Skip to main content

AMD reveals details of new Vega GPU architecture, goes all-in on HBM2

AMD’s Radeon RX 460, 470 and 480 were well received when released in 2016, and for good reason. The cards performed well, at reasonable prices. But the red team’s focus was strictly on the budget to mid-range market, which left gamers who want a powerful card without a good option from the red team.

That option still isn’t out yet, but now we know more about the architecture it’s based on, code-named Vega. AMD calls it the “world’s most scalable GPU memory architecture,” and that claim is not hot air. The company is making a number of tweaks to try and rid video cards of bottlenecks and build a foundation that can easily be modified for workloads with different demands.

The headline feature is the long-rumored adoption of High Bandwidth Memory 2 (HBM2). The original incarnation of HBM was picked up by AMD’s Radeon Fury line, and it gave those cards excellent memory performance. HBM2 does the same.

Compared to GDDR5, HBM2 can squeeze more memory into a smaller space. AMD says that means it offers twice the bandwidth “per pin,” and a 50 percent smaller footprint. We already saw that benefit in the Fury line. Those cards were very powerful, but also small – though AMD hasn’t said anything about the size of the final Vega cards.

Adopting HBM2 is great, but good memory is only as good as the GPU architecture its connected to. To solve that problem, AMD is using a high-bandwidth cache controller with a virtual address space of 512TB.

The over-arching goal of Vega’s design is to improve memory efficiency. AMD says most game developers code games to load far more data than they need as a hedge against hesitation, in case a game asset is called for but not found in memory. This is why modern games often require four gigabytes of memory at their highest detail settings. The faster memory design of AMD should allow quicker delivery of assets when called for. That, in turn, means games won’t need to consume as much of Vega’s memory.

Memory efficiency may be Vega’s most important enhancement, but it’s not alone. There’s also a new geometry pipeline, embracement of primitive shaders, and improved load-balancing. All these changes aim to reduce the need to draw assets that won’t actually be visible once the final frame of a game is viewed.

And then there’s Vega’s next-generation compute unit. AMD’s tactic here is clever. Rather than increasing precision of math, AMD is decreasing it – or, rather, giving developers that option. Math calculated at a lower level of precision can be processed more quickly, and many calculations in games don’t require a high level of precision. For example, Vega quotes 128 32-bit operations per clock, per compute unit. But if computed at 8 bits, it can handle 512 operations per clock.

These improvements are not all the new platform includes, but they’re by far the most important. The changes to the memory architecture, and the flexible compute precision, should prove the most important. If scalability is the goal, these changes seem like a great way to go about it, and they may solve memory issues that are becoming increasingly troublesome in modern games. On the other hand, nothing here tells us how fast Vega will be in raw compute capability, and that’s been the weakness of AMD’s high-end video cards. They simply haven’t matched Nvidia’s fastest.

While we now know a lot more about the architecture, we still don’t know anything about availability and pricing. AMD refuses to say anything firm about either. If past announcements are any guide, that means we’re at least a few months away from availability. But hey –- at least AMD’s fans can sate their appetite on Ryzen.

Editors' Recommendations

Matthew S. Smith
Matthew S. Smith is the former Lead Editor, Reviews at Digital Trends. He previously guided the Products Team, which dives…
AMD launches entry-level RX 6500 XT GPU for budget-conscious gamers
Specs for the AMD RX 6500 XT graphics card.

During its CES 2022 keynote presentation, AMD has introduced the RX 6500 XT, a new entry-level graphics card priced at $199 that the company believes will be a welcome salve for budget-conscious gamers in a time of major GPU shortages and uncertainty.

The card is built on a six-nanometer process and comes with what AMD claims are the “fastest sustained GPU clock rates ever,” at over 2.6GHz. It also packs in 16 hardware ray accelerators, 16MB of the company’s Infinity Cache (a technology that basically functions as a “bandwidth amplifier”), and supports AMD’s Adrenalin software features.

Read more
New Intel Xe-HPG DG2 leak reveals just how fast the new GPU could be
Intel GPU on a stand.

A new leak from the not-so-reliable Geekbench revealed some key details about the upcoming Intel Xe-HPG DG2. The benchmark shows a card with 128 execution units (EUs) that can run at up to 2,200MHz -- faster than most of the best graphics cards on the market. That speed didn't translate into extra performance, however.

The card earned a score of 13,710 in Geekbench's OpenCL test, which is about the same as the GTX 760 or a Radeon RX 550. That's not the performance we were expecting, and it's not the performance you should expect, either.

Read more
AMD bolsters Navi with new $279 RX 5600 XT graphics card at CES 2020
amd radeon rx 5600 xt ces 2020

AMD's mid-range division of its Navi graphics card line has some new reinforcements. Following the debut of the entry-level RX 5500 XT in December 2019, AMD has now unveiled its RX 5600 XT, which the company is heralding as the ultimate 1080p gaming card. Although a welcome addition to the lineup, this debut was far from surprising, as multiple leaks over the preceding weeks told us almost everything to expect from the new card.

Although we don't have third-party benchmarks to give us a true idea of what this new card is capable of, by the numbers at least the 5600 XT slots neatly into the existing lineup of 5000-series GPUs -- just between the 5700 and 5500 XT. Although its core and clocks are very near that of the 5700 (especially if you factor in overclocking from third-party manufacturers and gamers) the memory configuration is distinctly different.

Read more