Wednesday, January 16th 2019
AMD's Initial Production Run of Radeon VII Just 5,000 Pieces, Company Denies it
More news coming in on AMD's upcoming high-end graphics card, the Radeon VII, with Chinese media reporting that AMD's initial production run for the card is set to ship just 5,000 pieces worldwide. This comes hot on the heels of another report that the Radeon VII won't come in custom-designs by AMD's add-in board (AIB) partners, and that only the reference design will be repackaged and sold by them. What's worse, the source which leaked this production size also revealed that AMD is selling the card below cost-price, i.e., with each card sold, AMD is losing money. This probably explains Wall Street's cold response to the Radeon VII launch, but with a batch size of just 5,000 (roughly $3.5 million in sales at $699 a piece), this card has a negligible impact on AMD's bottom-line.
AMD posted a swift denial to both pieces of news, the size of its production run and the product's profitability. In a statement to MyDrivers, AMD said (translated): "We will not release production figures, but when released on February 7, AMD.com official website and AIB vendor partners will have products on sale, and we expect the supply of Radeon VII to meet the needs of gamers." In short, Radeon VII is shaping up to be the card you'd want to buy if you've sworn a blood-oath never to buy an NVIDIA product, and you need something to play games in 2019 at 4K with.
Sources:
MyDrivers, MyDrivers (2)
AMD posted a swift denial to both pieces of news, the size of its production run and the product's profitability. In a statement to MyDrivers, AMD said (translated): "We will not release production figures, but when released on February 7, AMD.com official website and AIB vendor partners will have products on sale, and we expect the supply of Radeon VII to meet the needs of gamers." In short, Radeon VII is shaping up to be the card you'd want to buy if you've sworn a blood-oath never to buy an NVIDIA product, and you need something to play games in 2019 at 4K with.
124 Comments on AMD's Initial Production Run of Radeon VII Just 5,000 Pieces, Company Denies it
1) He sets up (for example) a rendering benchmark and runs it on the CPU instead of the GPU's. He then concludes AMD and Nvidia render the same speed lol. Why would you mention this guy?
2) He proclaimed that "AMD is lying about prices" when demand overtook supply in late 2017. He doesn't understand basic market concepts. Why would you listen to this guy?
3) He has directly threatened other YouTubers on twitter with physical violence multiple times simply for disagreeing with him. You like this guy? You think he has good opinions?
Now why should I keep these facts to myself?
You are quoting someone who threw a public temper-tantrum when he didn't get a threadripper sample (and literally said he isn't using it anymore because of his hurt feelings, suggesting "pay for play"), threatened someone he supposedly found lived close to him, and seemingly sent fans to threaten a couple of youtube tech people:
Oh yeah, he can't even benchmark rendering correctly (and still hasn't corrected his video):
linustechtips.com/main/topic/829480-which-gpu-you-have-for-video-rendering-doesnt-matter-as-long-as-you-have-one/
^Jay saw the same render times between a bunch of cards and was confused. Good lord, rendering leverages the CPU mostly - you use GPU's for the previews. He doesn't even get how this works!
There, now I am providing links while you continue to spout complete nonsense, and try to shame my opinion.
So using this Bandwidth Calculator I get 1126 GB/s, or about 10% off the Vega 7 1229 GB/s. I think that's enough...
gpubandwidthcalculator.totalh.net/?i=1
I honestly wish they would ditch HBM already as it doesn't seem to be helping much in the consumer/gaming realm. Its not like it was when first released and showed great gains at higher res, and especially 4K UHD gaming. GDDR5X and GDDR6 can work just fine up there. Is it really cheaper? How much power does it really save (considering these cards use a lot more power per watt)? I just think HBM was stillborn. :(
But there is one thing that most people seem to have missed with the Radeon VII; AMD says it will be 25% better at the same power, and show benchmarks to indicate it's on par with RTX 2080, which would require an improvement of ~40% over Vega 64. Both of those can't be true at the same time. Radeon VII would have to be much better than 25% over Vega 64, or it's simply not on par with RTX 2080 in average gaming. I haven't seen any of the opinionators pick up on this. This is quite important as the card will be priced on par with RTX 2080.
Fair warning to all of those in a twist!
Lol, I couldn't imagine if it was 50W their cards would be using over 300W!
Seems that 30W per 8GB ram could be reasonable, could be more...could be less.
AMD hasn't given any power numbers as far as I know other than saying it has 2x8-pin. That only tells us the maximum potential draw, not typical. Being 7 nm and more or less same transistor count, the power number should be significantly improved from Vega 64.
Take a gander at benches of a healthily OCed vega. Nvidia becomes a joke as their minimums are awful (not that the ram is the culprit, but to give you the idea of gains on vega). Scoring way ahead in avg means nothing when your mins are under 60 lol. You'll need adaptive sync with that oscillation.
Production is the only problem. It saves space/power, so it's 100% the future unless someone wants to fund another type.
People claim GCN is starved of memory bandwidth, computational performance and fillrate (ROPs), but neither is true. GCN have plenty of memory bandwidth and computational performance compared to their Pascal and Turing counterparts, and fillrate is sufficient.
We all know what the problem with GCN is; utilization of resources. We have been over this many times before. The efficiency gap between Nvidia and AMD have increased with every generation since the initial GCN, and is also the cause of AMD's thermal problems, as they have to throw more and more "brute force" resources at it to achieve performance. If Vega had close to the level of resource utilization of Turing, it would have been able to compete, even without 7nm.
AMD is not going to make significant improvements until they have a new architecture. Still, Navi can do smaller improvements, like low hanging fruit such as tiled rendering. Tiled rendering would help memory bandwidth a little bit, but much more importantly it eases the GPU's task of analyzing resource dependencies, which is one of key causes of GCN's problems. So in the end, AMD might get greater benefits from tiled rendering than Nvidia.