'

AMD Vega GPU architectural analysis

AMD Vega GPU architectural analysis - Next Generation Geometry and Compute

AMD Vega GPU architectural analysis

Next Generation Geometry and Compute Engine Design  

With Vega, AMD has not limited their architectural changes to just their memory, announcing several improvements to both their Geometry pipeline and their Compute units. 

Vega now supports Primitive shaders, which is a new type of low-level shader that developers can use to specify all shading stages that they want, allowing them to run at a higher rate than shaders using the traditional DirectX shader pipeline model. In an ideal scenario, developers will work to perform these optimisations, though AMD can use their graphics driver to deliver pre-defined cases for games, where several DirectX shaders can be replaced by a single primitive shader for improved performance.

AMD has also improved their geometry pipeline to deliver much higher peak levels of geometry throughput, with AMD's R9 Fury X offering 4 Geometry engines with peak throughputs of 4 polygons per clock, with Vega coming with 4 geometry engined that can handle up to 11 polygons per clock, a 2.6x increase.  

 

AMD Vega GPU architectural analysis  AMD Vega GPU architectural analysis
AMD Vega GPU architectural analysis  AMD Vega GPU architectural analysis
  

With their next generation compute units AMD seeks to improve gaming performance with their Next Generation Compute Units (NCU), offering higher levels of mixed precision compute performance, greater 16-bit and 8-bit compute performance as well as higher clock speeds. 

On the compute side, AMD's NCU will also be capable of calculating 8-bit, 16-bit and 32-bit operations with perfect scaling, which is perfect for those that require higher levels of lower precision compute performance. This also opens up the option to do several of these varying precision levels of compute at the same time, with mixed precision compute capabilities. 

With a new feature called "rapid packed math", AMD can now clump 16-bit and 8-bit math together to increase the amount of compute tasks that AMD can do per clock. In theory, developers could optimise some of their code to run as 16-bit or 8-bit operations to increase GPU performance, which is something that developers are currently exploring in the PS4 Pro. 

Lastly, AMD's new compute unit designs will be better suited to running at higher clock speeds, which will allow AMD to deliver more performance by completing more clock cycles and well as increasing the performance that AMD can deliver per clock.  

 

AMD Vega GPU architectural analysis  AMD Vega GPU architectural analysis
AMD Vega GPU architectural analysis  AMD Vega GPU architectural analysis

 

«Prev 1 2 3 Next»

Most Recent Comments

06-01-2017, 16:46:52

BigDaddyKong
Interesting how AMD is is pitting this against Volta, and trying to leapfrog generations.Quote

06-01-2017, 17:12:41

TheF34RChannel
Quote:
Originally Posted by Kong View Post
Interesting how AMD is is pitting this against Volta, and trying to leapfrog generations.
The thing I cannot wrap my head around is how they can pit it against Volta, of which next to nothing is known (unless we're talking corporate espionage lol)??Quote

06-01-2017, 17:48:35

AngryGoldfish
Quote:
Originally Posted by The F34R Channel View Post
The thing I cannot wrap my head around is how they can pit it against Volta, of which next to nothing is known (unless we're talking corporate espionage lol)??
A part of me thinks AMD has lost it and is desperately cloying at the walls to climb out of the economic pit they're in, breaking their fingers in the process. But another part of me giggles with excitement at the thought of Vega not only competing and beating Pascal but competing with Volta. I find that very hard to believe, but still. It was initially rumoured that Vega 20 would be Vega 10 shrunk down using the 7nm process with 16GB of HBM2 running at 1TB/s and having vastly increased clock speeds and reduced TDP. They could then rebadge 14nm Vega 10 and 11 as midrange GPU's and the Polaris 10 chip as a low-end card. I doubt that, though, as optimising for both 14nm and 7nm in tandem might not be practical.Quote

06-01-2017, 17:55:20

TheF34RChannel
Quote:
Originally Posted by AngryGoldfish View Post
A part of me thinks AMD has lost it and is desperately cloying at the walls to climb out of the economic pit they're in, breaking their fingers in the process. But another part of me giggles with excitement at the thought of Vega not only competing and beating Pascal but competing with Volta. I find that very hard to believe, but still. It was initially rumoured that Vega 20 would be Vega 10 shrunk down using the 7nm process with 16GB of HBM2 running at 1TB/s and having vastly increased clock speeds and reduced TDP. They could then rebadge 14nm Vega 10 and 11 as midrange GPU's and the Polaris 10 chip as a low-end card. I doubt that, though, as optimising for both 14nm and 7nm in tandem might not be practical.
I just don't see it happening, it beating high end Pascal, let alone Volta, given their lengthy track record of big talk and not delivering (I recall the same before Polaris came out etc.). However, I don't know until it's out of course, but I cannot help but be weary and skeptical because of the aforementioned track record and the state the company has been in for many years now. And it is frustrating because I want them to deliver; it's the better outcome for everyone involved.Quote

06-01-2017, 18:06:05

AngryGoldfish
Quote:
Originally Posted by The F34R Channel View Post
I just don't see it happening, it beating high end Pascal, let alone Volta, given their lengthy track record of big talk and not delivering (I recall the same before Polaris came out etc.). However, I don't know until it's out of course, but I cannot help but be weary and skeptical because of the aforementioned track record and the state the company has been in for many years now. And it is frustrating because I want them to deliver; it's the better outcome for everyone involved.
I don't know how much the rejig that recently occurred at AMD—the Radeon group being sectioned off and dedicating its resources to GPU's and Raja taking over—will impact things. The Fury line could have been a slight slip up. The 290X suffered from temperatures and power consumption, but it was a stellar GPU other than that. And one of the main reasons why it suffered from a higher TDP than its competitors was because AMD were stuck with 28nm for so long. Nvidia focused on the right thing while AMD focused on the wrong thing. They're correcting that mistake. Polaris was, at first, underperforming, but it is now comparable to Nvidia and in some cases superior. Temperatures are in check, power consumption is in check, pricing is in check, memory configuration is in check, availability is in check (both both AIB partners and AMD directly), drivers are in check, VR and high resolution performance is in check, DX11 and DX12 performance is in check, even overclocking is better with Polaris than Fury. If Polaris is performing so well, and Vega isn't just a beefed up Polaris, why can't AMD pull it off again?Quote
Reply
x

Register for the OC3D Newsletter

Subscribing to the OC3D newsletter will keep you up-to-date on the latest technology reviews, competitions and goings-on at Overclock3D. We won't share your email address with ANYONE, and we will only email you with updates on site news, reviews, and competitions and you can unsubscribe easily at any time.

Simply enter your name and email address into the box below and be sure to click on the links in the confirmation emails that will arrive in your e-mail shortly after to complete the registration.

If you run into any problems, just drop us a message on the forums.