Watch AMD's Radeon RX 6000 'Big Navi' RDNA 2 GPU Launch Here

News
By
published

AMD strikes back

AMD RX 6000 early information tease
(Image credit: AMD)

Update: The livestream has concluded – here's our breakdown of the speeds, feeds, and pricing:

AMD Unveils Big Navi: RX 6900 XT, RX 6800 XT and RX 6800 Take On Ampere

And here's a few details on the new Ryzen 5000 pairing:

AMD’s RX 6000 GPUs to Boost Perf With Ryzen 5000 CPUs via Smart Memory Access

Original article:

AMD will debut its new RDNA 2 architecture that will power its new RX 6000 series graphics cards, lovingly known as Big Navi in enthusiast circles, today at 12pm ET. We've embedded the video below so you can watch the event unfold in real-time. Also, keep your eyes peeled for our ongoing coverage both during and after the event.

Nvidia's Ampere GPU launch reset our expectations for performance and pricing for gaming GPUs, upsetting our GPU hierarchy and Best GPU recommendations in the process, but AMD certainly isn't going to let that go without a response. That response comes in the form of the RDNA 2 architecture, which AMD has already revealed offers 50% more performance per watt over the previous-gen RDNA 1 architecture. During AMD's Ryzen 5000 launch, the company teased us with gaming performance that looks similar to the RTX 3080 - you can read our full analysis of the only official performance demo here. 

Of course, a string of leaks have kept us guessing on Big Navi's performance potential, but we expect the company to come gunning for not only the mid-range but also Nvidia's high-end RTX 30-series cards, so anything goes. We also expect support for some sort of hardware-accelerated ray tracing capability to level the playing field with Nvidia's Ampere.  

We've already seen some new features officially added to Linux patches, and the reports of a new Infinity Cache, which is a new term AMD recently trademarked, portend possible radical new features that could boost performance. 

In either case, AMD will set the record straight in today's webcast. Pricing, and the oh-so-important availability in the wake of the Ampere launch fiasco, could determine the winner in the GPU wars this year. While you wait, check out our Big Navi all-we-know article to get caught up on the latest chatter from around the GPU watercooler. 

Paul Alcorn
Paul Alcorn
Managing Editor: News and Emerging Tech

Paul Alcorn is the Managing Editor: News and Emerging Tech for Tom's Hardware US. He also writes news and reviews on CPUs, storage, and enterprise hardware.

See more GPUs News
47 Comments Comment from the forums
  • alceryes
    oHpgu-cTjyMView: https://www.youtube.com/watch?v=oHpgu-cTjyM
    Reply
  • ezst036
    I have high hopes for Big Navi. I'm planning for a new Linux gaming box and one of these is going to be in there.

    With AMD's open source driver on Linux and Valve's constant striving for better gaming in Linux it's going to be a lot of fun!
    Reply
  • Joseph_138
    I'm not optimistic. AMD hasn't been competitive for a few years, ever since Nvidia dropped Pascal on us. Turing was 'meh', but Nvidia got away with it because AMD wasn't there to compete with them tier for tier, and dollar for dollar. The rumors I have been seeing online all seem to point to Big Navi being equal to, or faster than Ampere, but at a cost of greater power consumption. If power consumption isn't an issue for you, then it's awesome, but for anyone wanting to squeeze another year out of their power supply, it's not an option if the equivalent Big Navi card draws 20-30 more watts of power, regardless of whether it's faster or not. Many people can afford to upgrade their video card, but not their power supply at the same time. That makes the AMD card a more expensive upgrade than Nvidia.

    AMD is also late to the raytracing party, so who knows if their implementation of it is compatible with Nvidias? Nvidia also has technologies unique to them that AMD won't be able to use like GDDR6X memory and DLSS. DLSS is particularly impressive because it allows a less expensive card to run at higher resolutions than it would normally be capable of in native mode. You can play in 4K using DLSS rendering at 1080p and the quality is impressive, judging by the stills and videos that are being shared. There are losses, yes, but they are not so noticeable that they would completely ruin the 4K experience. So you can play in 4K using a cheaper card than what you would require on the AMD side, making Nvidia an even better value proposition.
    Reply
  • Avro Arrow
    45 MINUTES AND COUNTING UNTIL RED OCTOBER
    Reply
  • King_V
    Joseph_138 said:
    I'm not optimistic. AMD hasn't been competitive for a few years, ever since Nvidia dropped Pascal on us. Turing was 'meh', but Nvidia got away with it because AMD wasn't there to compete with them tier for tier, and dollar for dollar. The rumors I have been seeing online all seem to point to Big Navi being equal to, or faster than Ampere, but at a cost of greater power consumption. If power consumption isn't an issue for you, then it's awesome, but for anyone wanting to squeeze another year out of their power supply, it's not an option if the equivalent Big Navi card draws 20-30 more watts of power, regardless of whether it's faster or not. Many people can afford to upgrade their video card, but not their power supply at the same time. That makes the AMD card a more expensive upgrade than Nvidia.

    AMD is also late to the raytracing party, so who knows if their implementation of it is compatible with Nvidias? Nvidia also has technologies unique to them that AMD won't be able to use like GDDR6X memory and DLSS. DLSS is particularly impressive because it allows a less expensive card to run at higher resolutions than it would normally be capable of in native mode. You can play in 4K using DLSS rendering at 1080p and the quality is impressive, judging by the stills and videos that are being shared. There are losses, yes, but they are not so noticeable that they would completely ruin the 4K experience. So you can play in 4K using a cheaper card than what you would require on the AMD side, making Nvidia an even better value proposition.

    These are very strange things to say, particularly given that the RX 5600 XT outdid the RTX 2060 both in performance and power efficiency. And, for what you get per dollar, the only disappointment was the RX 5500 XT. The rest of the Navi cards blew away Nvidia in the price-to-performance ratio.

    Further - why do you think the definition of "being competitive" absolutely MUST be matching Nvidia tier-for-tier, dollar-for-dollar. That's an extremely narrow definition.

    Was grabbing the mid-range with Polaris a failure to compete? Was getting the consoles a failure to compete?

    Seems like you selectively grabbed onto the "common wisdom" from a few years ago, and became dogmatic about it. Almost like you feel it's your sacred duty to be a naysayer.

    Ultimately, we'll see what happens when the hardware gets reviewed.
    Reply
  • InvalidError
    Joseph_138 said:
    AMD is also late to the raytracing party, so who knows if their implementation of it is compatible with Nvidias?
    No need to wonder, Nvidia's implementation of RT is proprietary to Nvidia just like the inner workings of AMD's RT are proprietary to AMD, rinse and repeat for every other company with RT hardware ambitions. The only thing that matters is how well DXR and other RT APIs can be mapped to each company's hardware, just like it is for regular 3D acceleration.
    Reply
  • CorbeauNoir
    At this point, whoever is the first to get physical cards on physical shelves at my local physical store gets my money. Simple as.
    Reply
  • ajr1775
    CorbeauNoir said:
    At this point, whoever is the first to get physical cards on physical shelves at my local physical store gets my money. Simple as.

    This. Nvidia did a good job of amping demand. Now that void is going to be filled by AMD assuming their supply is on point.
    Reply
  • InvalidError
    ajr1775 said:
    Now that void is going to be filled by AMD assuming their supply is on point.
    I'm going to guess that between all of the new stuff AMD is making on 7nm, its TSMC wafer agreement is going to get stretched thin and supplies will be relatively limited for the next many months.
    Reply
  • raycrayz
    Joseph_138 said:
    I'm not optimistic. AMD hasn't been competitive for a few years, ever since Nvidia dropped Pascal on us. Turing was 'meh', but Nvidia got away with it because AMD wasn't there to compete with them tier for tier, and dollar for dollar. The rumors I have been seeing online all seem to point to Big Navi being equal to, or faster than Ampere, but at a cost of greater power consumption. If power consumption isn't an issue for you, then it's awesome, but for anyone wanting to squeeze another year out of their power supply, it's not an option if the equivalent Big Navi card draws 20-30 more watts of power, regardless of whether it's faster or not. Many people can afford to upgrade their video card, but not their power supply at the same time. That makes the AMD card a more expensive upgrade than Nvidia.

    AMD is also late to the raytracing party, so who knows if their implementation of it is compatible with Nvidias? Nvidia also has technologies unique to them that AMD won't be able to use like GDDR6X memory and DLSS. DLSS is particularly impressive because it allows a less expensive card to run at higher resolutions than it would normally be capable of in native mode. You can play in 4K using DLSS rendering at 1080p and the quality is impressive, judging by the stills and videos that are being shared. There are losses, yes, but they are not so noticeable that they would completely ruin the 4K experience. So you can play in 4K using a cheaper card than what you would require on the AMD side, making Nvidia an even better value proposition.

    Anyone in that situation needs a new motherboard, new ram, new CPU, and new Video card.
    Reply