 18, 2004
1,676
0
76
Originally posted by: KeepItRed
Originally posted by: malG
Originally posted by: coldpower27


If the R520 is so cool, why the rumors of a refererence design Dual Slot cooler?

It's not a rumour, it's a fact. Here are photos from ATI Launch Event in Sydney (yesterday) showing an actual R520 in dual slot. :thumbsdown:

I'm quite weiry about that. I couldn't tell a single difference between the X850 > X850XTPE by looking at it. Besides there's still rumours the R520 will look similar to the X850, so I think those are just X850's in Crossfire. (could be wrong though)


Which one of those is R520? All I thought I was looking at were X850 XT PE's either in Crossfire or not?
 

Gamingphreek

Lifer
Mar 31, 2003
11,679
0
81
Yes but is it working/running. Anyone moron can make a pcb and stick some voltage regulators and capacitors on it with a nice flashy heatsink.

Additionally, if it was working/running, was it working correctly. While it is harder than my first comment, if the card wasn't working to well, more times than not they can get it working just enough that it can render some images. (Running well includes power consumption and heat output)

Finally, if all those are true can you verify that it is indeed the R520 and not an X850 that is slightly different looking or something such as that.

We need some concrete answers, we, the average consumer, simply dont have enough concrete information.

-Kevin
 

nitromullet

Diamond Member
Jan 7, 2004
9,031
36
91
Originally posted by: TheSnowman
Perosnally, I don't see any reason not to go dual slot when most motherboards these days don't even have a socket for the slot under the videocard. I'd rather kick any heat off the video card directly out of my case instead of letting it add to the rest of the system.

I agree on this. I've never understood this. I mean, sure the GTX is single slot, but in the other direction it's huge. I've had my eye on a Lian Li V1000 or 1200 for this exact reason. I pretty much can't work on anything in my rig with the GTX's installed, even simple stuff, like plugging/unplugging an SATA cable on the mobo. So, why not make it dual slot and exhaust the air out the back..? Those cards have already monopolized my system.

Anyway according to the inquirer heres what we got that inspired this chat .

16 pipes(extreme)
700 to 800Mhz for the sake of argument lets say 750 MHz core
1400MGz memory (maybe1600Mhz)

Looks good to me

The biggest thing that seems flakey about those specs is the memory speed, especially 1600. If RAM this fast exists in any quantity, it's doubtful that there would be enough to go around for mass production. Couple that with the rumors of a 512MB card, and you're easlity talking about a $700-800 MSRP.
 

bunnyfubbles

Lifer
Sep 3, 2001
12,248
3
0
Why are people still making a big deal of dual slot coolers? Just about every enthusiast motherboard I know of allows for dual slot video cards without sacficing another slot. The only major downside worth concern that I can see is that its there to cool a very hot chip ala 5800U. Hot isn't so bad, but hot usually means loud. Unless they've gone with a dual slot cooler to reduce noise vs. a similar single slot cooler.

If performance isn't in clear favor of the R520, then that will definately be a big factor against ATI, otherwise this "inefficient design" could be worthy if it is indeed clearly faster than the competition, it would just be a sacrifice you'd have to make. Heat/noise for performance. People would be so against Prescotts/PDs if they were actually faster than the competition.
 

Spoonbender

Junior Member
Aug 13, 2005
8
0
0
True, dual slot is no big deal, except for one thing. The fact that NVidia is able to cool their card without it, and ATI obviously isn't, seems to suggest that NVidia has a lot more headroom for future speed increases. (the higher number of pipelines would also seem to support this, as less extreme clock speeds are required in the first place.
Then there are ATI's countless problems with manufacturing the thing, which also seems to suggest that power consumption/leakage was out of control. No doubt that's improved by now, but it does point towards, well, the GPU equivalent of a Prescott...
That's not to say it won't be fast, but it sure doesn't look efficient.

And images or no, ATI has explicitly said that the R520 will be dualslot.
 

Killrose

Diamond Member
Oct 26, 1999
6,230
8
81
Originally posted by: Spoonbender
True, dual slot is no big deal, except for one thing. The fact that NVidia is able to cool their card without it, and ATI obviously isn't, seems to suggest that NVidia has a lot more headroom for future speed increases. (the higher number of pipelines would also seem to support this, as less extreme clock speeds are required in the first place.
Then there are ATI's countless problems with manufacturing the thing, which also seems to suggest that power consumption/leakage was out of control. No doubt that's improved by now, but it does point towards, well, the GPU equivalent of a Prescott...
That's not to say it won't be fast, but it sure doesn't look efficient.

And images or no, ATI has explicitly said that the R520 will be dualslot.

Nvidias cards are way longer, which these days is worse than a 2-slot card. PCI-e has room between slots and PCI devices have for the most part been replaced by on-board everything, so loosing a PCI slot is not a big deal.

Ati 2-slot design means you have the hot GPU air being exhausted from the case. Not at all like my 2-slot 6800Ultra which is still pushing hot GPU cooling air back into the case. It all depends how 2-slot is implemented.

 

ZobarStyl

Senior member
Mar 3, 2004
657
0
0
16 is definitely looking bad for ATi, considering it took 3 tries to get it right. If it had been 32 pipe, multiple retapes would make sense to get the fully working pipes in good yields, but if it's just 16, that likely means they had to keep trying to get it to clock high enough just to compete, despite already having dual slot coolers. More and more like NV30 every day, that's a shame. The sheer mhz this thing is going to need to really compete (i.e. seriously outdo the GTX, since it's late to the game) is phenomenal, and may be beyond possibility. Hope the 90 nm process pulls out some good midrange competitors for them, otherwise it appears they are in for some losses.
 

bunnyfubbles

Lifer
Sep 3, 2001
12,248
3
0
Originally posted by: Spoonbender
True, dual slot is no big deal, except for one thing. The fact that NVidia is able to cool their card without it, and ATI obviously isn't, seems to suggest that NVidia has a lot more headroom for future speed increases. (the higher number of pipelines would also seem to support this, as less extreme clock speeds are required in the first place.
Then there are ATI's countless problems with manufacturing the thing, which also seems to suggest that power consumption/leakage was out of control. No doubt that's improved by now, but it does point towards, well, the GPU equivalent of a Prescott...
That's not to say it won't be fast, but it sure doesn't look efficient.

And images or no, ATI has explicitly said that the R520 will be dualslot.


http://www.anandtech.com/video/showdoc.aspx?i=2501

R520XT dual slot
R520XL single slot

hmm... XL 700MHz and XT 800MHz?

700MHz x 16 = 11,200 vs. 430MHz x 24 = 10,320
800MHz x 16 = 12,800 vs. 530MHz x 24 = 12,720

Ofcourse this is all just speculation, if the 700MHz clock speed is true (with possible higher), then a 16 pipe part could very well compete with the 24pipe 7800GTX. If there is an 800MHz XT to come, then nVidia would need to also up their GPU core by 100MHz to match it and release a 7800Ultra. If 700MHz is true with any more pipes (more than 16), then nVidia would definately lose the performance crown.
 
sale-70-410-exam    | Exam-200-125-pdf    | we-sale-70-410-exam    | hot-sale-70-410-exam    | Latest-exam-700-603-Dumps    | Dumps-98-363-exams-date    | Certs-200-125-date    | Dumps-300-075-exams-date    | hot-sale-book-C8010-726-book    | Hot-Sale-200-310-Exam    | Exam-Description-200-310-dumps?    | hot-sale-book-200-125-book    | Latest-Updated-300-209-Exam    | Dumps-210-260-exams-date    | Download-200-125-Exam-PDF    | Exam-Description-300-101-dumps    | Certs-300-101-date    | Hot-Sale-300-075-Exam    | Latest-exam-200-125-Dumps    | Exam-Description-200-125-dumps    | Latest-Updated-300-075-Exam    | hot-sale-book-210-260-book    | Dumps-200-901-exams-date    | Certs-200-901-date    | Latest-exam-1Z0-062-Dumps    | Hot-Sale-1Z0-062-Exam    | Certs-CSSLP-date    | 100%-Pass-70-383-Exams    | Latest-JN0-360-real-exam-questions    | 100%-Pass-4A0-100-Real-Exam-Questions    | Dumps-300-135-exams-date    | Passed-200-105-Tech-Exams    | Latest-Updated-200-310-Exam    | Download-300-070-Exam-PDF    | Hot-Sale-JN0-360-Exam    | 100%-Pass-JN0-360-Exams    | 100%-Pass-JN0-360-Real-Exam-Questions    | Dumps-JN0-360-exams-date    | Exam-Description-1Z0-876-dumps    | Latest-exam-1Z0-876-Dumps    | Dumps-HPE0-Y53-exams-date    | 2017-Latest-HPE0-Y53-Exam    | 100%-Pass-HPE0-Y53-Real-Exam-Questions    | Pass-4A0-100-Exam    | Latest-4A0-100-Questions    | Dumps-98-365-exams-date    | 2017-Latest-98-365-Exam    | 100%-Pass-VCS-254-Exams    | 2017-Latest-VCS-273-Exam    | Dumps-200-355-exams-date    | 2017-Latest-300-320-Exam    | Pass-300-101-Exam    | 100%-Pass-300-115-Exams    |
http://www.portvapes.co.uk/    | http://www.portvapes.co.uk/    |