LOL.
Anyway, I have enough doubt about the next gen of cards that I'm probably going to wait until both companies have stuff in retail so I can see what's up. However, none of the current crop of DX12 games interest me so I'm not sure that it really matter too much for my use case. I may just hang onto my 290 and game until the big chip cards come out at the end of the year/early next year and see how the hands play out in the video card poker game.
Silverforce - you get it but try to look beyond async. Look at what is coming next. This is game changing for real.
Yes I have a vid on this coming soon, it's an "epic" but hopefully within a few days. Been losing sleep over this one lol.
So why don't they do it now?
Somehow I feel like your underestimating Nvidia's ability to undermine AMD's advantage in DX12 ...
Nvidia could literally go on a buying spree for AAA game exclusivity on their GPUs for the next 2 years ...
DX12 won't matter if there are no killer apps that will be using it or in AMD's favour ...
The point I was trying to make is that AMD is far from being in the clear or safe ...
Because they don't know AMD's plans yet ?
Even if Nvidia ends up with worse perf/mm^2 in DX12 titles as long as they can retain the performance crown all is fine for them since it'll hardly change their brand perception as the best in the industry when AMD may not bring up a 500mm^2+ competitor ... .
MS is pushing developers to use it, they feature video tutorials on how to best program for DX12 and it's big focus for the GPU is multi-engine rendering. Got lots of particles? Use the front-end ROPs to simulate them. Don't waste shaders on it when you don't have to. Same for all your shadow maps, SSAO etc.
Because they don't know AMD's plans yet ?
Brand is only relevant when you're selling to public consumers.Even if Nvidia ends up with worse perf/mm^2 in DX12 titles as long as they can retain the performance crown all is fine for them since it'll hardly change their brand perception as the best in the industry when AMD may not bring up a 500mm^2+ competitor ...
I'm not "understimating" Nvidia's huge marketing advantage. What many of you haven't realised yet is that AMD is removing brand from the equation.
More importantly, many are underestimating brand loyalty/consumer attachment. Kepler cards have been performing very poorly in the last 15 months (literally since November 2014 they started bombing) and that didn't stop Maxwell from dominating AMD.
-> NV got away with 3.5GB VRAM lies and showed 0 remorse. Didn't matter.
-> NV blocked mobile dGPU overclocking, only to later call it a bug and re-enabled it after enthusiasts complained. Didn't matter.
-> NV cards outside the 980Ti/Titan X have bombed in most AAA games in the last 4 months. Didn't matter.
-> NV has had pretty poor price/performance and VRAM gimp with 750->960 2GB. Didn't matter.
You are not telling the truth. AMD made serious market share gains and for the first time after AMD bought ATI they had overall GPU market share lead. AMD had > 40% desktop and close to 60% notebook GPU share.We also saw AMD completely dominate NV for 6-9 months with HD5850/5870 and top-to-bottom HD7000 vs. Kepler launch. Even with a big head-start with NV having no response and selling outdated products with inferior perf/watt, perf/mm2, price/performance, AMD failed to make headway in profits or market share. In fact, even with bitcoin and ethereum mining making AMD cards free, they are hardly making a dent in market share.
The ONLY way for AMD to start recovering is by getting OEM design wins and getting large customers on-board, and re-focusing its efforts on the mobile dGPU market. Even if AMD were to beat NV by 10-20% in the DIY desktop market, it wouldn't be enough as we've seen in the past.
RS I sometimes get the feeling you are just too impulsive to jump to conclusions. Lets see how Polaris 10/11 and GP104/GP106 turn out in performance and pricing. Remember the volume is at lower price points so if Polaris 10 and Polaris 11 beat the competition's cards at comparable price points and provide comparable or better efficiency then they will do very well. AMD need a card like HD 4870 which is priced to sell and tremendously competitive. Remember HD 4870 never beat the GTX 280 but it brought AMD back in the game after the HD 2900XT fiasco. The times now are more difficult for AMD as they have gone to historical lows of market share in more than 2 decades (including ATI). AMD need good products with great pricing to get back to traditional 35-40% market share.NV's strategically launching GP104 means that even if people got burned with Kepler or Maxwell, they will still see GP104 smashing Polaris 10. Once they see NV completely dominate anything AMD has starting June 2016, everything negative about NV will be forgotten and those users still on 660Ti/670/680/770/780/780Ti cards will be upgrading in droves!
I agree. AMD may be able to claw back some market share with Polaris 10/11 if they price them very aggressively since for a short period they will be competing against 950/960/970 but what about after NV launches GP106/107? If NV has GP104 that wipes the floor with Polaris 10 for 6 months, the king-of-the-hill brand perception will sell GP106/107 even if they are inferior to AMD's parts. We literally saw this play out for 10+ years. Average gamer will automatically assume if GP104 is the most advanced and fastest GPU, then GP106/107 derivatives are also better than Polaris.
It's the opposite actually, AMD want devs to avoid using those specialized units when those resources are more scarce compared to Nvidia. Nvidia has more geometry processors, ROPs, and a bigger front-end so it would do AMD no good to recommend that approach ...
Are you kidding? NV can't do it mate. They don't support DX12's multi-engine approach, no hardware async compute. No running graphics + compute queues in parallel.
They cannot use a compute queue to target ROPs for particle simulation or shadow map in parallel to graphics. They can't even use their DMA in parallel with graphics, which is why they got hammered in Quantum Break. AMD's Copy Queues all running in parallel with the main graphics rendering. Look in the QB thread for proof.
http://forums.anandtech.com/showpost.php?p=38164220&postcount=349
This is the major flaw of not having Async Compute support and going with a single engine design. You can't access the subunits in parallel. While SP/ALUs are doing work, the DMA and ROPs are idling, and vice versa.
AMD basically wants an ALL compute future, a la Intel Larrabee style ...
Brand loyalty matters and surely Nvidia is the stronger brand. But AMD was actually gaining market share in Q1 and Q2 2014 with Hawaii and reached 38% market share before Maxwell launched and destroyed AMD's market share. AMD had older, slower and much more power inefficient cards. AMD did not turn up to the fight and they were decimated.
You are not telling the truth. AMD made serious market share gains and for the first time after AMD bought ATI they had overall GPU market share lead. AMD had > 40% desktop and close to 60% notebook GPU share.
RS I sometimes get the feeling you are just too impulsive to jump to conclusions. Lets see how Polaris 10/11 and GP104/GP106 turn out in performance and pricing.
Remember the volume is at lower price points so if Polaris 10 and Polaris 11 beat the competition's cards at comparable price points and provide comparable or better efficiency then they will do very well.
AMD need a card like HD 4870 which is priced to sell and tremendously competitive. Remember HD 4870 never beat the GTX 280 but it brought AMD back in the game after the HD 2900XT fiasco. The times now are more difficult for AMD as they have gone to historical lows of market share in more than 2 decades (including ATI). AMD need good products with great pricing to get back to traditional 35-40% market share.
You are only looking at the first start of that HD5800 generation. Generations roughly last 2 years or so. What happened during HD5800/6900 vs. GTX400/500 generation? You know well. AMD got decimated. Most of the key metrics that NV fans have touted with Kepler and Maxwell as key selling features, AMD won during those generations.
I am connecting the dots. There are repeating rumors of 970->980Ti line-up being discontinued and GP104 taking over the price points of those cards. There are no rumors of Fiji cards being discontinued. There are rumors that Polaris 10 is a small chip (232mm2) with only 2304-2560 shaders. How in the world is that enough to beat 980Ti by 20-30%? AMD themselves said their goal was to bring 290/970 spec to lower price levels. Since we were shown Polaris 11 as a 950 competitor, it stands to reason that Polaris 11 isn't going to be the card bringing 290/970 performance level. That leaves us with Polaris 10 as that chip. I don't understand how can Polaris 10 be able to go head-to-head against a 1080 that should outperform 980Ti by 25-35% and yet it's also bringing 290/290X performance < $299?
Again, if I take perf/watt of Maxwell and Tonga, and apply 2.5X to AMD architecture, and 2X to Maxwell, Pascal wins. That's because AMD is massively behind AMD in perf/watt unless it's the Nano. On AMD's road-map, the 2.5X perf/watt isn't over the Nano. Again, I am just connecting the dots here. Doesn't appear to me that AMD's Polaris will somehow beat Pascal in perf/watt. At least there isn't sufficient data to support this assertion.
- Having lots of market share but making little $ (HD4000->6000 generation) isn't the answer. It's why Lisa Su finally abandoned this strategy.
HD4870 also beat $100 more expensive GTX260. When I got my 4890, it cost barely more $ than a much slower GTX260 216 and less than the GTX275. Back then AMD delivered more performance on the mid-range and their cards cost less, at the same time. This would be like having Vega 11 priced at $299 and beating $399 NV Pascal. Why do you think that's going to happen? AMD is content selling slower performance for $600+ with Fury X.
To me ground-breaking would be bringing 980Ti/Fury X performance to $299-349 price level in June. Do you honestly believe Polaris 10 can do that with 256-bit bus and 8Gbps GDDR5?
Fiji - 275w
GTX 980 Ti - 250w
Now divide the first by 2..5 and the second by 2 and see which one is smaller. I am not saying thats happening. Just lets wait and see what happens.
AMD should find a way to make DX12 10x worse of a nightmare for Nvidia compared to when they had to deal with GameWorks ...
Well I don't want anyone to suffer bad gameplay based on choosing the wrong brand of card, but yes there could be a certain element of revenge for AMD here.Make Nvidia's top tier suffer dips below sub-20FPS, that will be the only way for consumers to to pay attention to AMD ...
They already have. It's incredibly simple as well, and pure genius, but it won't be seen until the next generation of consoles.
Well I don't want anyone to suffer bad gameplay based on choosing the wrong brand of card, but yes there could be a certain element of revenge for AMD here.
In the end you're right, this is the only thing that gamers respond to otherwise GameWorks wouldn't exist at all.
any hint?
Soon, within a couple of days. I'm working on the video now but it's huge 30 minute+ already. This stuff is gonna blow people's minds.
iam guessing its adoredTV
Because they don't know AMD's plans yet ?
Even if Nvidia ends up with worse perf/mm^2 in DX12 titles as long as they can retain the performance crown all is fine for them since it'll hardly change their brand perception as the best in the industry when AMD may not bring up a 500mm^2+ competitor ...
No need for them to spend money just yet since their doing fine in a lot of AAA titles like Tom Clancy's The Division, Doom, Far Cry: Primal, Need for Speed and better in Dark Souls 3 plus let's not forget about the official launch for ARK: Survival Evolved just yet ...
lol man every time i hear him i always wanna get a beer lolOh hes the scottish dude Watched his vids before.
lol man every time i hear him i always wanna get a beer lol
That is good news for all Kepler and Maxwell owners!New nvidia cards will have double the compute and we will be back to the old standards,maxwell and earlier will continue to suck at dx12 compute-only games but the new cards will run them twice as fast...