Vega refresh in 2018, current Vega is broken!

[Rroff]

AMD 7nm “Super Secret” Navi GPU Spotted In Driver, 2H 2018 Launch Expected https://wccftech.com/amd-navi-gpu-spotted-in-linux-drivers/

I suspect that isn't Navi.

 

[Steampunk]

AMD 7nm “Super Secret” Navi GPU Spotted In Driver, 2H 2018 Launch Expected https://wccftech.com/amd-navi-gpu-spotted-in-linux-drivers/

Is that going to be a 2H launch like the one for Vega? Where OEM cards arrived six months late for £800?

 

[nashathedog]

As they are using a cut down OS dedicated towards gaming and lower level APIs,the impact is not as bad and I suspect Ryzen would not have been ready in the timeframe for the updated consoles. Having looked at a mate playing HZD,I was impressed by the world that was created and some of the interesting graphical tricks they used in the latest DLC:
http://www.eurogamer.net/articles/d...e-frozen-wilds-is-an-unmissable-tech-showcase

The PC tends to be more a case of brute forcing things sadly. It makes me wonder if the PC was more efficiently used as a platform,that extra power could be used to really improve the fidelity of graphics in games,or the basic interaction in the world around you in the game.

I've seen rumours regarding a 2018 Q4 or 2019 Q1 PS5, I haven't a clue if it's true(ish) but if it is I just hope they stay all AMD for that. Hopefully they will as AMD's the only one able to offer a complete APU package, I get the feeling we need both Microsoft and Sony to do both, I don't think the Switch matters as much so I hope Nvidia are content with that.

 

[nashathedog]

AMD 7nm “Super Secret” Navi GPU Spotted In Driver, 2H 2018 Launch Expected https://wccftech.com/amd-navi-gpu-spotted-in-linux-drivers/

I suspect that isn't Navi.

Is that going to be a 2H launch like the one for Vega? Where OEM cards arrived six months late for £800?

Ooh,

I hope it is,

Let's hope not.

new_chip.gfx10.mmSUPER_SECRET.enable[0:0]

All aboard


The last Hype train should have been renamed the Titanic, let's hope this one goes a bit better.

 

[sideways14a]

To be honest the Navi train was about due to get under steam about now anyway - lets see how fast this one goes.

 

[CaptainRAVE]

What a massive fail.

 

[JediFragger]

To be honest the Navi train was about due to get under steam about now anyway - lets see how fast this one goes.

Will anyone dare to speculate good performance though considering the lop-sided performance we get with Vega??

 

[Kirby Wurm]

My biggest question for Navi is HBM2, GDDR6 or both?

 

[Rroff]

My biggest question for Navi is HBM2, GDDR6 or both?

Or neither.

EDIT: Reading between the lines I think there is a good chance of seeing a refreshed Vega with GDDR6 though.

 

[AmateurExpert]

At least amongst Steam users from looking at the CPU section - looks like despite the success of Ryzen those Coffee Lake CPUs have sold a ton - way more than I expected and even seen some people moving over.

From September to October & November there were big jumps in share for CPUs in the 2.7-3.3GHz ranges, while 3.7+ dropped - so if true, of Coffee Lake only i5-8400 and i7-8700 (non-Ks) could have sold in significant numbers (to the Steam survey base) - an influx of older hardware may be more likely.

 

[Kaapstad]

My biggest question for Navi is HBM2, GDDR6 or both?

Or play it safe and use GDDR5X, it is fast enough for a Pascal Titan so it should be fine for Navi.

 

[AmateurExpert]

AMD 7nm “Super Secret” Navi GPU Spotted In Driver, 2H 2018 Launch Expected https://wccftech.com/amd-navi-gpu-spotted-in-linux-drivers/

That article has already been debunked - that the "new_chip.gfx10.mmSUPER_SECRET.enable[0:0]" text string is from this patch (from back in July) which is just a sample output string and doesn't even relate to the Linux driver, but the debugger "umr".

 

[4K8KW10]

My biggest question for Navi is HBM2, GDDR6 or both?

Or neither.

EDIT: Reading between the lines I think there is a good chance of seeing a refreshed Vega with GDDR6 though.

Or play it safe and use GDDR5X, it is fast enough for a Pascal Titan so it should be fine for Navi.

HBM3.

I don't see why Vega would be refreshed. It can't be fixed, so............ ?!

 

[AmateurExpert]

HBM3

Seems unlikely as Samsung's own roadmap doesn't project availability of HBM3 until 2019/2020, and the biggest problem with HBM2 isn't performance, but availability.

 

[4K8KW10]

Seems unlikely as Samsung's own roadmap doesn't project availability of HBM3 until 2019/2020, and the biggest problem with HBM2 isn't performance, but availability.

Is Samsung the single manufacturer of HBM? That article is extremely old and the slide there is extremely not serious. Just look at what kind of meaningless words there were used.

On a more serious note, HBM3 will obviously improve and deliver similar performance with less efforts.

 

[4K8KW10]

That article has already been debunked - that the "new_chip.gfx10.mmSUPER_SECRET.enable[0:0]" text string is from this patch (from back in July) which is just a sample output string and doesn't even relate to the Linux driver, but the debugger "umr".

AMD Navi Found Secretly Hiding in Linux Drivers
We know AMD has been doing a great job keeping the lid on their Navi architecture with information being scarce at the moment. Aside from knowing that Navi is being fabricated on the 7 nm process, it is possible that the microarchitecture will quite possibly support next-generation memory like GDDR6 or HBM3. In a Navi discussion on the Beyond3D forums, a user found an entry in a Linux driver dated back to July that apparently mentions AMD's upcoming architecture - not by its real name, of course. The code is to add support for importing new asic definitions from a text file as opposed to adding support in code. Tom St Denis, a software engineer at AMD, listed the output that would be generated by using this functionality. However, the entry that caught our attention reads: new_chip.gfx10.mmSUPER_SECRET.enable [0: 0]. If our memory serves us right, the codename for Vega was GFX9. So by logic, Navi should carry the GFX10 codename. Obviously, the SUPER_SECRET part further backs up our theory or maybe AMD's just trolling us. The red team has been hiring personnel for their GFX10 projects, so we can assume they're working diligently to release Navi some time next year.

Source: Beyond3D
https://www.techpowerup.com/239794/amd-navi-found-secretly-hiding-in-linux-drivers

 

[Doogles]

To be honest the Navi train was about due to get under steam about now anyway - lets see how fast this one goes.

It'll derail on it's debut

 

[opethdisciple]

It's WAYYY to late for then to do anything drastic to Navi surely at this point. So in other words if they sacked Raja for Vegas disaster, Navi is built from the ground up by Raja so another epic disaster on the cards?

 

[4K8KW10]

It's WAYYY to late for then to do anything drastic to Navi surely at this point. So in other words if they sacked Raja for Vegas disaster, Navi is built from the ground up by Raja so another epic disaster on the cards?

No, because Vega gets better when you decrease its power consumption.

One Scalable Navi GPU To Rule Them All – The Legend Of The Wonder Glue https://wccftech.com/amd-navi-gpu-spotted-in-linux-drivers/

There’s been talk in the industry that Navi could very well be AMD’s first attempt at “gluing” several small, high yielding 7nm GPU dies to make bigger and more powerful graphics chips. This would work similarly to what we’ve already seen the company do using Infinity Fabric to link 4 Zeppelin dies to create 32 core EPYC processors and 2 Zeppelin dies to create the ever popular Threadripper chips.

 

[ubersonic]

Considering how Vega went, I can quite imagine Lisa walking into Raja's office after sacking him, opening up the box marked "Navi prototype, do not eat" and finding a Radeon 9700 pro with go faster stripes painted on the side