The Texture Units
As we said earlier, Larrabee doesn’t look much like a GPU, but while Intel was able to eliminate the setup engine and ROP by implementing those functions directly at the level of the Larrabee cores, the same isn’t true of the texture units. These units handle a very specific job that can be done much more efficiently in a dedicated unit. Texture decompression (DXTC), for example, is very simple to do in hardware, which is what guaranteed its success, but it requires enormous resources to do it on the software side. Intel calculated that performing texture operations on the processors would be between 12 and 40 times slower than on dedicated units, depending on the configuration (such as filtering quality and compressed or uncompressed texture format).
The texture units are fairly classic, and Intel doesn’t really provide a lot of detail about them, except that they will support all standard Direct3D 10 operations and compression modes. In fact, that’s the only point that might limit Larrabee’s ability to evolve. As we’ll see later, software entirely handles Larrabee’s rendering pipeline and so could address the future functionalities of Microsoft's application programming interface (API) via a simple update of the 3D engine executed by Larrabee’s cores. On the other hand, the texture units will be stuck at a certain level of functionality, which will determine that of the chip as a whole.
One interesting specificity of these texture units is that they handle translation of virtual addresses into physical addresses, which, in more concrete terms, means that there’s no longer a need to load an entire texture with its mipmap stack into local memory, as only the portions needed for display will be stored in the form of pages of a few kilobytes in size. If a page isn’t available in memory (a page fault), the texture unit notifies the processor, which then calls for it. This mechanism would make it very simple for programmers who aren’t afraid to get their hands dirty to implement, for example, an algorithm like id Software’s MegaTexturing.
- 1 / 5
- Next
-
Latest Graphics Cards News
- 05/20 – Qualcomm Hires Former AMD CTO Demers
- 05/18 – Nvidia Responds to GeForce 600 Series V-Sync Stuttering Issue
- 05/17 – Behold: Here Are The First Unreal Engine 4 Screens
- 05/17 – Nvidia Debuts GK110-based 7.1 Billion Transistor Super GPU
- 05/17 – GE Announces Kepler Graphics Card for Military and Aviation
Latest Graphics Cards reviews
- 05/10 – GeForce GTX 670 2 GB Review: Is It Already Time To Forget GTX...
- 05/09 – Best Graphics Cards For The Money: May 2012
- 05/09 – Video Teaser: Radeon HD 7800 Series Remains A Solid Value
- 05/08 – Benchmarking AMD's 768-Shader Pitcairn: Not For Public...
- 05/03 – GeForce GTX 690 Review: Testing Nvidia's Sexiest...
-
Latest Intel News
- Intel Picks UK for Research Institute on Sustainable Cities
- Specs for Dell's Windows 8 Clover Trail Tablet Leaked
- Thunderbolt Will Become Key Motherboard Spec in 2H 2012
- AMD Backing Out of CPU Speed Wars Against Intel
- Intel Hopes New Batteries Can Reduce Ultrabook Cost
-
Latest Intel reviews
- Overclocking Core i7-3770K: Learning To Live With Compromise
- Core i5-3570K, -3550, -3550S, And -3570T: Ivy Bridge Efficiency
- Best Gaming CPUs For The Money: May 2012
- Intel SSD 330 Review: 60, 120, And 180 GB Models Benchmarked
- Core i7-3720QM: Ivy Bridge Makes Its Mark On Mobility
very interesting, i know nvidia cant settle for being the second best. As always its good for the consumer.
Yes interesting, but intel already makes like 50% of every gpu i rather not see them take more market share and push nvidia and amd out although i doubt it unless they can make a real performer, which i have no doubt on paper they can but with drivers etc i doubt it.
I wonder if their aim is to compete to appeal to the gamer market to run high end games?
Very interesting, finally some more information about Intel upcoming "GPU".
But as I sad before here if the drivers aren't good, even the best hardware design is for nothing. I hope Intel invests more on to the software side of things and will be nice to have a third player.
cool ill wait for windows 7 for my next build and hope to see some directx 11 and openGL3 support by then.
Maybe there is more than a little commonality with the Atom CPUs: in-order execution, hyper threading, low power/small foot print.
Does the duo-core NV330 have the same sort of ring architecture?
"Simultaneous Multithreading (SMT). This technology has just made a comeback in Intel architectures with the Core i7, and is built into the Larrabee processors."
just thought i'd point out that with the current amd vs intel fight..if intel takes away the x86 licence amd will take its multithreading and ht tech back leaving intel without a cpu and a useless gpu
Driver. If Intel made driver as bad as Intel Extreme than event if Intel can make faster and cheaper GPU it will be useless.
Hope for an Omega Drivers equivalent lol?
Damn, hoped there would be some pictures
. Looks interesting, I didn't read the full article but I hope it is cheaper so some of my friends with reg desktps can join in some Orginal Hardcore PC Gaming XD.
I was quite suprised by the quality of this article and am quite eager to see the follow up.
Well I am looking forward to Larrabee but I'll keep my optimisim under wraps until I start seeing some screenshots of Larabee in action playing real games i.e. not Intel demo's.
I wonder just how compatible larrabee is going to be with older games?
Great article! Keep ones like this coming!
Hope for an Omega Drivers equivalent lol?
That would be FANTASTIC! Maybe the same people who make the Omega drivers could make alternate Larrabee drivers? We all know Intel sucks balls at drivers.
So this is Intel's approach to a GPU... we put lots of simple x86 cores in it , add SMT and vector operations and hope that they would do the job of a GPU. IMHO Larrabee will be a complete failure as GPU but as an x86 CPU that is highly parallel this thing could screw AMD's FireStream and NVIDIA's CUDA (OPENCL too) beacause it's x86 and the programming is pretty popular for this kind of architecture.
Yes interesting, but intel already makes like 50% of every gpu i rather not see them take more market share and push nvidia and amd out although i doubt it unless they can make a real performer, which i have no doubt on paper they can but with drivers etc i doubt it.
Yeah but that 50% includes all the integrated cards that no consumer even realizes they're buying most of the time.. but not in discrete cards. I'd like to see a bit more competition on the discrete side.
"Simultaneous Multithreading (SMT). This technology has just made a comeback in Intel architectures with the Core i7, and is built into the Larrabee processors." just thought i'd point out that with the current amd vs intel fight..if intel takes away the x86 licence amd will take its multithreading and ht tech back leaving intel without a cpu and a useless gpu
Umm, what makes you think that AMD pioneered multi-threading? And Intel doesnt use HyperTransport, so they cant take it away.
Now we know what they're trying to do with it. There's still no indication if it will work or not.
I really don't see the 1st gen. being successful-it's not like AMD and nVidia are goofing around waiting for Intel to join up and show them a real GPU. Although there's no numbers on this that I've seen, I'm thinking Larry's going to have a pretty big die size to fit all those mini-cores so it better perform, because it will cost a decent sum.
I would mention ... "but will it play crysis" but I am not sure how funny that is anymore.
Can't wait for Larrabee; hopefully a single Larrabee can have the performance of 295. Nvidia and ATI are slacking as they know they can price fixing and stop coming out with better GPU, just more cards with the same old GPU.