AMD Posts "The four core principles of AMD’s Mantle"
by Ryan Smith on October 18, 2013 9:30 AM EST
Picking up from where we left off with AMD’s Mantle-related Tweet on Tuesday, the company has published a longer blog post that goes a bit deeper into what the company is doing with Mantle.
Penned by Ritche Corpus, AMD’s Director of ISV Gaming and Alliances, the blog post is generally a rehash of points we’ve previously covered, and at other points is little more than empty marketing speak (principle #4). Consequently we initially weren't even going to post this, however with as coy as AMD has been in official statements about the underpinnings of Mantle there were a couple of paragraphs we thought warranted further attention.
In discussing helping developers:
It’s not that Mantle is the initial language with which developers are writing their games on each platform, as some have surmised; the point of Mantle is that it’s easy to reuse, in whole or in part, the development effort expended on the next-generation consoles when bringing the same game to life on the PC. This is because Mantle allows developers to use the same features and programming techniques they are already utilizing for next-gen game consoles. And while the initial iteration of Mantle is intended specifically for PCs, it has been designed from the beginning to be extensible to other platforms as well.
And later in their conclusion (emphasis ours):
In short, Mantle is a new and better way to bring the code developers are already writing for next-generation consoles to life on the PC. It achieves this by being similar to, and often compatible with, the code they are already writing for those platforms. The ultimate goal of Mantle is to give gamers the ultimate performance in compatible games, and doing that in such a way that developers are free to put forth whatever effort is required to ensure optimal performance for competing platforms.
Of course we’re not going to get complete details on the API until APU13 next month, but at the very least this does agree with our earlier speculation about Mantle being heavily derived from the low level API constructs already created for the Xbox One. The big question continuing to be over just how similar Mantle is to the Xbox One's low level API constructs.
It’s interesting to note though that between this blog post and Tuesday’s tweet, AMD looks to be making a concentrated effort to try to better manage the public’s perception of Mantle, both the good and the bad perceptions. Mantle is far from the first initially ambiguous technology initiative in the PC graphics industry, but it has certainly attracted a great deal of attention from AMD’s supporters and detractors alike, with the ambiguity serving as a distraction since it can be wielded to prove and disprove a number of points. Ultimately until we have the full technical details and have final software in our hands it’s going to be far too early to properly judge Mantle, or for that matter say for certain how any of this will play out. But it's something we'll be watching closely, as wherever this eventually goes it has clearly just begun.
Source: AMD
Facebook
Twitter
RSS
11 Comments
View All Comments
nathanddrews - Friday, October 18, 2013 - link
Until someone lets out some code for BF4 for comparison between Xbone, PS4, and PC, we just won't know for certain.AMD wants to market this as easy to use, compatible, and portable to get gamers to buy Radeon products and to get devs to optimize for it (to win benchmarks).
Microsoft wants to market this as a totally different technology that isn't at all related to get gamers to believe the Xbone offers a unique experience that can't be had anywhere else.
Sony... *cricket*
Krysto - Tuesday, October 22, 2013 - link
Xbone - just puked a little in my mouth.Hrel - Friday, October 18, 2013 - link
I'm sad that you don't call the xbox "Xbone" in the article.BMNify - Friday, October 18, 2013 - link
That is because immature namecalling is not acceptable by normal people with functioning brain, leave the xbone, PSFags, Xbots etc to fanboys and their fanboy websites.Adamantine - Friday, October 18, 2013 - link
First time I saw Xbone on an article brief, I thought it was funny once I saw someone pointed out in the comment section that the writer probably meant to type XBone. Should probably use XB1 instead of XBone. It almost caused me to think of the site as becoming unprofessional, but it was probably just a simple typo error.teiglin - Friday, October 18, 2013 - link
There's a legitimate abbreviation problem here, to be fair--XbOne would be the canonically correct capitalization for that particular abbreviation, but that looks awful, so I can imagine a particularly naive abbreviator writing Xbone in the days before that was a common way to mock, though obviously this far in it has to either be mockery or idiocy. Honestly, I think Ryan made the right call in just spelling out Xbox One. It's only eight characters and this is Anandtech, not Twitter.Imaginer - Sunday, October 20, 2013 - link
So how about Crossbone?Pwnstar - Sunday, October 20, 2013 - link
Wait, Anandtech lets you say "fag" in the comments? Huh. Nothing wrong with that, I was just surprised.Klimax - Saturday, October 19, 2013 - link
4 principles are:Vendor lock-in
Hardware lock-in
Technological lock-down
Small performance benefit (sub 10%)
Alexvrb - Sunday, October 20, 2013 - link
Klimax, the performance benefits are said to be quite substantial. Also, no game vendor is going to use Mantle only in a PC title, so there's no real lock-in. If you'll recall days of yore, many games had a drop-down box allowing you to select from various render paths (allowing you to choose whatever worked best on your system). There's no reason they can't provide at least two render paths - Direct3D or OpenGL for compatibility with a broad range of graphics hardware, and Mantle as an option for GCN-based hardware.Where I really see Mantle providing a huge benefit is in APUs - especially mobile low power variants. Mantle improves rendering performance, but it also can significantly reduce CPU overhead. In a GCN-based APU system, this would free up a lot of CPU cycles which will reduce bottlenecking in CPU-bound games. They're actually boosting their CPU performance indirectly with Mantle. I think this is going to provide a huge boost to Kaveri performance, if enough of the big licensed engines provide support (such as Frostbite).