AMD Mantle could get you 20% more performance

Published by

Click here to post a comment for AMD Mantle could get you 20% more performance on our message forum
https://forums.guru3d.com/data/avatars/m/180/180832.jpg
Moderator
The Mantle API has just 8 percent overhead
hmm i assumed it didnt have any overhead at all from earlier presentations...
https://forums.guru3d.com/data/avatars/m/243/243536.jpg
nice article, mantle probably had a small hand in NVidia's recent price drop, shame dice can't even say the word 'nvidia' though.
https://forums.guru3d.com/data/avatars/m/164/164033.jpg
hmm i assumed it didnt have any overhead at all from earlier presentations...
That sounds pretty much an impossibility to be honest to not have any since it's still api inbetween 😯 But 8 vs 40 is like really good 😀
https://forums.guru3d.com/data/avatars/m/101/101307.jpg
Yes, 8% isn't much. Way better than 40%.
https://forums.guru3d.com/data/avatars/m/101/101307.jpg
nice article, mantle probably had a small hand in NVidia's recent price drop, shame dice can't even say the word 'nvidia' though.
Why must they say nVidia? It could include INtel or other future vendors. Also, since when does nV drop AMD name?
data/avatar/default/avatar14.webp
hmm i assumed it didnt have any overhead at all from earlier presentations...
Impossible. Even a simple operation like copying some memory from main RAM to the GPU will involve the CPU. Commands will still be sent to the GPU as well. I think what AMD is getting at here is that modern GPUs don't need as much "preparation" of the data before letting it go to work on the render. DirectX hides a lot of hardware functionality behind software abstractions which helped developers work with the fixed-function nature of older GPUs. Now those abstractions are just standing in the way of the sophisticated general-purpose nature of recent GPUs. On a side note, my take on this 20% claim is a best-case scenario. People are screaming for numbers on this Mantle thing and I think this guy let a number slip that is probably just going to disappoint in most situations. I am more interested in the other render possibilities that may be opened up by allowing engines to use many-but-simple draw calls to achieve other effects than what we've seen over the past several years. I, for one, am ready for new games that are more than just a twist on the Unreal DX9 engine. I'd like to see some new and exotic rendering possibilities take hold - like photon mapping or metropolis light transport for example.
https://forums.guru3d.com/data/avatars/m/247/247476.jpg
Really curious how is Nvidia gonna reply to Mantle. Gsync isn't gonna be the thing though it's a great idea that someone should have gotten years ago. Anyway they can't afford to let AMD gain a lead in AAA games just thanx to an API with worse hardware.
https://forums.guru3d.com/data/avatars/m/164/164033.jpg
Really curious how is Nvidia gonna reply to Mantle. Gsync isn't gonna be the thing though it's a great idea that someone should have gotten years ago. Anyway they can't afford to let AMD gain a lead in AAA games just thanx to an API with worse hardware.
g-sync would be great if it wasn't tied to nvidia and to asus monitors (not even all asus monitors will support it ofc)
data/avatar/default/avatar14.webp
Really curious how is Nvidia gonna reply to Mantle. Gsync isn't gonna be the thing though it's a great idea that someone should have gotten years ago. Anyway they can't afford to let AMD gain a lead in AAA games just thanx to an API with worse hardware.
Does AMD have worse hardware ?
data/avatar/default/avatar34.webp
Hopefully this should give my 7950 a nice boost 🙂
https://forums.guru3d.com/data/avatars/m/52/52796.jpg
Does AMD have worse hardware ?
Nothing I've seen has indicated that to be the case. The only problem I see at the moment is with their stock coolers, which is easily rectified. In some respects you could argue that they have better hardware, it's apples to oranges. Both have their selling points.
https://forums.guru3d.com/data/avatars/m/252/252138.jpg
If Mantle works like how it's said to work - fantastic. I, however, don't care about the marketing hype until I actually see real benchmarks.
data/avatar/default/avatar10.webp
Nothing I've seen has indicated that to be the case. The only problem I see at the moment is with their stock coolers, which is easily rectified. In some respects you could argue that they have better hardware, it's apples to oranges. Both have their selling points.
Their stock coolers are trash since HD4 series. But there are many vendors , so thats not an issue right now.
https://forums.guru3d.com/data/avatars/m/195/195639.jpg
hmm i assumed it didnt have any overhead at all from earlier presentations...
It will have overhead as it is an API that talk between the application and the hardware. The question is, how much is the overhead cost.
https://forums.guru3d.com/data/avatars/m/99/99142.jpg
I expected more than 20%
https://forums.guru3d.com/data/avatars/m/228/228458.jpg
We'll find out next month how well it's going to work.
data/avatar/default/avatar36.webp
10-20% would be nice. But i expect more on heavly bottlenecked GPUs (like mine).
https://forums.guru3d.com/data/avatars/m/195/195639.jpg
I think 20% is too much and probably won't be met depends on the type of games. Mantle is just one of many API that developers used, so remember that even if when Mantle API improved the overhead, there are still function calls that rely on other API and DirectX which might nullify the improvement. Especially with CPU heavy games i suppose?
https://forums.guru3d.com/data/avatars/m/101/101307.jpg
I expected more than 20%
Maybe 20% is worst case scenario.
data/avatar/default/avatar33.webp
Which card(without mantle) is equivalent to a%20 mantle-boosted Stock HD7870pitcairn? Stock GTX670? Stock HD7950? What about overclocking the 7870pitcairn to 1275/1375 ? (1330/1525 for benchmarks) Stock GTX680? (GTX770 for benchmarks?) Stock HD7970? (R9-280x-revized for benchmarks?)