AMD Polaris architecture – GCN 4.0

[ICDP]

@ICDP: You really don't know what trolling is.

Ironic post is ironic. Here let me help

https://en.wikipedia.org/wiki/Irony

Now for the definition of an internet troll.

In Internet slang, a troll (/ˈtroʊl/, /ˈtrɒl/) is a person who sows discord on the Internet by starting arguments or upsetting people, by posting inflammatory,[1] extraneous, or off-topic messages in an online community (such as a newsgroup, forum, chat room, or blog) with the deliberate intent of provoking readers into an emotional response[2] or of otherwise disrupting normal on-topic discussion.

You deliberately misquoted someone with the intent of provoking a response. I call that trolling.

 

[CAT-THE-FIFTH]

OFC,if AMD is going for smaller dies close to 300mm2 than 400mm2 to do another HD4000 moment we could see a smaller performance bump. Even something like a 20% improvement over a Fury X at £300 to £375 might be decent.

The other aspect is with HBM2 having 8GB stacks we could see different SKUs maybe with different memory bandwidth too.

 

[Davedree]

Ironic post is ironic. Here let me help

https://en.wikipedia.org/wiki/Irony

Now for the definition of an internet troll.



You deliberately misquoted someone with the intent of provoking a response. I call that trolling.

You could say that yes, however if you've followed his comments over the years in other threads, then his fear in stagnation over mid range cards holds some truth.

However people are jumping in the air with too much excitement in this thread when nothing has been given away in the specification of this demoed chip.
If the smaller polaris is around 1536-2048 shaders and is the pitcairn replacement but scales with clocking them with the improvements it could be edging a 7950, which is where a gm206 nearly performs.

If that means the bigger polaris is 300-400mm2 then it leaves scope for a similar 3584/4096 but more refined fury II.

 

[bru]

It needs to be compared to whatever Nvidia has out at the time it launches.

Well on that basis whoever releases first wins, even if they are released a day apart.

However people are jumping in the air with too much excitement in this thread when nothing has been given away in the specification of this demoed chip.

Exactly this, we know nothing because they didn't want to tell us anything concrete.

All we know is there is two GPU's one of which was shown to be on a small card, which the press was told powered the machine, in the power sipping demo against a 950. the other is a bigger chip.

Those are the facts. More than that is pure guesswork, still fun though.

 

[Overlag]

Are these out yet? Bored of waiting already

me too, and just as my 7970 is starting to die (i mined 24/7 on it), I NEED a new GPU now, not in summer.

 

[ICDP]

You could say that yes, however if you've followed his comments over the years in other threads, then his fear in stagnation over mid range cards holds some truth.

However people are jumping in the air with too much excitement in this thread when nothing has been given away in the specification of this demoed chip.
If the smaller polaris is around 1536-2048 shaders and is the pitcairn replacement but scales with clocking them with the improvements it could be edging a 7950, which is where a gm206 nearly performs.

If that means the bigger polaris is 300-400mm2 then it leaves scope for a similar 3584/4096 but more refined fury II.

FoxEye is not talking about stagnation. He has been deliberately obtuse by claiming as fact that AMD Polaris is only going to be low and mid-range GPUs in 2016 with a mythical high end Polaris being delayed until 2017. Nowhere in any of the articles available is that even remotely being claimed. It has been pretty much confirmed that Polaris will be released to cover from low end right up to enthusiast.

He has taken his own perspective on the existing info and extrapolated to conclude and parade as fact that the high-end Polaris in 2016 will equal or only slightly beat a Fury X.

 

[Boomstick777]

AMD’s Flagship GPU “Greenland” Is Vega10 – Future GPUs To Be Named After Stars And Galaxies

Read more: http://wccftech.com/amd-future-gpus...ids-farewell-island-code-names/#ixzz3xhsxgkD7

 

[HardStyler3]

all guys talking about the little chip showcased for laptops and stuff xD

dont you guys know that amd showcased the higher version behind doors to some journalists but not official

 

[Orangey]

"Samsung Electronics announced that it has begun mass producing the industry’s first 4-gigabyte (GB) DRAM package based on the second-generation High Bandwidth Memory (HBM2) interface, for use in high performance computing (HPC), advanced graphics and network systems, as well as enterprise servers. Samsung’s new HBM solution will offer unprecedented DRAM performance – more than seven times faster than the current DRAM performance limit, allowing faster responsiveness for high-end computing tasks including parallel computing, graphics rendering and machine learning"

full samsung press release here

about time, now we got HBM2 ready, so high end GPUs might actualy be possible in 2016.

These companies have a very loose definition of "mass production has begun". I hope it's for real and they have solved whatever problems caused shortages before.

 

[pete910]

Are these out yet? Bored of waiting already

Your bored after a week of putting a new GPU in

 

[Orangey]

FoxEye is not talking about stagnation. He has been deliberately obtuse by claiming as fact that AMD Polaris is only going to be low and mid-range GPUs in 2016 with a mythical high end Polaris being delayed until 2017. Nowhere in any of the articles available is that even remotely being claimed. It has been pretty much confirmed that Polaris will be released to cover from low end right up to enthusiast.

He has taken his own perspective on the existing info and extrapolated to conclude and parade as fact that the high-end Polaris in 2016 will equal or only slightly beat a Fury X.

Exactly. Also he belives any wccf garbage he reads no questions asked and constantly mistakes clickbait rumour for official AMD statement.

 

[Davedree]

FoxEye is not talking about stagnation. He has been deliberately obtuse by claiming as fact that AMD Polaris is only going to be low and mid-range GPUs in 2016 with a mythical high end Polaris being delayed until 2017. Nowhere in any of the articles available is that even remotely being claimed. It has been pretty much confirmed that Polaris will be released to cover from low end right up to enthusiast.

He has taken his own perspective on the existing info and extrapolated to conclude and parade as fact that the high-end Polaris in 2016 will equal or only slightly beat a Fury X.

I totally understand your point and you're not wrong about foxeye's conjecture and selected text, but you are also only commenting on his rolling eyes in response to a certain person typing a weird future is bright caption. Foxeye has talked about stagnation in other threads which follows up with his viewpoint in this thread. He may be right he hopefully is wrong lol but at this stage we can only wait for the hardware to turn up to evaluate. End of the day I myself will admit to going off topic for a page and whilst i've made some comments in this thread. It's all a guessing game until the big reveal.

 

[FoxEye]

FoxEye is not talking about stagnation. He has been deliberately obtuse by claiming as fact that AMD Polaris is only going to be low and mid-range GPUs in 2016 with a mythical high end Polaris being delayed until 2017. Nowhere in any of the articles available is that even remotely being claimed. It has been pretty much confirmed that Polaris will be released to cover from low end right up to enthusiast.

He has taken his own perspective on the existing info and extrapolated to conclude and parade as fact that the high-end Polaris in 2016 will equal or only slightly beat a Fury X.

What do you believe?

AMD said "two new GPUS". We know one is tiny; the other one we know is more powerful.

Do you believe there is going to be - this year - a big Polaris GPU? Ie, there will be three GPUs, and that AMD themselves simply can't count?

Or do you think that the bigger gpu of the two will beat a FuryX by 40-50%?

You seem certain that my speculation is utterly wrong. So therefore you must have some ideas yourself of how things will be.

Let's hear them then. I'm getting bored of you just **** talking my posts and doing nothing constructive in this thread. And you call /me/ the troll.

 

[FoxEye]

One other thing. Why is it that on other forums (like anand) you can speculate to your heart's content, and nobody gets upset?

The zealotry in this place is a truly bizarre thing to behold. The number of people who will get upset, enraged, practically foaming at the mouth... all over a bit of harmless speculation.

And yes, it's totally harmless. Beyond people getting unreasonably defensive over their favourite GPU maker, nobody is doing any damage here, even if we get it all wrong.

I'm not sure whether to laugh or cry when I come here. It really is totally off the rails compared to just about any other tech forum. Insults, tantrums, accusations... in just about every thread!

Frankly it's a joke, and I'm sure many people will be put off posting here because of how certain people will jump on them if they disagree.

 

[~Mike~]

Are these out yet? Bored of waiting already

I got bored of having to trawl through the crap posted in this thread to see if there was anything worth reading.

 

[andybird123]

I got bored of having to trawl through the crap posted in this thread to see if there was anything worth reading.

Then don't, 99% of anything interesting on this forum gets posted to a new thread. If banter annoys you just stick to reading opening posts.

 

[Gregster]

I got bored of having to trawl through the crap posted in this thread to see if there was anything worth reading.

You seem to post that quite a bit in this sub section.

 

[Overlag]

You seem to post that quite a bit in this sub section.

probably because its true? We've had 10 pages of bitter arguments between people on one side of the "fence", or the other... plus we've had CPU arguments too. 90% of this thread is nothing to do with Polaris.

 

[Klo]

You seem to post that quite a bit in this sub section.

Reflects on the subsection more than him.

 

[ICDP]

What do you believe?

AMD said "two new GPUS". We know one is tiny; the other one we know is more powerful.

Do you believe there is going to be - this year - a big Polaris GPU? Ie, there will be three GPUs, and that AMD themselves simply can't count?

See here is where you are putting your own agenda and assumptions ahead of the actual facts. Your preconceived notion of "big Polaris" is just that, a notion not based on any facts or even rumours. Should AMD be releasing a Polaris GPU with a die size similar to Fury X in 2016 for you to be happy? Only once a process node matures will we start seeing such large die sizes again. The first year on 16/14nm was never going to see the large die GPUs released.

Or do you think that the bigger gpu of the two will beat a FuryX by 40-50%?

With the architectural changes and the new process I anticipate ~30% at stock rising to ~45% with overclocking. Though this is for me a best case scenario.

You seem certain that my speculation is utterly wrong. So therefore you must have some ideas yourself of how things will be.

Let's hear them then. I'm getting bored of you just **** talking my posts and doing nothing constructive in this thread. And you call /me/ the troll.

This isn't about your speculation it's about you making up "facts" so you can shoot them down to show how right you are. Nowhere did it say that the high end Polaris due in 2016 would have a similar or only slightly better performance than Fury X. Nowhere has any of these articles claimed "big Polaris has been delayed until 2017". Yet you made those erroneous statements then proudly proclaimed Polaris a failure because you read somewhere it's only as fast as Fury X.

This is the kind of "factual" statements you have made with zero shred of proof, just thoughts in your head you spout as facts.

Only two GPUs in 2016. That's straight from AMD themselves.

Big Polaris is 2017 at the earliest.

Speculation is that the low-end, tiny Polaris (notebooks) is due in a couple months. With medium Polaris (desktop) about mid-2016. June/July.

Big Polaris is nowhere to be seen, and hasn't even taped out yet, apparently.

So either show the links stating that "big Polaris" has been delayed until 2017 or not taped out yet and that the 2016 Polaris "high end" is only as fast as Fury X.

In fact I just did a Google search for "AMD Polaris delayed until 2017" and it returned zero articles.

You are basing your "speculations/facts" on info you entirely made up.