A Quick Note on Architecture & Features

With pages upon pages of architectural documents still to get through in only a few hours, for today’s launch news I’m not going to have the time to go in depth on new features or the architecture. So I want to very briefly hit the high points on what the major features are, and also provide some answers to what are likely to be some common questions.

Starting with the architecture itself, one of the biggest changes for RDNA is the width of a wavefront, the fundamental group of work. GCN in all of its iterations was 64 threads wide, meaning 64 threads were bundled together into a single wavefront for execution. RDNA drops this to a native 32 threads wide. At the same time, AMD has expanded the width of their SIMDs from 16 slots to 32 (aka SIMD32), meaning the size of a wavefront now matches the SIMD size. This is one of AMD’s key architectural efficiency changes, as it helps them keep their SIMD slots occupied more often. It also means that a wavefront can be passed through the SIMDs in a single cycle, instead of over 4 cycles on GCN parts.

In terms of compute, there are not any notable feature changes here as far as gaming is concerned. How things work under the hood has changed dramatically at points, but from the perspective of a programmer, there aren’t really any new math operations here that are going to turn things on their head. RDNA of course supports Rapid Packed Math (Fast FP16), so programmers who make use of FP16 will get to enjoy those performance benefits.

With a single exception, there also aren’t any new graphics features. Navi does not include any hardware ray tracing support, nor does it support variable rate pixel shading. AMD is aware of the demands for these, and hardware support for ray tracing is in their roadmap for RDNA 2 (the architecture formally known as “Next Gen”). But none of that is present here.

The one exception to all of this is the primitive shader. Vega’s most infamous feature is back, and better still it’s enabled this time. The primitive shader is compiler controlled, and thanks to some hardware changes to make it more useful, it now makes sense for AMD to turn it on for gaming. Vega’s primitive shader, though fully hardware functional, was difficult to get a real-world performance boost from, and as a result AMD never exposed it on Vega.

Unique in consumer parts for the new 5700 series cards is support for PCI Express 4.0. Designed to go hand-in-hand with AMD’s Ryzen 3000 series CPUs, which are introducing support for the feature as well, PCIe 4.0 doubles the amount of bus bandwidth available to the card, rising from ~16GB/sec to ~32GB/sec. The real world performance implications of this are limited at this time, especially for a card in the 5700 series’ performance segment. But there are situations where it will be useful, particularly on the content creation side of matters.

Finally, AMD has partially updated their display controller. I say “partially” because while it’s technically an update, they aren’t bringing much new to the table. Notably, HDMI 2.1 support isn’t present – nor is more limited support for HDMI 2.1 Variable Rate Refresh. Instead, AMD’s display controller is a lot like Vega’s: DisplayPort 1.4 and HDMI 2.0b, including support for AMD’s proprietary Freesync-over-HDMI standard. So AMD does have variable rate capabilities for TVs, but it isn’t the HDMI standard’s own implementation.

The one notable change here is support for DisplayPort 1.4 Display Stream Compression. DSC, as implied by the name, compresses the image going out to the monitor to reduce the amount of bandwidth needed. This is important going forward for 4K@144Hz displays, as DP1.4 itself doesn’t provide enough bandwidth for them (leading to other workarounds such as NVIDIA’s 4:2:2 chroma subsampling on G-Sync HDR monitors). This is a feature we’ve talked off and on about for a while, and it’s taken some time for the tech to really get standardized and brought to a point where it’s viable in a consumer product.

AMD Announces Radeon RX 5700 XT & RX 5700 Addendum: AMD Slide Decks
Comments Locked

326 Comments

View All Comments

  • Phynaz - Tuesday, June 11, 2019 - link

    Members of the Red Team will shell out all for these side grades. They never learn
  • wumpus - Tuesday, June 11, 2019 - link

    You'd think that with the money saved on Ryzen over Intel you could afford a decent Turing (or perhaps an older/used Pascal. No real advantage of going full Turing outside the money-is-no-object 2080ti).

    I guess that's the difference between fans and fanboys.
  • neblogai - Tuesday, June 11, 2019 - link

    Learn what? For anyone knowing the industry- there are plenty of reasons TO NOT BUY NVIDIA, and to support the underdog. And now, with Navi, there are even better AMD options to buy a faster GPU for less.
  • elwro - Tuesday, June 11, 2019 - link

    Well, remember that "SUPER" versions of RTX cards are about to arrive, so regular ones will get a price cut. And nowadays when AMD says about their card as "competitive with XYZ" it should be understood as "~5-10% slower on average than XYZ" (like Radeon VII vs 2080). So I guess waiting for price drop for regular 2070 better deal than getting 5700 XT.

    AMD is back in business in the CPU area, but unless we tak about the low-end cards, Red Team does not have impressive products. OK, Radeon VII is impressive if you're a person which does some AI/ML pet projects and likes to game at the same time, but that's a niche.

    I'm quite disapointed that there is not "Big Navi" this year. I plan to finally upgrade my 2600K/GTX970 rig and while choosing the CPU is easy (Ryzen 9 3950X is no-brainer for me), the GPU market right now sucks. I guess I go for used 1080 Ti, which is best value for 1440p gaming I guess...
  • imaheadcase - Tuesday, June 11, 2019 - link

    "fast" GPU, not faster. Supporting a underdog in a tech industry is the most insane logic i ever heard. Its not like you are shouting at some sports team. lol
  • Phynaz - Tuesday, June 11, 2019 - link

    No kidding, rewarding a company for producing mediocre products, so they will continue to produce mediocre products. It takes some special thinking to justify that.
  • Korguz - Wednesday, June 12, 2019 - link

    and paying a company way to much for its products is better ?? its like saying, keep charging us these insane prices, even though most of us know they are over priced cause all you care about is your profits, and we will keep buying them at these prices... phynaz, you are the most dumbest, close minded, ignorant person i have seen yet.... seems like you want amd's vid card business to fail, to nvidia has no competition, and charge even more for their already overpriced products
  • Phynaz - Wednesday, June 12, 2019 - link

    And here’s one of the special thinkers now....
  • evernessince - Wednesday, June 12, 2019 - link

    Medicore as a metric depends on many variables. A 40% performance uplift over previous generation cards with a nice drop in power consumption and a vastly smaller die certainly seems less mediocre then the 27% performance increase along with higher power consumption and price increases across the board The only way you can rationalize these new AMD cards as mediorce is from a pure performance perspective compared to a $1,200 video card. Otherwise Nvidia's turning generation is far more mediocre, especially when you consider the price hikes. In fact it provides worse performance per dollar then the previous gen Nvidia cards, especially the new titan and 2080 Ti.
  • Qasar - Thursday, June 13, 2019 - link

    evernessince, keep in mind, phynaz, is just trying to justify his purchase of his, my guess, 2080. a card he paid WAY to much for, for little gain over the 1000 series.....

Log in

Don't have an account? Sign up now