The Xbox 360 GPU: ATI's Xenos

On a purely hardware level, ATI's Xbox 360 GPU (codenamed Xenos) is quite interesting. The part itself is made up of two physically distinct silicon ICs. One IC is the GPU itself, which houses all the shader hardware and most of the processing power. The second IC (which ATI refers to as the "daughter die") is a 10MB block of embedded DRAM (eDRAM) combined with the hardware necessary for z and stencil operations, color and alpha processing, and anti aliasing. This daughter die is connected to the GPU proper via a 32GB/sec interconnect. Data sent over this bus will be compressed, so usable bandwidth will be higher than 32GB/sec. In side the daughter die, between the processing hardware and the eDRAM itself, bandwidth is 256GB/sec.

At this point in time, much of the bandwidth generated by graphics hardware is required to handle color and z data moving to the framebuffer. ATI hopes to eliminate this as a bottleneck by moving this processing and the back framebuffer off the main memory bus. The bus to main memory is 512MB of 128-bit 700MHz GDDR3 (which results in just over 22GB/sec of bandwidth). This is less bandwidth than current desktop graphics cards have available, but by offloading work and bandwidth for color and z to the daughter die, ATI saves themselves a good deal of bandwidth. The 22GB/sec is left for textures and the rest of the system (the Xbox implements a single pool of unified memory).

The GPU essentially acts as the Northbridge for the system, and sits in the middle of everything. From the graphics hardware, there is 10.8GB/sec of bandwidth up and down to the CPU itself. The rest of the system is hooked in with 500MB/sec of bandwidth up and down. The high bandwidth to the CPU is quite useful as the GPU is able to directly read from the L2 cache. In the console world, the CPU and GPU are quite tightly linked and the Xbox 360 stands to continue that tradition.

Weighing in at 332M transistors, the Xbox 360 GPU is quite a powerful part, but its architecture differs from that of current desktop graphics hardware. For years, vertex and pixel shader hardware have been implemented separately, but ATI has sought to combine their functionality in a unified shader architecture.

What's A Unified Shader Architecture?

The GPU in the Xbox 360 uses a different architecture than we are used to seeing. To be sure, vertex and pixel shader programs will run on the part, but not on separate segments of the hardware. Vertex and pixel processing differ in purpose, but there is quite a bit of overlap in the type of hardware needed to do both. The unified shader architecture that ATI chose to use in their Xbox 360 GPU allows them to pack more functionality onto fewer transistors as less hardware needs to be duplicated for use in different parts of the chip and will run both vertex and shader programs on the same hardware.

There are 3 parallel groups of 16 shader units each. Each of the three groups can either operate on vertex or pixel data. Each shader unit is able to perform one 4 wide vector operation and 1 scalar operation per clock cycle. Current ATI hardware is able to perform two 3 wide vector and two scalar operations per cycle in the pixel pipe alone. The vertex pipeline of R420 is 6 wide and can do one vector 4 and one scalar op per cycle. If we look at straight up processing power, this gives R420 the ability to crunch 158 components (30 of which are 32bit and 128 are limited to 24bit precision). The Xbox GPU is able to crunch 240 32bit components in its shader units per clock cycle. Where this is a 51% increase in the number of ops that can be done per cycle (as well as a general increase in precision), we can't expect these 48 piplines to act like 3 sets of R420 pipelines. All things being equal, this increase (when only looking at ops/cycle) would be only as powerful as a 24 piped R420.

What will make or break the difference between something like a 24 piped R420 and the unified shaders of the Xbox GPU is how well applications will lend themselves to the adaptive nature of the hardware. Current configurations don't have nearly the same vertex processing power as they do pixel processing power. This is quite logical when we consider the fact that games have many more pixels displayed than vertices. For each geometry primitive, there are likely a good number of pixels involved. Of course, not all titles will need the same ratio of geometry to pixel power. This means that all the ops per clock could either be dedicated to geometry processing in truly polygon intense scenes. On the flip side (and more likely), any given clock cycle could see all 240 ops being used for pixel processing. If game designers realize this and code their shaders accordingly, we could see much more focused processing power dedicated to a single type of problem than on current hardware.

ATI is predicting that developers will use lots of very small triangles in Xbox 360 games. As engines like Epic's Unreal Engine 3 have shown incredible results using pixel shaders and normal maps to augment low geometric detail, we can't tell if ATI is trying to provide the chicken or the egg. In other words, will we see many small triangles on Xbox 360 because console developers are moving in that direction or because that is what will run well on ATI's hardware?

Regardless of the paths that lead to this road, it is obvious that the Xbox 360 will be a geometry power house. Not only are all 3 blocks of 16 shaders able to become vertex shaders, but ATI's GPU will be able to handle twice as many z operations if a z only pass is performed. The same is true of current ATI and NVIDIA hardware, but the fact that a geometry only pass can now make use of shader hardware to perform 48 vector and 48 scalar operations in any given clock cycle while doing twice the z operations is quite intriguing. This could allow some very geometrically complicated scenes.

How Many Threads? Inside the Xenos GPU


View All Comments

  • calimero - Wednesday, July 6, 2005 - link

    btw Anand article was "full of shit" (sorry but that is the right phrase) and it's not odd that Anand pull it. It's quite embarassing for Anand; someone already told: one thing is to write test of CPU speed and speed of graphics card in games... and another to analyse CPU architecture.
  • jwix - Tuesday, July 5, 2005 - link

    Creathir - the article was reposted on other forums around the net. Here is the story in summary - Sony & Microsoft have both overhyped the processing power of their cpu's by using clever marketing speak. It turns out the processor designs are uneccessarily complicated, inefficient at crunching today's game code, and unlikely to be useful when game code finally becomes fully multi-threaded in the coming years. Why microsoft and sony didn't go with an Intel or AMD design, I don't know. The article speculates that both companies wanted IP rights to the cpu, maybe that's the reason.
    The GPU's on the other hand look plenty powerful. They should both be relatively equivalent in performance to the R520 and the current 7800 GTX.
    Bottom line - the new consoles will be quite powerful compared to the previous generation. However, PC's will still be more powerful, and wil remain the platform of choice for high end gaming. Something I was glad to read as I just built a new pc.

  • steveyoung123456789 - Friday, December 9, 2011 - link

    wow your so smart! faggit Reply
  • creathir - Saturday, July 2, 2005 - link

    I had read a good portion of the article, but had been pulled away (thought to myself I'll just reread it later) and was upset to find it was gone. I have never seen this here at Anandtech, and Anand has not made a single comment on his blog about it. I suppose some fact was incorrect? Maybe Sony/Microsoft decided they would SUE him over the article? I bet the most logical answer is this, Tim Sweeney saw the article, and even though Anand referenced the "anonymous developer", he had earlier mentioned in his blog he had been waiting for some answers from Tim. I would bet this "outed" his source, much like the LA Times outed their source recently for a Grand Jury. This outing probably was followed by a request by Tim to pull the article. I would have to bet we will see it soon enough, reworked, reworded. Whatever the case, Anand, it was a good article, you should be sure to repost it.
    - Creathir
  • steveyoung123456789 - Friday, December 9, 2011 - link

    o someone can read!! yay! Reply
  • linkgoron - Thursday, June 30, 2005 - link

    blckgrffn, THIS IS NOT i repeat NOT the article you think it is. Reply
  • blckgrffn - Thursday, June 30, 2005 - link

    Yes it is back up! :D

  • jwix - Thursday, June 30, 2005 - link

    Last night, around 10:00pm EST, I surfed over to the Anandtech home page to see what was happening. I was greeted by Part II of the article (Xbox 360, Sony PS3 - a hardware discussion). Did anyone else read this article last night. I was only able to read the first 2 pages before the article was pulled off the website. Why would they post it and then pull it so quickly? And why has not been reposted since?
    The story it told was unbelievable - basically, the floating point processing power of both the Sony and Xbox processor was less than half of your average Pentium 4. Anand went into detail on how and why this was the case. His sources apparently were confidential, but definitely industry insiders ( developers). I wish I could have finished reading the article before it was pulled. Did anyone read the whole article?
  • ecoumans - Thursday, June 30, 2005 - link

    Physics Middleware will be Multithreaded and heavily optimized for Cell's 7 SPE's. This makes life easier for gamedevelopers, and it changes the story about CPU usage... Same story for sound etc. Reply
  • Houdani - Tuesday, June 28, 2005 - link

    29: In order to turn off the "sponsored links" go to ABOUT in the top left menu and turn off INTELITEXT.

    I think this setting is stored in a cookie, so you will need to do this everytime you clear your cookies.

Log in

Don't have an account? Sign up now