AMD Mantle update...

[Ace123]

Umm... im trying to read the last part of your comment... how is the a8-7600 apu a FireGL card? ....its a socket Fm2+ Apu....

[blindbox]

Before everyone starts running out to buy AMD stock, keep in mind the 45% figure comes not from Battlefield, but Oxide Games? Starswarm demo - a 64-bit engine test first shown in December that attempts to fill space with thousands of ships on-screen at once kinda like the test on 3dmark Vantage. And it doesn?t apply to just any generic AMD card - rather the A8-7600, a new APU from the Kaveri line the manufacturer is showing at CES. A very expensive AMD FireGL card.

Where the hell did you hear that the 45% figure doesn't come from Battlefield? If it came from Oxide Game's starswarm demo, it won't be 45%. It would be 200%.

A8-7600 is a FireGL card? Oh man.

[STEvil]

oh wow..

[spursindonesia]

Now, XtremeSystem forum still tolerates this kinda trolling, and of course none of the self proclaimed "fair & balanced Graphic pundit & AMD fans basher" make any comment out of that.

[kuroikenshi]

Before everyone starts running out to buy AMD stock, keep in mind the 45% figure comes not from Battlefield, but Oxide Games? Starswarm demo - a 64-bit engine test first shown in December that attempts to fill space with thousands of ships on-screen at once kinda like the test on 3dmark Vantage. And it doesn?t apply to just any generic AMD card - rather the A8-7600, a new APU from the Kaveri line the manufacturer is showing at CES. A very expensive AMD FireGL card.

You Sir must come from planet Bizarro... I can see you have a nice valve tube amplifier on your Avatar..... maybe you should kinda stick to what you know, since you just demonstrated your knowledge on Amd's product line.

[Sparky]

Before everyone starts running out to buy AMD stock, keep in mind the 45% figure comes not from Battlefield, but Oxide Games? Starswarm demo - a 64-bit engine test first shown in December that attempts to fill space with thousands of ships on-screen at once kinda like the test on 3dmark Vantage. And it doesn?t apply to just any generic AMD card - rather the A8-7600, a new APU from the Kaveri line the manufacturer is showing at CES. A very expensive AMD FireGL card.

[Iconyu]

Before everyone starts running out to buy AMD stock, keep in mind the 45% figure comes not from Battlefield, but Oxide Games? Starswarm demo - a 64-bit engine test first shown in December that attempts to fill space with thousands of ships on-screen at once kinda like the test on 3dmark Vantage. And it doesn?t apply to just any generic AMD card - rather the A8-7600, a new APU from the Kaveri line the manufacturer is showing at CES. A very expensive AMD FireGL card.

Actually the Starswarm demo runs 200% faster on the A8-7600, but like I said that APU doesn't really have that much in the way of CPU resources to begin with.

[MaddMuppet]

Now, XtremeSystem forum still tolerates this kinda trolling, and of course none of the self proclaimed "fair & balanced Graphic pundit & AMD fans basher" make any comment out of that.

I would say it is more of an honest mistake. rather than a genuine attempt at trolling.

[mongoled]

I would say it is more of an honest mistake. rather than a genuine attempt at trolling.

Nah, the guy is a (fill in the blank)

I am a long time XS member, dont post much anymore just read, this 'person' only ever posts negative comments regarding anything to do with AMD.

[Olivon]

Wow.
Having a constructive discussion seems more and more difficult on the news section.
Whatever you post, people cry a river if the post it's not at the advantage of their dear brand.

P.S : No need to disrespect or discredit Hardware.fr. I know this site very well and they do a great job. Making such a move is futile.

[Hornet331]

Star Swarm Demonstration

https://www.youtube.com/watch?v=6PKxP30WxYM

take it for what ever it is worth.

Personal opinion: I find it hilarious that the only "advantage" they show over DirectX is motion blur. This reminds me a lot to the first metro game where they used a useless demanding motion blur technique ho put down every gpu at that time.
Not that motion blur is the first thing I disable in games anyway.

[blindbox]

Here's another one from CES. https://www.youtube.com/watch?v=yak25TKCCrc

[kromosto]

P.S : No need to disrespect or discredit Hardware.fr. I know this site very well and they do a great job. Making such a move is futile.

seems like a good site but their uber mode invention on nvidia cards are very suspicious i think.

[MaddMuppet]

Here's another one from CES. https://www.youtube.com/watch?v=yak25TKCCrc

It's a shame with a test like that, they can't have 2 identical machines. One running DX and the other mantle, side by side.

[Andrew LB]

My only excuse is I was half asleep (5am i believe) when I did a hack job cut-and-paste from here....

http://www.pcgamesn.com/battlefield/...e-over-directx

A couple of important caveats: the 45% figure comes not from Battlefield, but Oxide Games? Starswarm demo - a 64-bit engine test first shown in December that attempts to fill space with thousands of ships on-screen at once. And it doesn?t apply to just any generic AMD card - rather the A8-7600, a new APU from the Kaveri line the manufacturer is showing at CES. A very expensive AMD card.

It?s a claim and a half nonetheless. If AMD?s new bollocks turn out to be as doggy as they say, will you be busy justifying a new card to yourself this year?

[Andrew LB]

Don't expect Mantle anytime soon. AMD is now saying Q1 2014. So it can be as late as March 31....

[kromosto]

q1 is good if they can catch it last day or not. being late for a while is less important then going to market with lots of bugs.

[blindbox]

My only excuse is I was half asleep (5am i believe) when I did a hack job cut-and-paste from here....

http://www.pcgamesn.com/battlefield/...e-over-directx

45% comes from these FPS values, apparently. http://i.imgur.com/8tf2zwH.png

Latest I would say for Mantle would be the last day of February. I've never seen them being way too late to release a driver designated for January. That said I haven't updated my drivers lately because I never had any problems.

[LordEC911]

My only excuse is I was half asleep (5am i believe) when I did a hack job cut-and-paste from here....

http://www.pcgamesn.com/battlefield/...e-over-directx

I would suggest you get your news from somebody a bit more in the know...

[SKYMTL]

I would suggest you get your news from somebody a bit more in the know...

I have to agree with that.

AMD was claiming 300% improvement for the Starswarm demo.

45% is for BF4 with the A8 7600.

To me, that's particularly important since even a 15% bump in framerates makes a HUGE difference for APUs.

[KiSUAN]

I would suggest you get your news from somebody a bit more in the know...

I suspect he just get them from places that fit his schedule

[Stukov]

I have to agree with that.

AMD was claiming 300% improvement for the Starswarm demo.

45% is for BF4 with the A8 7600.

To me, that's particularly important since even a 15% bump in framerates makes a HUGE difference for APUs.

I think the reason you are seeing such a speed boost variance is based on what limitation a CPU bottleneck is affecting performance. While you may get 10% where no bottleneck exists, when you compare a slower CPU (such as AMD's APU) vs the fastest (Intel top of the line) you are going to see a much bigger boost with the APU % wise vs that of the Intel EE. You will also see greater improvement in a game which uses loads of CPU calculations like AI, such as the Swarm demo, Starcraft, or other RTS type games.

[Iconyu]

I have to agree with that.

AMD was claiming 300% improvement for the Starswarm demo.

45% is for BF4 with the A8 7600.

To me, that's particularly important since even a 15% bump in framerates makes a HUGE difference for APUs.

I don't actually trust results with Kaveri, there are too many unknown factors like HSA, the 512 shaders, and the fast memory to take into account. At the very least I would expect Mantle to push the GPU compute work over to the APU shaders to free up the GPU shaders. Which isn't something I can replicate on my Intel.

[SKYMTL]

I think the reason you are seeing such a speed boost variance is based on what limitation a CPU bottleneck is affecting performance. While you may get 10% where no bottleneck exists, when you compare a slower CPU (such as AMD's APU) vs the fastest (Intel top of the line) you are going to see a much bigger boost with the APU % wise vs that of the Intel EE. You will also see greater improvement in a game which uses loads of CPU calculations like AI, such as the Swarm demo, Starcraft, or other RTS type games.

No, the reason there is such a variance is that Starswarm was coded especially for Mantle. It's beyond a best case scenario. In 90% of the Mantle titles we see for the next few years, the standard DirectX + Windows driver will be the primary rendering tool while Mantle will be added in. Hence why there is a much lower gain in BF4, the poster child for an actual Mantle-supporting game.

I don't actually trust results with Kaveri, there are too many unknown factors like HSA, the 512 shaders, and the fast memory to take into account. At the very least I would expect Mantle to push the GPU compute work over to the APU shaders to free up the GPU shaders. Which isn't something I can replicate on my Intel.

HSA isn't active right now, nor will it come into effect within games. Games actually do a pretty good job of partitioning resources (especially those that support DirectCompute, etc.) already so HSA is mostly focused on compute-focused apps through OpenCL 2.0.

[nossy23]

It would be wonderful if Nvidia also supported this, and we no longer have to use DirectX. With Microsoft trying to force people the upgrade to a newer OS by supporting newer versions of DirectX only on the latest Windows, something must be done. Of course, Nvidia will never do this, and before you know it we'll have OpenGl, Direct X, Mantle, and a Nvidia variation.