Radeon HD 7000 Revealed: AMD to Mix GCN with VLIW4 & VLIW5 Architectures

[LordEC911]

As much as I hate doing it... I am about to pull a saaya.

VLIW4 is better than VLIW5 isnt it? Something about the extra overhead or whatever.

Compute capabilities.

But GCN sounds like a very big chip from his description and with a lot of potential. Let's hope the thermals don't spoil it.

Smaller than Cayman.

Also for the TL: DR Crowd:

It is more BS from BS.

A straight-up Cayman shrink shouldn't be too hard...

There is no straight Cayman shrink.

According to neliz at beyond3d, its rumored that we won't see an increase in transistor to performance from NV or AMD.

That generally doesn't happen unless something went terribly wrong the previous gen... *cough*R600*cough*
As you move away from fixed units to slightly more generalized units you have to, unfortunately, give up some transistor efficiency.

What happened to my XDR2?

It was never going to happen.

Plus, there isn't that much volume production of it and the prices of it are much higher than GDDR5... MUCH higher.

How about no volume production...
It is hard for a certain company to get "partners" to manufacture their product when they sue them left and right.

Here we go with the wild, over inflated hopes and dreams of some.....again.

Don't worry, you will get your card soon enough.

So it has been confirmed the 7970 has a 384 bit memory bus?

Pretty much, if you believe Charlie.

Neliz? That guy promised a bunch of stuff in regards to the Cayman GPUs verse the GTX 580 when it launched. I'm not really going to bother paying attention to his input after that.

Quotes please. He was pretty much on the money with most of his info.
When you have better tidbits than him please post them.

A rumor is never a solid fact.

True but some rumors are better than others.

so yur thinking the HD 7000 will be a flop?

http://www.xtremesystems.org/forums/...=1#post4999710

... and VILW4 in 28nm for the rest ? something new i have miss ? ( outside it is now confirmed, all the press will be brief during december )

No. Pitcairn is GCN. The midrange/lowend is what is questionable.
There are at least 3 28nm ASICs and the 40nm lowend rebrands are 40nm.

[Dimitriman]

Here we go with the wild, over inflated hopes and dreams of some.....again.

Guessing on a die shrunk Cayman as the 7870 is possibly the safest bet anyone could make though. I don't see it going any other way and it does sound like a fantastic product for 250 squid.

[flopper]

The lack of faith for amd is disturbing.
It be a fast, good and awesome series with good power/performance ratio that dosnt blow a hole in the socket in the wall.

[SKYMTL]

so yur thinking the HD 7000 will be a flop?

Absolutely not.

What I am saying is this: there is no reason to start or listen to any wild assumptions about pricing, performance or market orientation. They only way ANYONE will know the true potential of an upcoming product is when the first REAL reviews go live with a full suite of applications and using final drivers. Up until that point, everything is just background noise which will likely set people up for a disappointment.

I've said it many times and I will say it again here. There is a natural progression of these threads that goes something like this:

- Site A ensures they get plenty of traffic by posting supposed "inside info" about a product
- The excitement and wild assumptions begin
- Forum poster A will make some posts that look legit and draw the attention of the community (eg: neilz with Cayman and Barts or a certain unnamed forum member here -not JF- with Bulldozer)
- Yet more chest beating and assumptions ensue
- The launch draws near and people have completely the wrong idea about said product, its price and performance.
- Reviews are posted and the same people who built up the product in their heads as the Second Coming cry foul. "Too expensive", "where's the promised performance?" and "I'll wait for xxxx" are the usual responses.

There is something very important everyone needs to remember about pricing in particular. If a graphics card outperforms another, it WILL be more expensive. Simple as that. For example, if (and this is totally an example) the HD 7800 or whatever it will be called performs just above a HD 6970, expect it to be priced accordingly (ie: proportionally above the HD 6970's relative performance). Anything else would be market suicide for AMD.

In addition, I am sure we will once again see a ton of misinformation thrown around by various sites and forum posters prior to any GPU launch. There will invariably be some that after launch point to themselves and a small portion of their pre-launch assumptions and say "I told you so". Well, there is a good analogy for that: even a blind squirrel finds a nut once in a while.

[phantomferrari]

The lack of faith for amd is disturbing.
It be a fast, good and awesome series with good power/performance ratio that dosnt blow a hole in the socket in the wall.

i think some people need to be force choked

[xBanzai89]

Quotes please. He was pretty much on the money with most of his info.
When you have better tidbits than him please post them.


True but some rumors are better than others.

All I remember last year at this time of the month was everyone getting hyped about the 1920 SP 6970. I don't know if Neliz fed all of that, but I am pretty sure he contributed to it. I swear I remember him being quoted as saying the Cayman Pro was going to outdo the GTX 480 at least. Then that all came crashing down on launch day.

Rumor is a rumor. I will read it, but I am not going to just assume it is correct anymore regardless of how good the source is. Cayman and BD were a perfect example of this. BD was suppose to at least level the playing ground, but it went in reverse and those guys posting up the lackluster benchmarks were correct as opposed to some experts saying otherwise.

[SKYMTL]

The lack of faith for amd is disturbing.
It be a fast, good and awesome series with good power/performance ratio that dosnt blow a hole in the socket in the wall.

I haven't seen anyone with a lack of faith in AMD. Remember, asking for caution before jumping to assumptions is NOT a lack of faith, it is common sense.

[[XC] gomeler]

Absolutely not.

What I am saying is this: there is no reason to start or listen to any wild assumptions about pricing, performance or market orientation. They only way ANYONE will know the true potential of an upcoming product is when the first REAL reviews go live with a full suite of applications and using final drivers. Up until that point, everything is just background noise which will likely set people up for a disappointment.

I've said it many times and I will say it again here. There is a natural progression of these threads that goes something like this:

- Site A ensures they get plenty of traffic by posting supposed "inside info" about a product
- The excitement and wild assumptions begin
- Forum poster A will make some posts that look legit and draw the attention of the community (eg: neilz with Cayman and Barts or a certain unnamed forum member here -not JF- with Bulldozer)
- Yet more chest beating and assumptions ensue
- The launch draws near and people have completely the wrong idea about said product, its price and performance.
- Reviews are posted and the same people who built up the product in their heads as the Second Coming cry foul. "Too expensive", "where's the promised performance?" and "I'll wait for xxxx" are the usual responses.

There is something very important everyone needs to remember about pricing in particular. If a graphics card outperforms another, it WILL be more expensive. Simple as that. For example, if (and this is totally an example) the HD 7800 or whatever it will be called performs just above a HD 6970, expect it to be priced accordingly (ie: proportionally above the HD 6970's relative performance). Anything else would be market suicide for AMD.

In addition, I am sure we will once again see a ton of misinformation thrown around by various sites and forum posters prior to any GPU launch. There will invariably be some that after launch point to themselves and a small portion of their pre-launch assumptions and say "I told you so". Well, there is a good analogy for that: even a blind squirrel finds a nut once in a while.

You are screaming into the wind.

[SKYMTL]

You are screaming into the wind.

I know. But it feels good.

[Lanek]

You are screaming into the wind.

Still better of the other way ...

[ohnoitseddy]

And for some more screaming:

These numbers almost perfectly match those that came with the initial "XDR2" crap (which in turn was from some Chineese forum somewhere... Not quite what one would call "trustworthy"). Just have a look here: http://www.nordichardware.com/news/7...us-memory.html (Do note that article is from September.) So it seems like BSN's "sources" simply took that info and changed the memory to make it look a little more believeable. Nonetheless it should be seen as fake and false, as the data still came out of nowhere originally.

[SKYMTL]

Actually, those slides in the BSN article are from the Fusion Developer Summit.

Looking at the rendering paths and listening to Eric's keynote, the core layout shown is quite obviously for an implementation as a Fusion IGP rather than discrete desktop parts.

So these aren't the *ahem*....discrete parts..... you are looking for. Nonetheless, I am sure there will be a ton of similarities somewhere down the line.

[[XC] hipno650]

I could really care less about all the speculation on specs and whatnot that are being thrown around. I would be more interested in this rumored "launch date" it seems a little soon to just more or less show up without any lower end parts on the new process first but I will be at CES 2012 so seeing these would be a bonus... i don't have high hopes however to see it by then...

[Pantsu]

If there really is a press briefing in december it's certainly possible that 7900 could be released in january. I guess we'll see soon after the leaks start pouring in, whether they are accurate or not.

[Sentential]

I find it odd that for a card that is to be released in less than one month's time we still have yet to see PCBs or die shots leaked. Something feels amiss; to be honest I think it is delayed much like Kepler is.

I could be wrong but you'd think we would have seen more information by now.

[SKYMTL]

I could really care less about all the speculation on specs and whatnot that are being thrown around. I would be more interested in this rumored "launch date" it seems a little soon to just more or less show up without any lower end parts on the new process first but I will be at CES 2012 so seeing these would be a bonus... i don't have high hopes however to see it by then...

Launch date means nothing IMO. I'm more concerned about the timeframe in which consumers will actually be able to buy the next gen cards en masse.

[BababooeyHTJ]

I find it odd that for a card that is to be released in less than one month's time we still have yet to see PCBs or die shots leaked. Something feels amiss; to be honest I think it is delayed much like Kepler is.

I could be wrong but you'd think we would have seen more information by now.

Now that you bring up Kepler I have to admit that I am a bit concerned that AMD is going to do what they did with the 5xxx series and not really move the bar for price vs performance at all due to the lack of competition.

[LordEC911]

Now that you bring up Kepler I have to admit that I am a bit concerned that AMD is going to do what they did with the 5xxx series and not really move the bar for price vs performance at all due to the lack of competition.

Why would they hurt their own margins as well as AIBs when they can price it accordingly to the market and maybe slightly undercut Nvidia with competing products?

As much as I would love GTX580 performance out of a $200 product at the end of the day AMD is a business and has to milk some cash where they can and when they can. This has been said in these forums quite a few times before.

[Mechromancer]

I just hope Stanford will finally come out with a damned F@H client that takes FULL advantage of AMD's uArch this time. I've been waiting every generation of GPU since the 2900XT....................


...................................


.........................


......That is a long fuggin' time.

[Lanek]

Actually, those slides in the BSN article are from the Fusion Developer Summit.

Looking at the rendering paths and listening to Eric's keynote, the core layout shown is quite obviously for an implementation as a Fusion IGP rather than discrete desktop parts.

So these aren't the *ahem*....discrete parts..... you are looking for. Nonetheless, I am sure there will be a ton of similarities somewhere down the line.

You completely mix the report made by Eric D on the last days, and what have been shown during the event..... this was 2 things completely different. Demers was just made a compilation of it... all the parts about GCN have been excluded of it.

[Sentential]

Now that you bring up Kepler I have to admit that I am a bit concerned that AMD is going to do what they did with the 5xxx series and not really move the bar for price vs performance at all due to the lack of competition.

I agree and raise you this; I'm afraid that they are focusing too much on compute performance like nVidia did with Fermi thereby causing what you described above.

[SKYMTL]

You completely mix the report made by Eric D on the last days, and what have been shown during the event..... this was 2 things completely different. Demers was just made a compilation of it... all the parts about GCN have been excluded of it.

No.

[paulbagz]

Absolutely not.

What I am saying is this: there is no reason to start or listen to any wild assumptions about pricing, performance or market orientation. They only way ANYONE will know the true potential of an upcoming product is when the first REAL reviews go live with a full suite of applications and using final drivers. Up until that point, everything is just background noise which will likely set people up for a disappointment.

HA!

I tried saying that about Ivy Bridge and I got slayed for it.

-PB

[BababooeyHTJ]

Why would they hurt their own margins as well as AIBs when they can price it accordingly to the market and maybe slightly undercut Nvidia with competing products?

As much as I would love GTX580 performance out of a $200 product at the end of the day AMD is a business and has to milk some cash where they can and when they can. This has been said in these forums quite a few times before.

They also lost a sale with me with the 5xxx series and I'm sure that I'm not alone. I just saw no reason to upgrade my video card. They didn't move the price vs performance bar at all really. They really had a chance to gain a bigger chunk of the market share but that didn't really happen.

[Iconyu]

HA!

I tried saying that about Ivy Bridge and I got slayed for it.

-PB

No, we were telling people not to have high expectations about IB performance per clock, you said that we hadn't seen any numbers and we couldn't know for sure, but numbers had been leaked months ago. Ivy Bridge performs as expected.