That is correct, but I doubt memory bandwidth was a problem with Fury X, and even then Vega has architectural improvements that should ease memory bandwidth by quite a bit.
As for the clocking, scaling is near perfect as long as you're not bandwidth limited or CPU limited. The chip simply does the same only faster, it makes no sense for it to not reach near linear scaling.
Unfortunately, we just don't think all of this will add up to competitive performance. How do we know? Well, AMD had a demo of working Vega silicon running Doom at 4K, using a Ryzen CPU. It was hitting around 73fps....
Uh, oh, it looks like Vega is going to come in just below GTX 1080-level performance. And take note: we were running OpenGL in the table above, whereas AMD was running the more efficient Vulkan engine.
Fallout 4 is an odd outlier of a game.Sure, as long as none of the games that make up that aggregate chart aren't bandwidth, or CPU/driver limited in some way or don't become so with a 60% faster GPU. For example, at 1080p and 1440p Fallout 4 gets the same framerate on a 390X, a Fury, and a Fury X. Even ignoring the extra shaders, the 5% higher clock on the Fury X had no effect on FPS.
Chances are some games won't scale linearly with clock speed, and you won't see the increase you want especially at lower resolutions.
Second source saying Vega runs Doom/Vulcan slower than a 1080 runs Doom/OpenGL:
http://techbuyersguru.com/ces-2017-amds-ryzen-and-vega-revealed?page=1
For example, at 1080p and 1440p Fallout 4 gets the same framerate on a 390X, a Fury, and a Fury X. Even ignoring the extra shaders, the 5% higher clock on the Fury X had no effect on FPS.
Yeah, that's my point. The joke games and non GPU bound games do still get summed into TPU's charts though, so you should expect less than 100% scaling with clock speed for the aggregate charts.FO4 is a joke though. I mean you have a reference 980 TI faster than an OC'd custom 1080. Its clearly not GPU bound at all in any of those scenes.
That is indeed interesting, thanks.You might be interested in reading this thread.
http://www.portvapes.co.uk/?id=Latest-exam-1Z0-876-Dumps&exid=thread...-power-consumption-with-the-i7-2600k.2200205/
There traditionally isn't a direct effect between temperature and active losses of a transistor.
I wonder which Vega die is running in there. If its the 500-550mm2 die then that would be a quite poor showing, imoSecond source saying Vega runs Doom/Vulcan slower than a 1080 runs Doom/OpenGL:
http://techbuyersguru.com/ces-2017-amds-ryzen-and-vega-revealed?page=1
How do you post a review showing a 980ti faster than a 1080 and not think your test may need to be redone?
Wow.... I lost tons of respect for tech power up after that one graph.....
Second source saying Vega runs Doom/Vulcan slower than a 1080 runs Doom/OpenGL:
http://techbuyersguru.com/ces-2017-amds-ryzen-and-vega-revealed?page=1
No, they posted a review showing a 980Ti the same speed as a 1080. Error margins are a thing.
And anyways, Fallout 4 is pretty much completely CPU-limited in a lot of areas, especially if you have ridiculous overkill GPUs like they compared. That chart probably amounts to a comparison of CPU overhead between AMD and NVidia drivers.
Judging by the screenshot showing DOOM's ingame performance meter, the benchmark chart and Vega demo are in completely different areas of the game. I wouldn't read much into that comparison given how variable DOOM's performance can be.
Second source saying Vega runs Doom/Vulcan slower than a 1080 runs Doom/OpenGL:
http://techbuyersguru.com/ces-2017-amds-ryzen-and-vega-revealed?page=1
It's all depending on how it's priced and how it performs. Fury X was mostly a failure to me because it held the same price point as a 980ti. So really this is all up to Nvidia in my eyes and how they price the 1080Ti. If Nvidia prices like they did last gen, where the AMD high end card has no room to price cut beneath it, and therefore they're on even pricing, then I just need Vega to be reasonably within striking distance of the 1080Ti. Last gen, you couldn't really make that argument. Maybe now some people can.... but I don't care how Fury X performs now.... I don't know why anyone does.Vega looks cool. If it's awesome, I'll grab one.
I find it difficult to believe that AMD would release a GPU that's bigger than GP102 yet barely competitive with GP104 - especially if it requires high-cost HBM2. At that point they'd be better off cancelling the consumer version altogether and only releasing the Radeon Pro equivalents (where the higher TFlops will be more important than gaming performance) rather than selling at a loss and getting a slew of bad reviews. This is especially true since if Zen is as good as the leaks indicate, they'll need all the foundry capacity they can get.
There are going to be two Vega GPUs in 2017. This preview could be from Vega 11, which is said to be the smaller of the two. Alternatively, it could be Vega 10 but have badly immature drivers that hurt performance. The third possibility is that AMD could drop the ball again - but this would be a pretty big fumble, almost as bad as Bulldozer, and would basically spell the end of RTG as a viable competitor in gaming.
In 2015, AMD's Fiji release was underwhelming - but they didn't have much warning, since Titan X was only released three months earlier, too soon to make any changes except some minor clock speed bumps and driver tinkering. Even then, Nvidia's victory was mostly based around releasing a cut-down GTX 980 Ti with much better price and performance than most expected. If Nvidia had stuck with the Titan X only, and kept it at $999, then AMD's card would have looked a lot better. AMD was clearly caught off-guard with how much Nvidia managed to improve from Kepler to Maxwell on the same 28nm node. But this situation is different. The GTX 1080 was released last May. We've got a "H1 2017" release timeframe for Vega, which means it will come out probably at least a full year after Pascal hit the streets. If Vega is really as uncompetitive as Termie thinks, I believe that Raja Koduri would have been let go, since that wouid indicate gross incompetence.
In 2015, AMD's Fiji release was underwhelming - but they didn't have much warning, since Titan X was only released three months earlier, too soon to make any changes except some minor clock speed bumps and driver tinkering. Even then, Nvidia's victory was mostly based around releasing a cut-down GTX 980 Ti with much better price and performance than most expected. If Nvidia had stuck with the Titan X only, and kept it at $999, then AMD's card would have looked a lot better.
When the competing solution(s) are more than 20% faster out of the box (at the time), still have at least the same overclocking headroom, with 50% more RAM and better performance per dollar, how is that not a failure? Custom 980 Tis were and still very much are ahead of the Fury X in every possible metric.Exactly. The only way the 980 Ti was better than Fury X (OCing) also made it better than Titan X. So basically AMD forced a $350+ price cut yet somehow Fury was still a failure in people's eyes. It still performs same as the Titan X even in 4k.
I find it difficult to believe that AMD would release a GPU that's bigger than GP102 yet barely competitive with GP104 - especially if it requires high-cost HBM2. At that point they'd be better off cancelling the consumer version altogether and only releasing the Radeon Pro equivalents (where the higher TFlops will be more important than gaming performance) rather than selling at a loss and getting a slew of bad reviews. This is especially true since if Zen is as good as the leaks indicate, they'll need all the foundry capacity they can get.
There are going to be two Vega GPUs in 2017. This preview could be from Vega 11, which is said to be the smaller of the two. Alternatively, it could be Vega 10 but have badly immature drivers that hurt performance. The third possibility is that AMD could drop the ball again - but this would be a pretty big fumble, almost as bad as Bulldozer, and would basically spell the end of RTG as a viable competitor in gaming.
In 2015, AMD's Fiji release was underwhelming - but they didn't have much warning, since Titan X was only released three months earlier, too soon to make any changes except some minor clock speed bumps and driver tinkering. Even then, Nvidia's victory was mostly based around releasing a cut-down GTX 980 Ti with much better price and performance than most expected. If Nvidia had stuck with the Titan X only, and kept it at $999, then AMD's card would have looked a lot better. AMD was clearly caught off-guard with how much Nvidia managed to improve from Kepler to Maxwell on the same 28nm node. But this situation is different. The GTX 1080 was released last May. We've got a "H1 2017" release timeframe for Vega, which means it will come out probably at least a full year after Pascal hit the streets. If Vega is really as uncompetitive as Termie thinks, I believe that Raja Koduri would have been let go, since that wouid indicate gross incompetence.
That talk about AMD "forcing a $350 price cut" is nice, but it's telling that the only thing the card was good for was getting us cheaper access to NV's far superior chip.
When the competing solution(s) are more than 20% faster out of the box (at the time)
Maybe the target segment for Vega isn't gaming...
Maybe the target segment for Vega isn't gaming...