• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

AMD Mantle: A Graphics API Tested In Depth (TH)

Soldato
Joined
7 Dec 2012
Posts
17,653
Location
Gloucestershire
Tom's Hardware's in depth look at Mantle using a variety of CPUs and GPUs in Thief and BF4;
http://www.tomshardware.com/reviews/amd-mantle-performance-benchmark,3860.html

As you would expect, Thief sees a good boost for mantle, particularly at the higher GPU end where the CPU is the bottleneck. The 290x/FX-8 figures are particularly eye catching.

BF4 seems a complete fail, though. cards with <4GB vram suffering a performance hit, those with 4GB vram gain little.
 
Last edited:
This'll be an interesting thread seeing at how much hate Tom's gets.

EDIT : There's some very dodgy looking results, My 290 sees gains across the board with a 4.4GHZ 4770K in Thief. Yet there's seems barely any? Yeah right.
 
Last edited:
This'll be an interesting thread seeing at how much hate Tom's gets.

EDIT : There's some very dodgy looking results, My 290 sees gains across the board with a 4.4GHZ 4770K in Thief. Yet there's seems barely any? Yeah right.

They did look closer at that one, which does look odd;
Then, we swap the R9 290X into our Core i7-4770K-based system and observe dismal results with Mantle turned on.

The numbers are repeatable, and we don't have a concrete explanation to put forth. But we're reminded that AMD considers Mantle to be a technology in its beta stage.
It's worth noting that the i3 buries the i7 using mantle, which can't happen, really, so seems like some sort of bug.
 
Interesting article. Shame they didn't test the online portion of the game, or multi gpu setups which is where Mantle shows it's biggest improvements in average fps because of cpu bottleneck situations.

Reading the posts above, some of their results do conflict with my testing as well.

EDIT

They used 14.3 Beta too, quite an old driver now. No idea if that could explain things or not.
 
Last edited:
Interesting article. Shame they didn't test the online portion of the game, or multi gpu setups which is where Mantle shows it's biggest improvements in average fps because of cpu bottleneck situations.

Reading the posts above, some of their results do conflict with my testing as well.

EDIT

They used 14.3 Beta too, quite an old driver now. No idea if that could explain things or not.

Yeah I agree. No multi-GPU results just makes the article a little 'meh'. For those of us who have been reading about Mantle for a while we know that the gains over DX at the top end are completely insignificant. But multi-GPU is a different story really would have been nice to see those with frame time comparisons between AMD DX and nVidia DX too.
 
From there comments here and plus its TomsH, im not going to bother clicking on the link.
Tested In Depth, obviously not.
 
Reads as Mantle being great for those with low end CPU + with high end AMD GPU combo, but for those with i7's not much advantage.

Mantle does seem like a very clever way to bridge the underperforming AMD CPU's with software API until AMD can release some competitive hardware later on.

Either way, it's impressive and spurred MS to get a move one with DX12, and probably shaped what DX12 would be. Not sure how relevant Mantle will be when DX12 arrives, but if it bridges that gap between CPU hardware for AMD it will have probably done it's job by the time DX12 arrives anyway.

Lot of similarity between 3DFX's Glide API, before going under, 3DFX had the Glide API, but refinement of Microsoft's Direct3D and full OpenGL implementation from other graphics card vendors, eventually caused it to become superfluous. This could happen with Mantle but will have at least bridged that gap in lack of competitive CPU hardware for AMD.
 
Only had a glance on the phone, but I like the opening Prince of Bel Air intro approach at schooling individuals on what DirectX is and has done :D


"Don't forget, kids"


I rate Toms along side Anandtech TBH. Not very
 
Last edited:
Looks as though the AMD 8 core chips are actually pretty good in Mantle.

Shame they suffer in everything else tbh otherwise I'd switch back in a heart beat.
 
Another Mantle review that is an epic fail.

Where is the info about using it at 4K, or rather that it is a total and utter mess at the resolution. It would be nice of reviewers to warn people about the problems as well as the pluses. The reviewers failure to do this is highly irresponsible at best.

Having said that Mantle at normal resolutions does work very well and gives real benefits.
 
Looks as though the AMD 8 core chips are actually pretty good in Mantle.

Mantle makes stuff like the FX8320 even better price/performance.
But the figures in this review are BS (Ignoring the AMD results, they're irrelevant to the point) but the Intel/R9 290X Mantle results are pure crap.
 
Its good that Toms did such an extensive Mantle test, as far as i know they are the only reviewer who did this, its a shame that by the looks of their confusion in the following text even they don't understand it.



Finally, with the High preset enabled, and a Radeon R9 290X/GeForce GTX 780 Ti installed, the results start getting strange. Nvidia's high-end gaming card averages about 80 FPS on a Core i7-4770K, and is matched by the Radeon R9 290X using Mantle and an FX-8350. Then, we swap the R9 290X into our Core i7-4770K-based system and observe dismal results with Mantle turned on.

The numbers are repeatable, and we don't have a concrete explanation to put forth. But we're reminded that AMD considers Mantle to be a technology in its beta stage. Overall, though, Mantle continues to help performance trend higher than DirectX.
Nothing strange about that, The 780Ti is able to match or beat the 290X's Avrage FPS because its able to produce higher high FPS as long as it has a Powerful CPU, like the 4770K.
If not it falls way behind the 290X on the same lower powered CPU, the FX-8350.
What i find strange is that they did not test the 290X on the same 4770K, why not?

Also, the FX-8350 is able to hold much higher Min FPS on the 290X in Mantle than the 780TI is on the 4770K.

If both the 780TI and 290X are running on the FX-8350 the 290X destroys the 780TI.
The 290X is faster on an FX-4170 than the 780TI is on the FX-8350.
Quite an eye opener.

But why not test the 290X on a 4770K in Mantle?

Edit, they did, its right down the slide, that is an odd one????
 
Last edited:
Mantle makes stuff like the FX8320 even better price/performance.
But the figures in this review are BS (Ignoring the AMD results, they're irrelevant to the point) but the Intel/R9 290X Mantle results are pure crap.

A lot more reviewers these days don't seem to understand or even play the games they are testing - they should be testing more intensive parts of games. Its like TR with the G3258 preview,where they tested a weird part of Crysis3(G3258 clock for clock was similar to a Core i7 which is interesting since pcgameshardware showed that even HT would make a Core i7 faster than a Core i5),or Techspot with some of their reviews too. They concentrate way too much on the hardware instead of the software part. As they say,Garbage In,Garbage Out.
 
Last edited:
Nothing strange about that, The 780Ti is able to match or beat the 290X's Avrage FPS because its able to produce higher high FPS as long as it has a Powerful CPU, like the 4770K.
If not it falls way behind the 290X on the same lower powered CPU, the FX-8350.
What i find strange is that they did not test the 290X on the same 4770K, why not?

You're reading it wrong; the 4770k/290x/mantle is on there; it's just performed shockingly and that's what they're talking about

I am somewhat surprised at how much better the 780Ti is than the 290x under DX, though.
 
Yeah, spotted that now ^^^^ i was expecting to see it at the top :)

A lot more reviewers these days don't seem to understand or even play the games they are testing - they should be testing more intensive parts of games. Its like TR with the G3258 preview,where they tested a weird part of Crysis3(G3258 clock for clock was similar to a Core i7 which is interesting since pcgameshardware showed that even HT would make a Core i7 faster than a Core i5),or Techspot with some of their reviews too. They concentrate way too much on the hardware instead of the software part. As they say,Garbage In,Garbage Out.

The Mantle with AMD CPU results they came up with look right.

But its really strange that the performance drops significantly when they use Intel and Mantle, thats not representative of reality, User testing shows using Intel CPUs you get at least the same performance as you do using AMD CPUs in Mantle.

How did they come up with these results? utter incompetence?
 
Last edited:
Yeah, spotted that now ^^^^ i was expecting to see it at the top :)



The Mantle with AMD CPU results they came up with look right.

But its really strange that the performance drops significantly when they use Intel and Mantle, thats not representative of reality, User testing shows using Intel CPUs you get at least the same performance as you do using AMD CPUs in Mantle.

How did they come up with these results? utter incompetence?

Probably something to do with Gameworks...

...:D
 
Back
Top Bottom