AMD Radeon RX VEGA to Launch at SIGGRAPH 2017

[mr moose]

24 minutes ago, tom_w141 said:

If that was the case you'd have an argument but 6+ months no that's not a competing product. That's the next offering from the competition which your next product has to compete against. That's like saying a bulldozer CPU is supposed to compete with a Kaby Lake CPU because both are available for purchase. NO.

Fixed

 

EDIT: Volta should drop around Q2 2018. Assuming its start of Q2 so April, that is 9 months after Vega... Definitely not meant to compete with Volta.

 

Vega definitely wasn't supposed to compete with volta, but they kept having issues getting it out and if they delay it any further or Nvidia decide to drop early then they'll have no choice, the market will make it a competition.

[Prysin]

14 minutes ago, leadeater said:

You're quite welcome to go look up those release dates, I did to make sure that information was correct. Also remember not all products were released at the same time for new architectures so it's not even necessary the correct dates to be using if you just want to look at the base top offering i.e. non Ti.

 

GeForce: 8800 series (G80, Tesla): 8 November 2006

GeForce: 9800 series (G92, Tesla): 1 April 2008

GeForce 100 series rebrand, OEM only (G92b, Tesla): 10 March 2009

GeForce 280 (GT200-300-A2, Tesla): 17 June 2009

GeForce 300 series rebrand, OEM only (GT21x, Tesla): 27 November 2009

GeForce 480 (GF100, Fermi): 26 March 2010

GeForce 580 (GF110, Fermi): 9 November 2010

GeForce 680 (GK104-400-A2, Kepler): 22 March 2012

GeForce Titan (GK110, Kepler): 19 Feburary 2013

GeForce 780 (GK110, Kepler): 23 May 2013

GeForce 980 (GM204, Maxwell): 18 September 2014

GeForce 1080 (GP104-400-A1, Pascal): 27 May 2016

 

Since the discussion is mainly around architectures and when they get released I'm not aware of Nvidia ever having a shorter release span than 24 months so don't expect Volta any sooner than Jan 2018 otherwise you'll be more disappointed than Vega fans hoping it will be faster than the 1080Ti.

I would like to point out that from the launch of Fermi (26th of March 2010) until the release of Kepler 22nd of march 2012, is 23 months and 28 days... aka 3 days short of 24 months. Your statement is so wrong. You should be such ashamed. Much Lead, very eater.

[leadeater]

5 minutes ago, Prysin said:

I would like to point out that from the launch of Fermi (26th of March 2010) until the release of Kepler 22nd of march 2012, is 23 months and 28 days... aka 3 days short of 24 months. Your statement is so wrong. You should be such ashamed. Much Lead, very eater.

2012 was a leap year so only 2 days short 

[tom_w141]

20 minutes ago, mr moose said:

 

Vega definitely wasn't supposed to compete with volta, but they kept having issues getting it out and if they delay it any further or Nvidia decide to drop early then they'll have no choice, the market will make it a competition.

If Nvidia bring volta forward to Q3 2017 then I absolutely agree, but if we see Vega at the end of July with supply in august and no Volta till 2018 as planned then they definitely don't compete.

[mr moose]

1 minute ago, leadeater said:

2012 was a leap year so only 2 days short 

Don't forget every year is out by a few 100ths of a second. We must account for that too.

[tom_w141]

33 minutes ago, leadeater said:

Vega sales will stop

Miners might carry it if its decent.

[Prysin]

21 minutes ago, leadeater said:

2012 was a leap year so only 2 days short 

no, that adds a day. If it wasnt a leap year, it would be 24 standard months.

Now we can argue if we are talking calendar or nominal months, in which case you'd be even more wrong if we went by what those pesky "muricans" call "calendar" months.

[leadeater]

Just now, Prysin said:

no, that adds a day. If it wasnt a leap year, it would be 24 standard months.

Now we can argue if we are talking calendar or nominal months, in which case you'd be even more wrong if we went by what those pesky "muricans" call "calendar" months.

Yea it adds a day to February 2012 making the month 1 day longer meaning the number of days between the releases is 1 more day.

 

Edit:

If they were released on the same calendar day it would have been 366 days not 365

Pointless arguing ftw

[Prysin]

8 minutes ago, leadeater said:

Yea it adds a day to February 2012 making the month 1 day longer meaning the number of days between the releases is 1 more day

Sorry, you didnt clarify that in your first statement. The use of months, can thus be clearly misinterpreted.

Let us just go by Calendar months (all months are 28 days, or 4 weeks). Aka, you get VERY wrong. Or if you go by nominal months (or whatever that is when translated into english), then you'd be right.

 

Now third option is to just count the months, as they normally are, in which case, its +3 days, as a leap year is 366 days, rather then 365. So either way, its +1 day.

 

PS: you're still wrong <3

[leadeater]

Just now, Prysin said:

Sorry, you didnt clarify that in your first statement. The use of months, can thus be clearly misinterpreted.

Let us just go by Calendar months (all months are 28 days, or 4 weeks). Aka, you get VERY wrong. Or if you go by nominal months (or whatever that is when translated into english), then you'd be right.

 

Now third option is to just count the months, as they normally are, in which case, its +3 days, as a leap year is 366 days, rather then 365. So either way, its +1 day.

All months can't be calculated using the 28 day months or 4 week months, you'd be massively short on an actual year. 336 vs 365 days, that's not a small difference.

[Prysin]

5 minutes ago, leadeater said:

All months can't be calculated using the 28 day months or 4 week months, you'd be massively short on an actual year. 336 vs 365 days, that's not a small difference.

hey, it was invented by americans economy departments in regards to payroll, what the fuck did you expect? logic?

[leadeater]

Just now, Prysin said:

hey, it was invented by americans economy departments in regards to payroll, what the fuck did you expect? logic?

Just a bend in time space to make me correct, is that too much to ask?

[Prysin]

6 minutes ago, leadeater said:

Just a bend in time space to make me correct, is that too much to ask?

Economy department bends for no mortal man. Only for Benjamin

[Valentyn]

Compute tests show FE is meh compared to Fury X and 1080 somehow, despite all those Floppers it has. FE is still a damp squib.

 

[cj09beira]

1 minute ago, Valentyn said:

Compute tests show FE is meh compared to Fury X and 1080 somehow, despite all those Floppers it has. FE is still a damp squib.

 

i am seen this wrong or is the card slower each time it needs to use the rasterizer ? (the first few benches)

[Valentyn]

Just now, cj09beira said:

i am seen this wrong or is the card slower each time it needs to use the rasterizer ? (the first few benches)

Yah, despite a clock speed advantage over Fury X as well. It's 30% slower essentially taking clocks at 1440Mhz average into account over the 1050Mhz of Fiji.

[tom_w141]

1 minute ago, Valentyn said:

Yah, despite a clock speed advantage over Fury X as well. It's 30% slower essentially taking clocks at 1440Mhz average into account over the 1050Mhz of Fiji.

Something seems wrong here... They didn't take 3 years to produce a card worse than Fiji clock for clock. I get the feeling the hardware isn't being utilised correctly by software.

[cj09beira]

Just now, tom_w141 said:

Something seems wrong here... They didn't take 3 years to produce a card worse than Fiji clock for clock. I get the feeling the hardware isn't being utilised correctly by software.

rasterizer isn't working using tiles as it should, and with that off it might become a bottleneck on the card 

[leadeater]

Just now, Valentyn said:

Compute tests show FE is meh compared to Fury X and 1080 somehow, despite all those Floppers it has. FE is still a damp squib.

It's actually quite funny how well Fury X/Fiji does in certain workloads yet translates so poorly to gaming performance. It also doesn't take much critical thinking to realize that since Vega is still based on GCN architecture family that a 50%-60% increase in clock speed with no other optimizations would make a Fury X/Fiji card slot right in between the 1080 and 1080Ti.

 

I mean that alone should be enough to know Vega FE is not actually representing the proper gaming performance it should have, not even including the architecture improvements unless people are getting bold enough to say AMD have actually produced an architecture with lower performance than the last. If that was actually the case you would just cut your loses and node shrink Fiji and increase the clock speed.

[Prysin]

19 minutes ago, tom_w141 said:

Something seems wrong here... They didn't take 3 years to produce a card worse than Fiji clock for clock. I get the feeling the hardware isn't being utilised correctly by software.

ding ding ding. 

Also, BS benchmark is BS, but that is another thing entirely.

[Taf the Ghost]

@Valentyn

 

Looks a lot like those tests are being run through the same driver as the gaming tests. So I guess we need to know what pipeline are CAD-focused software running through? As Vega FE rocks at those.

 

Beyond just the driver issues, is it possible the Vega FE dies are the "bad" ones with specific parts broken that would make gaming an issue? I don't know the GCN architecture well enough to say either way. (GPU architectures just have never been my thing.)

[LAwLz]

2 hours ago, tom_w141 said:

If that was the case you'd have an argument but 6+ months no that's not a competing product. That's the next offering from the competition which your next product has to compete against. That's like saying a bulldozer CPU is supposed to compete with a Kaby Lake CPU because both are available for purchase. NO.

But that is the case...

When I go out shopping I don't look at the release dates of products to determine which one was the best at the time of release. What I will do is look at what's in store the day I am out shopping and then decide which products to get out of the ones available.

 

If Vega is released today, and Volta released next month, and then we don't get a new graphics card for 24 months then I sure as hell wouldn't go "well AMD is still competitive because at the time of release, Nvidia did not have Volta!". I would say Vega is competing against Volta because at the time of shopping those are my two options.

 

What I am worried about is that AMD will release a card that's only as good as what Nvidia have had on the market for over a year now, and then Nvidia will be able to crush AMD shortly after with Volta.

It just means AMD is one step behind Nvidia. If you're only competitive 6 months out of 12 then you're in a really bad spot.

Of course AMD could drop prices to stay competitive in price:performance, but then we are yet again in this situation where AMD's margins are low and they are seen as a mid-range offering.

 

 

Anyway, leadeater put it way better than me when he said:

1 hour ago, leadeater said:

Vega mostly likely will end up competing against Pascal and Volta, and in regards to Volta we know what kind of shit show that is going to be for Vega. Vega will have to be the fastest selling card they have ever made to recoup costs from development because as soon as Volta hits Vega sales will stop, or might as well say they have considering how low they will be.

That's what my original point was. Vega and Volta will be on store shelves at the same time, and if Vega is just barely matching Pascal then AMD will have a bad time.

 

 

 

2 hours ago, Prysin said:

Ah, seems like the queen of veasel words are back in action. Facinating argument, except its not an argument.

Love you too. <3

[cj09beira]

12 minutes ago, Taf the Ghost said:

@Valentyn

 

Looks a lot like those tests are being run through the same driver as the gaming tests. So I guess we need to know what pipeline are CAD-focused software running through? As Vega FE rocks at those.

 

Beyond just the driver issues, is it possible the Vega FE dies are the "bad" ones with specific parts broken that would make gaming an issue? I don't know the GCN architecture well enough to say either way. (GPU architectures just have never been my thing.)

the only thing that could have a silicon bug would be the rasterizer as it has 2 modes, the old one in which it rasterizes the triangles linearly (one pixel after another, one color after another) and the new one where it does this 

[tom_w141]

10 minutes ago, LAwLz said:

If Vega is released today, and Volta released next month

ITS NOT BEING RELEASED ANY TIME SOON. Sorry you keep saying "volta tomorrow" and "volta next month", I thought raising my voice might get past the ear wax  

 

IF it was next month then yes you'd be fair to say so. But if you don't compete with something released 8-9 months after then that's hardly an issue and is clearly what your next product competes against. How many different people have to say this before you get it? You are semi right, in the sense that if volta followed near immediately but it won't. Or it won't unless NVidia have to launch it early as damage control  because vega clearly beats what they have (which it seems like it won't).

 

tldr: on sale at the same time is not equal to competing against. RX 480 and GTX 1080 were on sale at the same time. They did not compete.

[Valentyn]

47 minutes ago, Taf the Ghost said:

@Valentyn

 

Looks a lot like those tests are being run through the same driver as the gaming tests. So I guess we need to know what pipeline are CAD-focused software running through? As Vega FE rocks at those.

 

Beyond just the driver issues, is it possible the Vega FE dies are the "bad" ones with specific parts broken that would make gaming an issue? I don't know the GCN architecture well enough to say either way. (GPU architectures just have never been my thing.)

These are pure compute loads, which is what pro applications would use. Considering compute was always been a very strong part of AMD this is very disappointing. 

 

The Fury X should not be winning against a Vega card under any circumstances. 

 

There was a tweet from Videocardz.com ages ago saying the reason for the delays is because of a error in a production stepping and they had to respin a new one. 

 

So there could be a chance FE is that bugged stepping that does alright for viewport workloads, but are rubbish at 3D. As the FE sucks at those pro 3D tests as well.

 

We'll find out more in 4 weeks, but the wait is getting frustrating.