AMD NAVI Radeon 5700 Product Announcement thread

Discussion in 'Frontpage news' started by Hilbert Hagedoorn, Jun 10, 2019.

  1. alanm

    alanm Ancient Guru

    Messages:
    12,236
    Likes Received:
    4,437
    GPU:
    RTX 4080
    I would be surprised if AMD stick to their announced Navi prices for long. Given the sour reception RTX cards had at launch, AMD have a golden opportunity to really shake things up and claw back some market share if they were to reduce prices just by a mere $50. Sadly, AMD doesnt seem to realize this and have a habit of poorly handling product launches. A $399 XT and $329 5700 could really impress reviewers at launch day. I hope someone in management recognizes this and and capitalizes on this opportunity before its too late.
     
    Jagman and Loophole35 like this.
  2. kings

    kings Member Guru

    Messages:
    158
    Likes Received:
    131
    GPU:
    GTX 980Ti / RX 580
    Yeah, this double standards is getting out of hand!

    Nvidia introduces the RTX 2060 at $349 and half the internet has a meltdown. "A mid-end card shouldn't cost more than $250, what a greedy basterds".

    AMD introduces the RX5700 six months later at $379, "oh, look, what a lovely mid-end card, greetings to AMD".

    I guess people only see what they want to see!
     
    Venix likes this.
  3. Venix

    Venix Ancient Guru

    Messages:
    3,440
    Likes Received:
    1,944
    GPU:
    Rtx 4070 super
    @Mpampis i remember very well the Rx 480 4gb came out with msrp of 199usd and 239usd for the 8gb price was the marketing of amd at the time that they brought vr gaming entrance to 199 usd
    and yes sadly yes they are and i do not like em at all from both camps !
    @Fox2232 well is kind of known that so many want to amd to bring killer cards so they can buy nvidia cheaper witch is sad ... the rx 470/480 -570/580 outside of the mining craze where criminally neglected and seeing the 1050ti selling like hot cake on 250 ... is just sad
     
    carnivore, Jagman, Mpampis and 2 others like this.
  4. Loophole35

    Loophole35 Guest

    Messages:
    9,797
    Likes Received:
    1,161
    GPU:
    EVGA 1080ti SC
    Link to that being confirmed? I speculated that considering the previous AMD launches but hadn't seen it stated anywhere. I see August but that is only one month after launch.
     
    airbud7 likes this.

  5. Loophole35

    Loophole35 Guest

    Messages:
    9,797
    Likes Received:
    1,161
    GPU:
    EVGA 1080ti SC
    I've seen August but again that is only a month after release on the 7th of July (likely paper with stock not hitting shelves till a week later).
     
    airbud7 and las like this.
  6. ZXRaziel

    ZXRaziel Master Guru

    Messages:
    425
    Likes Received:
    134
    GPU:
    Nvidia
    Still playing the catching up , I hope the they will bring something exciting out in my lifetime , it has been bit underwhelming in the graphics cards industry lately .
     
  7. cowie

    cowie Ancient Guru

    Messages:
    13,276
    Likes Received:
    357
    GPU:
    GTX
    I like navi already
    rumored price "fixing"
    super cards what ever they are
    getting better I think
     
  8. Fox2232

    Fox2232 Guest

    Messages:
    11,808
    Likes Received:
    3,371
    GPU:
    6900XT+AW@240Hz
    Show me historically when was it last time AMD gained market share by undercutting nVidia. 3 years ago AMD launched Polaris. I do not see any great improvement in their market share since then.
    Having faster product at lower price did not work... Doing same thing and expecting different results...
    Who do you have them for?
     
  9. alanm

    alanm Ancient Guru

    Messages:
    12,236
    Likes Received:
    4,437
    GPU:
    RTX 4080
    Its been a long time, but HD4850 ($199) and 4870 ($299) back in 2008 certainly helped them get a bump in market share. These cards arrived only within a month of Nvidias expensive GTX 280 and 260 cards that were priced at $650 and $450. Nvidia had to re-adjust their pricing as a result.
     
    airbud7 likes this.
  10. Fox2232

    Fox2232 Guest

    Messages:
    11,808
    Likes Received:
    3,371
    GPU:
    6900XT+AW@240Hz
    Exactly. As nVidia got Ageia. But since then they have stranglehold of proprietary tech. And no reason to react. Same way as intel has no big reason to react.
    If people want Nvidia to react, they'll have to stop buying their products. (Does not mean that they have to buy AMD's either.)

    People had chance to say no to Turing pricing. Their choice, consequences for everyone.
     
  11. airbud7

    airbud7 Guest

    Messages:
    7,833
    Likes Received:
    4,797
    GPU:
    pny gtx 1060 xlr8
    yep^ funny how soon we forget....
     

  12. cowie

    cowie Ancient Guru

    Messages:
    13,276
    Likes Received:
    357
    GPU:
    GTX
    soon? launched in June 2008
    was over a decade ago
    amd happened to be better for "3dbenching" then intel was at that time too.:)

    its all just price placement now price it on how fast it is compared to the other guy,both seem to care about the bottom line of coarse so higher the better
     
  13. J Guy

    J Guy Guest

    People didn't talked too much about what could scalability be ... Could Amd copy the Zen chiplet architecture to Navi ??? If you look at the second picture in "Tech preview: Radeon RX 5700 and 5700 XT, https://www.guru3d.com/articles-pages/tech-preview-radeon-rx-5700-and-5700-xt-(navi),1.html we can see 20 similar patterns all around the center. 20 * 128 = 2560 shaders ; 18 *128 = 2304 shaders. Numbers match. This could be the first iteration and second should be 128 shaders becoming a chiplet and then AMD could repeat the Zen success, in lowering cost and maximizing the number of shaders as they did with CPU Cores.

    That's my 2 cents !
     
  14. Fox2232

    Fox2232 Guest

    Messages:
    11,808
    Likes Received:
    3,371
    GPU:
    6900XT+AW@240Hz
    GPU chiplets are in pipeline. GPU itself is embedded in infinity fabric already since Vega. For certain tasks Chiplets are no problem. For other tasks, access speed to memory attached to other GPU chiplet(s) may prove to be an issue.
    Using I/O hub as with Zen2 may prove to be problematic as GPUs use magnitude higher bandwidth than CPUs. Complexity may prove to be too much.
    We'll see with 8-channel 8chiplet Zen2. But that uses rather big I/O die and that has to be paid too.

    It may start to be useful in case AMD goes for 5 times 10 Dual-CU (20 CUs per chiplet = 1280SP in 1st Navi configuration) => 6400SP.
    But monolithic GPU with 5120SP may still have reasonable size (price) on 7nm to offset cost of interposer for chiplets and huge I/O die.
     
    Aura89 likes this.
  15. Loophole35

    Loophole35 Guest

    Messages:
    9,797
    Likes Received:
    1,161
    GPU:
    EVGA 1080ti SC
    @Fox2232 do you know if RDNA has a CU limit like GCN did?
     
  16. Fox2232

    Fox2232 Guest

    Messages:
    11,808
    Likes Received:
    3,371
    GPU:
    6900XT+AW@240Hz
    It should not. I think that it is reason why RDNA on macro building level looks like it is GCN partly turned inside out. But I can't remember it being written on any slide or supporting text.

    64CU limit was end of the road for AMD since Fiji. Since that point AMD could only go for clock and beefed up CUs. Doing that again would be end of their GPU division and claims that they are going to deliver/compete with enthusiast GPUs again would be false.
    (Or rather those GPUs would be limited to mainstream performance for some time and then to entry level.)

    They may have one of following approaches:
    - Current Shader Engine has 10x Dual-CU (1280SP)
    - > This can be either duplicated (more Shader Engines) or count of Dual-CUs per SE may go up
    - > Duplicating entire SE may have some issues with access to parts that are needed but are in center of GPU (ACEs, Geometry Processor, ...), but that's just speculation on my side as bandwidth required may be actually pretty small
    - Each SE caries rasterization and L1, those can be beefed in case more CUs are used per SE too

    I honestly think that every weakness I may come with may prove to be overcome just by Infinity Fabric on which AMD made big bet and it seems to pay off in CPUs.
     

Share This Page