Thread Rating:
  • 0 Vote(s) - 0 Average
  • 1
  • 2
  • 3
  • 4
  • 5
Rumored Polaris Refresh
There's also a Navi rumor, but it's sketchy.
Quote:First off, there’s a new Polaris family supposedly being prepped for a Q4 2018 introduction. Built on the same 12nm process improvement as AMD’s second-generation Ryzen CPUs, it would offer a 15 percent performance improvement over current cards.

There are only two ways for AMD to deliver this kind of performance improvement, and only one of them makes sense. To improve GPU performance you can make a GPU wider or smaller while keeping the architecture the same, or you can increase the GPU’s clock speed. With architectural changes unlikely, this suggests that AMD would instead simply try to ratchet clocks higher. And who knows? Given that Polaris was the first 14nm discrete GPU GlobalFoundries had ever built, it’s possible that AMD found some low-hanging fruit that would allow it to hit higher clocks. The larger problem is that while a 15 percent jump would give AMD much stronger footing against Nvidia today, it might not compare well against any next-generation hardware Nvidia launches — at least not without price cuts.
Quote:At the XFastest Network event in Japan, ASRock shared some slides detailing its overall graphics card strategy up to February 2019. There are some interesting bits of information that can be gleaned/extrapolated from it. One bit of information that seems to be set in stone is the introduction, come August, of revised versions of some graphics cards (namely, the RX 570 and RX 580 models) under the MK2 marketing - likely revised in their cooling apparatus. That the RX Vega versions of ASRock graphics cards won't be receiving such a revision seems clear as well: there's no reason for the company to withhold information on that. The others, however, are more prone to speculation.
Quote:According to Phoronix, a new PCI ID, 0x6FDF, has been added to Linux. It’s not mentioned in any database of Radeon drivers or GPU models anywhere online. It’s listed as being part of the Polaris 10 family — in Linux, Polaris 20 GPUs (RX 500 series) are part of the Polaris 10 family as well, which increases the chance that this is a 12nm die shrink. What might we expect from such a part?
A straightforward 10 percent clock increase would put AMD’s RX 580 ahead of the GTX 1060 in every test we ran at launch. Power would still be a significant advantage for Nvidia unless AMD managed to rearchitect the chip along with the die shrink, but AMD would have a stronger position to challenge Team Green in the midrange.

The idea that AMD would pull a refresh like this seemed unlikely back when Nvidia was thought to be launching a top-to-bottom stack refresh. But today, that doesn’t look to be the case. The performance hit from enabling features like RTX is so heavy, it’s not clear if Nvidia can even launch the feature below the RTX 2070, which means Turing may effectively be a refreshed GPU family with a lot of Pascal cards hanging on. Nothing is stopping NV from eventually launching new “2060” cards that are basically rebadged 1060s, and both AMD and Nvidia have gone down this road before.

But Nvidia may not want to take that step this time around. The question for the company is whether it makes more sense to position the new RTX family as entirely devoted to ray tracing and DLSS with the old Pascal numbering system reserved for non-RTX cards or if bringing these other GPUs forward into the Turing product line and labeling them with the new naming convention would confuse buyers. I’m inclined to think it would; buyers are unlikely to grasp the distinction between an “RTX 2070” and a hypothetical “GTX 2060” if Nvidia tries to make the “G” alone the distinguishing factor for whether new features are available. Regardless of whether or not Nvidia keeps Pascal in market or attempts to re-brand older cards as part of the Turing family, AMD may have an opportunity to better position itself in the mid-market.

Of course, all of this is supposition, based on some PCI ID codes for a product family, not actual hardware. But if AMD can snag a win across the midrange for a die-shrunk version of its Polaris family, the company may well go for it. Improving its competitive midrange position is a good way for AMD to win back market share, even if it isn’t competing with the RTX family.
Quote:Benchmark scores for 3D Mark's Time Spy have surface, and are purported to represent the performance level of an unidentified "Generic VGA" - which is being identified as AMD's new 12 nm Polaris revision. The RX 590 product name makes almost as much sense as it doesn't, though; for one, there's no real reason to release another entire RX 600 series, unless AMD is giving the 12 nm treatment to the entire lineup (which likely wouldn't happen, due to the investment in fabrication process redesign and node capacity required for such). As such, the RX 590 moniker makes sense if AMD is only looking to increase its competitiveness in the sub-$300 space as a stop-gap until they finally have a new graphics architecture up their shader sleeves.
The reported RX 590's call for fame is that its 1545 MHz clocks can be achieved at much lower power consumption figures than an overclocked RX 580 - and would likely be overcklockable on top of the base 1545 MHz, thus increasing the gap over the base clock % increase. Remember overlcocking gains aren't linear, though, and since it seems the RX 590 will still make use of GDDR5 memory (2000 MHz clocks; and again, remember the investment in repurposing the design for GDDR6), so you better push out your own manual memory overcklocking to improve on Polaris' most pressing limitation.
Quote:Assuming AMD is planning an RX 590, we’re thinking it could be a 12nm spin or 14nm respin of Polaris with a subsequent clock bump and almost certainly still built at GlobalFoundries. Introducing a new Polaris GPU now lets AMD put a refresh on the board for 2018 and the first part of 2019, but it isn’t a part that Lisa Su mentioned in her analyst call. Then again, AMD really isn’t talking publicly about its consumer GPU plans at all right now. While GPUs were frequently mentioned this week during the conference call, all of the discussion focused on data centers and the 7nm Vega ramp. If AMD is ramping an RX 590 now, it implies Navi will either be focused in a different market area (at least initially) or won’t arrive for quite some time — long enough not to collide with this product in the market.
RX 590 sighted:
Quote:In regards to actual specifications, the RX 590 features the same 2304 Stream processors, 144 TMUs (texture mapping units), and 32 ROPS (render output units) as the RX 580. This is because the Polaris 30 design used in the RX 590 is just a die shrink of Polaris 20 used in the RX 580. Obviously with a die shrink typically comes improved performance, usually via higher clock speeds. Currently, the final clock speeds for Sapphire's Radeon RX 590 NITRO+ are not known. However, if the rumored reference boost clock of 1545 MHz is correct, an overclock pushing that a step further is likely. Meaning performance should be improved compared to what we have seen in various leaks thus far.
Quote:The Red Devil Radeon RX 590 8GB GDDR5 comes with a game bundle that's worth $180 if purchased from a selected eTailer. The list of unreleased AAA titles include Resident Evil 2 (2019), Devil May Cry 5 and The Division 2. PowerColor didn't reveal the pricing for the Red Devil Radeon RX 590 8GB GDDR5. However, the Radeon RX 590 is expected to launch November 15, so we won't have to wait long to find out.
Quote:According to a slide deck seen by VideoCardz, AMD is setting the baseline price of the Radeon RX 590 at USD $279.99, which is about $50 higher than RX 580 8 GB, and $40 higher than the price the RX 480 launched at. AMD will add value to that price by bundling three AAA games, including "Tom Clancy's The Division 2," "Devil May Cry 5," and "Resident Evil 2." The latter two titles are unreleased, and the three games together pose a $120-150 value. AMD will also work with monitor manufacturers to come up with graphics card + AMD FreeSync monitor bundles.
Quote:What we can see, however, are the benchmark results, power consumption measurements, value comparison, and efficiency calculation. Radeon RX 590 may benefit from a tuned process, but it’s still being flogged for a few percentage points of additional performance and sold at a higher price. It’s sucking down GeForce RTX 2080 power to generate frame rates between GeForce GTX 1060 and 1070. As a result, the Radeon RX 580 and 590 both look bad when we look at performance per watt.

Sure, $280 (£250) for Radeon RX 590 remains a relative bargain to shell-shocked gamers still reeling from the cryptocurrency bonanza that saw mainstream graphics cards selling for two or three times their original worth. In that context, you’re basically getting a great (guaranteed) overclock at a 25 or 30 percent premium over Radeon RX 580 8GB. But we’d just as soon save some money and buy the cheaper Polaris card for high-detail gaming at 1920 x 1080. After all, RX 580s are readily available for less than the price point AMD launched them at back in 2017.
And so, we’re left with Radeon RX 590 instead. It’s faster than GeForce GTX 1060 6GB across our suite at 1920 x 1080 and 2560 x 1440, which seems to have been AMD’s goal. However, when we comb over graphics card prices and compare their performance, the real winner today is Radeon RX 580 8GB. Ample performance for cranking up quality at 1920x1080 and post-crypto-crazy pricing combine for some of the best deals we’ve seen on mainstream gaming hardware in 2018.
Quote:Our value scatters boil down the story of the RX 590 quite well. On the back of its clock-speed boost alone, the RX 590 capably steps into the wide gap left by the RX 580 8 GB and the GTX 1060 6 GB in today's midrange graphics-card market. Perhaps more critically, the RX 590 is the first midrange card we've reviewed that clears the 60-FPS mark for 99th-percentile FPS per dollar. For 1920x1080 gaming at high or ultra settings, the RX 590 proves both swift and smooth. Can't ask for much more than that.

For the first time in a long time for a Radeon launch, the move to GlobalFoundries' 12LP process has apparently yielded enough performance headroom that AMD's engineers didn't feel the need to hurl this card over the shoulder of the voltage-and-frequency-scaling curve (or at least not any more so than it already was). With our XFX RX 590 on our test bench, I observed less than 20 watts' extra draw on our power meter versus a hopped-up RX 580 8 GB. AMD is still nowhere close to matching Nvidia for performance per watt, but it's nice to know that the RX 590 shouldn't be much more demanding of power supplies or custom coolers to deliver its extra performance.
All that said, discounts don't last forever, and old stock of high-end graphics cards may not, either. If you're shopping for a graphics card in the under-$300 range and were already considering spending $250 or $260 on a GTX 1060 6 GB or Radeon RX 580, I would spend the extra $20 or $30 on an RX 590 without hesitation. It shouldn't come as a shock that this card comes TR Recommended.
Quote:AMD's "Polaris 30" silicon at the heart of Radeon RX 590 graphics card is the company's first 12 nm GPU. Unlike NVIDIA, which is exclusively sourcing its "Turing" family of GPUs from TSMC, the "Polaris 30" is coming from not one, but two sources. This, according to AMD in response to a question by TechPowerUp. The two foundries manufacturing "Polaris 30" are GlobalFoundries and Samsung. AMD did not provide us with visual cues on how to tell chips made from either foundries apart (such as serial numbering schemes). Packaging of dies sourced from both foundries is done in China, and the national-origin marking for the chip is on the package, rather than printed on the die.
Linus refuses to review the RX 590 because he's sick of rebranding in general. He also mentions that Nvidia goes out of their way to make it difficult for reviewers to get review samples of multiple graphics cards ahead of launch, so that they can get a new cycle of reviews:
Quote:If you’re in the market for a graphics card and you have roughly $300 to spend, your best option right now is an AMD Radeon RX 590. But the best option isn’t always a good option.

There’s a term in chess called Zugzwang, which is when you’re forced to make a bad move for lack of any other option. The options available in the mid-tier GPU market feel somewhat like a Zugzwang. You can purchase a GTX 1060, which is the cheaper option, but offers inferior performance than the competition and is due for a 20-series replacement in the coming months. Or you can purchase an RX 590, which is effectively a rehash of a 3-year-old platform with the power limits pushed to their maximum.

Both options are sub-optimal, and we’d be somewhat inclined to suggest waiting to see what Nvidia is cooking up for the mid-tier market, but with the tariff increases coming in January, what is now a $300 graphics card could soon become a $375 graphics card, in which case you’d be better off buying what you can get now. And with Nvidia’s recent track record of increasing the price of the high-end GPUs, who’s to say what the price of the 1060’s replacement will be?
Quote:One of our readers discovered an interesting entry in the INF file of AMD's Adrenalin 19.4.3 graphics drivers. It includes two instances of "Radeon RX 640," and has the same device ID as the Radeon RX 550X from the current generation. The branding flies in the face of reports suggesting that with its next-generation "Navi" GPUs, AMD could refresh its client-segment nomenclature to follow the "Radeon RX 3000" series, but it's possible that the RX 600 series was carved out to re-brand the existing "Polaris" based low-end chips one step-down (i.e. RX 550X re-branding as RX 640, RX 560 possibly as RX 650, etc.).
Quote:It's unknown at this point in time whether the RX 600-series will retain the same silicon and manufacturing process or get an upgrade to the 12nm node. We would expect an increase in the operating clocks at the very least. Either way, it appears that AMD wants to give its GCN architecture one more run before moving on to Navi.
Quote:After weeks of rumors, Nvidia has released the GTX 1660 Super graphics card today. Meanwhile, rival AMD cards have received price cuts on the Radeon RX 590 graphics card, as spotted by HotHardware.

The RX 590 is currently around or below $200 mark on Newegg for a good handful of variants. When it first came out, cards started at $280. That's a fair price, offering similar frames per second per dollar as the GTX 1660 and GTX 1660 Super.
However, if you're thinking about buying a new graphics card but aren't in a rush, you may want to wait and see what the RX 5500 and GTX 1650 Super bring to the table.
Quote:News outlet Expreview has spotted several listings for a new AMD graphics card that is believed to be exclusive to the Chinese market. Apparently, AMD is resuscitating the Polaris silicon for the Radeon RX 590 GME.
Based on the listings, the primary difference between the Radeon RX 590 GME and Radeon RX 590 is that the first comes with lower clock speeds. That would make the Radeon RX 590 GME slide in between the Radeon RX 580 and Radeon RX 590.
The Radeon RX 590 GME is expected to launch in China on March 9. Popular Chinese retailer has the custom models listed between 1,199 and 1,399 yuan, which convert to $172 and $200, respectively.

Forum Jump:

Users browsing this thread: 1 Guest(s)