http://wccftech.com/amd-fiji-xt-r9-390x-zauba/
Hopefully, we'll see 390X parts with more than 4GBs of VRAM though.
Hopefully, we'll see 390X parts with more than 4GBs of VRAM though.
Last edited by a moderator:
TSMC’s 20 SoC has been described as being inappropriate for discrete graphics cards by some due to its low power nature. However TSMC’s 20nm SoC process has proven to be easily capable of hitting excellently high clock speeds. The process manages to sustain frequencies just as high as 28nm if not slightly higher, making it an ideal candidate for discrete GPUs.
AMD really needs 300 series to be good. They basically need whatever it takes to hold out for the next 2 years until 14/16nm for GPUs drop and Zen is out. Hopefully 300 series and booming XB1/PS4 sales are enough for them to stretch it to late 2016. After that things should be easier. I am far less concerned about AMD's 300 series competing well on the desktop considering just how low the performance bar that was set by 970/980.
Pretty much AMD is holding its own with outdated 290/290X designs, which themselves were not even an improvement over Tahiti in terms of IPC and perf/watt. I basically view 290/290X as a larger Tahiti with a bigger memory bus and more units. The underlying architecture is more or less intact. Even geometry performance hardly improved with 285 beating 290X by nearly 70%. This shows that the original GCN was really a great architecture as it has now kept up for 3 years but a drastic improvement is needed for it to evolve and be relevant for 2015-end 2016 as games become even more advanced.
I maintain that AMD's 390X must be a big improvement over a 290X because I don't think it would have been that difficult for AMD to squeeze 15% more performance from a hybrid cooled and more mature 28nm 295X. If AMD didn't even bother refreshing Hawaii like they did 7970-->7970Ghz, sounds like they put all their effort into 300 series as a do or die.
What's more concerning though is AMD's ability to gain mobile dGPU market share. Once the major OEMs lock in 850/860/965/970/980M chips, they don't tend to release newer products for 6-8 months. Usually major laptop designs are updated around new Intel CPUs and GPU launches. These tend to come around June/July and Late fall/Holiday season. If AMD wants to be relevant in 2H of 2015 for mobile wins, they really need to have mobile 300 series ready by Computex, to align with Intel's Broadwell/Skylake launches. I suppose this time may be a slight exemption since Windows 10's launch could result in the notebook makers and OEMs updating their products more than the usual 2x a year, but generally speaking NV has the next 5-6 months already locked in with Maxwell's mobile design wins.
Apparently it is frowned upon to call out posters who claim the exact opposite of all public statements and leaks from AMD regarding the upcoming 300 series Radeons.
As far as I know, only 4 parts are really made in volume on TSMCs 20nm process as of today. The A8, A8X, 810 and 615. None of them got high clocks, and the last 2 are having severe overheating issues and barely hitting 2/3rds of the frequency target.TSMC’s 20 SoC has been described as being inappropriate for discrete graphics cards by some due to its low power nature. However TSMC’s 20nm SoC process has proven to be easily capable of hitting excellently high clock speeds. The process manages to sustain frequencies just as high as 28nm if not slightly higher, making it an ideal candidate for discrete GPUs.
AMD has special privileges to Global Foundries as we all know, so the usual "dGPU comes after mobile" doesn't necessarily apply here.
I largely agree with Bateluer's excellent riposte. I'd just add one thing: 14 nm is coming this autumn. AMD has special privileges to Global Foundries as we all know, so the usual "dGPU comes after mobile" doesn't necessarily apply here.
Finally, Hawaii is 1.5 years old now. This raises the interesting question: releasing the 380X/390X as soon as possible is important, and it could happen on 20 nm.
But what then happens on 14 nm if it's ready due in autumn and Nvidia is still stuck on TSMC? AMD could deliver a double blow and essentially compete against themselves and I hope that they do that; only way to win not only 2015 but also quite some distance into 2016. In the long run, that's good for competition since it would even out the market share between the two companies.
Yeah, I'm saying that as someone who has 290s in Crossfire, but unless something spectacular happens, I'm going Pascal in 2016 and would like Nvidia to feel the pressure from AMD so that I don't get robbed trying to upgrade
snip
I think you a little confused. How outdated do you believe the Hawaii skus are? A 290X still offers performance near the GTX 970/980 while costing hundreds of dollars less. Seems like it was a solid design to me, lackluster reference cooler not withstanding. You really, really need to stop repeating this. Its flat wrong, no matter how many times you repeat it. The 290s have hit 200 repeatedly now, and for that price, its a steal. 970-ish performance for ~150 dollars less. 290X is usually ~250-300 dollars less than a 980 while offering 90% of its performance.
And I'm sure the 20nm 390X will be a nice bump from the 290X, especially with the hybrid Hydra cooler it'll likely launch with. The reference cooler was the only real negative with the Hawaii GPU after all. 7970 to 7970Ghz wasn't much of a refresh either, slight OC on the 7970. You can do that on any 290X with a non-reference cooler. My Asus DCU2 card comes with a comparable OC from the factory.
OK, this is valid. AMD's mobile skus are lacking. The market wants slim, light long lasting ultrabook type devices, and these designs don't lend themselves to power hungry GPUs, from any manufacturer. Most go with the IGPs Intel provides, and they're not gaming parts. Lenovo's Yoga 1, 2, and 3, for example, all boast nearly identical GPU performance due to Intel's IGP. The 'green' movement in IT pisses me off sometimes. 3 generations of a product line and performance has remained static.
Reading your comments in various threads, it seems AMD's primary problem isn't technology, but rather marketing. You've cut the performance of the 290/29)X drastically in your head, putting the 970/980 on some kind of pedestal. In reality, the Hawaii parts cost substantially less than the Maxwell skus while offering performance thats only slightly behind. I loathe to suggest a company focus more on their PR and marketing, but in AMD's case, I think its very important given the level of falsehoods and blatant misinformation that people like yourself keep repeating.
It all depends on how much AMD is making per unit. The 290/290X is an established, mature product. All the kinks have been worked out, production issues should be non-existent by now and yields should be stable.Lololol
Wow, thats funny.
Your going on and on but dont get what he is saying at all.
RS never said the 290 was a bad buy, this is not even close to what he is talking about. Your missing the whole point.....and then some.
RS wants to see AMD succeed, he wants to see them doing well. I think many people would/should want this. In that light, AMD having to sell a 512bit 6billion transistor chip for 200 bucks isnt this great thing you seem to think it is. Not for AMD.
No way no shape. Its not good for the company. This is harmful, not helpful.
You have to think about it. The less they make, the more they cut back. Already falling behind in what they spend in R&D, its bad enough as it is. Amd did not intend hawaii to be a 200$ part.
You can keep telling yourself that everything is great but RS is thinking a little more deeply than you. He wants to see AMD succeed and understands what it will take.
I think you went too harsh on 290X here, probably because of the lack of personal experience with the card. Fully dynamic clock engine alone is a huge improvement, i still enjoy how stutter free and power efficient the card performs at variable clocks. And raw rendering power is still enough to run most games in 2.5k as long as you tune some overly costly things (generally any option that spikes GPU usage by 30-50% vs previous level of quality, good example - ultra lighting in MGS GZ at night) down.Pretty much AMD is holding its own with outdated 290/290X designs, which themselves were not even an improvement over Tahiti in terms of IPC and perf/watt. I basically view 290/290X as a larger Tahiti with a bigger memory bus and more units. The underlying architecture is more or less intact. Even geometry performance hardly improved with 285 beating 290X by nearly 70%. This shows that the original GCN was really a great architecture as it has now kept up for 3 years but a drastic improvement is needed for it to evolve and be relevant for 2015-end 2016 as games become even more advanced.
I think if AMD is going to at least do a soft launch before long in order to maintain is customer base.
The next trick when it does launch is keep stock in place from all the miners scooping them up.
I don`t understand WCCFTech`s logic.
Tegra Maxwell is made with TSMC 20nm SOC process. Therefor R9 390X is confirmed with 20nm?
What?
Do they know what SOC is? What it involves?
Let me know when R9 390X got the same power consumption as Tegra or any other SOC chip (Typical <5W).
Let me know when the R9 390X have a core voltage <1.00V.
Let me know when the R9 390X is even a bloody SOC, CPU and GPU and other small components on the same die.
I don't believe your first sentence is actually a sentence...and is mining even viable anymore?