Next-Gen Console CPUs Not Up to Hype 783
rAiNsT0rm writes "Anandtech follows up their initial in-depth coverage of the Xbox 360 and PS3 CPU with the real truth about the next-gen consoles' Poor CPU Performance. From the article: "Speaking under conditions of anonymity with real world game developers who have had first hand experience writing code for both the Xbox 360 and PlayStation 3 hardware (and dev kits where applicable), we asked them for nothing more than their brutal honesty. What did they think of these new consoles? Are they really outfitted with the PC-eclipsing performance we've been lead to believe they have? The answer is actually quite frequently found in history; as with anything, you get what you pay for."" Update: 06/30 21:11 GMT by Z : The original article disappeared from Anandtech, so I've changed the link to point to the story as hosted by Google Groups.
Re:Xbox 360 twice as fast as Xbox? (Score:3, Informative)
He's likely referring to single-threaded performance, likely from PC developers who ported PC applications to the consoles in a month or two.
In-order cores like Xenon and Cell require a lot more careful optimizations, they don't have the Out Of Order Execution logic on the CPU to dynamically re-order the instructions more optimally.
Re:Random Thoughts: (Score:5, Informative)
3 Core vs. 1 Core (Score:1, Informative)
No more free lunches; should we get used to it? (Score:5, Informative)
Not really surprising; at any rate, it may be essential to get used to this type of architecture/programming, as The Free Lunch Is Over [www.gotw.ca], if this article is to be believed. (This may have featured in
Re:More hype (Score:5, Informative)
Re:This just in... (Score:5, Informative)
http://www-306.ibm.com/chips/techlib/techlib.nsf/
http://research.scea.com/research/html/CellGDC05/
http://research.scea.com/research/html/CellGDC05/
If you don't split up the local store, you're going to incurr a 500 cycle penalty while waiting for memory. If you split up the local store, you can fetch to half the mem and process on the other half. This amortizes, if not completely masks the cost of main memory access.
Correct me if I'm wrong.
It's up to the developer to optimize their code and ensure that it is being scheduled properly.
I'd love to hear from a developer that is actually doing everything they can at the low level to optimize data flow. What's their experience with keeping the processors fed with data?
Re:Slashdot called this a year ago (Score:3, Informative)
The "Cell is overhyped" thing is complete nonsense. These consoles will be more powerful than PCs on introduction (if only for the equivalent of a GeForce 7800GTX running at 550MHz!), and thanks to developers figuring out how to use the Cell's power over time, will still run games as well as contemporary PCs a few years down the line.
Re:development hardware (Score:3, Informative)
You do realize that launch titles will be made with these current devkits?
Games made with devkits for the completed systems won't come out until the first console price drop or so.
Re:Slashdot called this a year ago (Score:1, Informative)
Re:So... (Score:5, Informative)
I'd also point out the "Toy Story in Real Time" thing was never a Sony claim either. As far as I've been able to track it down, it was some idiot journalist that made the claim, not a Sony spokesperson or any Sony marketing literature.
Re:Random Thoughts: (Score:5, Informative)
They're inexpensive and downloadable off the net, too
These days, most of the really good, non-violent stuff in PC/Mac gaming comes from web sites marketing their goods online. The small developers haven't "sold out" to Hollywood yet.
Actual Articles for Your Reading Pleasure. (Score:2, Informative)
http://www.anandtech.com/video/showdoc.aspx?i=2461 [anandtech.com]
http://www.gamespot.com/news/2005/06/28/news_61283 06.html [gamespot.com]
Re:Xbox 360 twice as fast as Xbox? (Score:2, Informative)
Well put and absolutely correct... (Score:2, Informative)
Re:Xbox 360 twice as fast as Xbox? (Score:5, Informative)
False! I don't know how old you were last console cycle, but Nintendo was very realistic about the Gamecube's abilities before it was released. They said, "it can render 9 million polygons per second under realistic conditions." Cue Sony: "Well ours can render ONE HUNDRED BILLION polygons per second!" and then microsoft: "We can do INFINITY BILLION TO THE INFINITY POWER!!!". So it isn't at all clear to me why the fact that Sony and MS overhype indicates that Nintendo overhypes.
Re:So... (Score:5, Informative)
http://news.com.com/2100-1040-250632.html?legacy=
Re:So... (Score:3, Informative)
So basically, Mode 7 graphics = shit [beebgames.com] :)
Apple doesn't make consoles... (Score:2, Informative)
It isn't appropriate for Apple because it doesn't have regular Altivec. So that means that code written for older PPCs wouldn't run well on it. It also wouldn't be appropriate because the Cell doesn't have out-of-order execution (retirement) of instructions. That means that instructions must be scheduled in the proper order, taking memory latencies into account. This isn't possible on a Mac, because Macs change all the time. Today's CPU has a 5 clock latency to memory, tomorrows has a 7 clock latency (because CPUs speed up more rapidly than memory does). If that happened, Cell would start to run slowly because the code isn't arranged correctly for the new latencies.
But on a console, all those relationships are fixed when the console is first built. The CPU doesn't get faster over time, they're all the same until the console is retired.
So, don't jump to conclusions here. Cell may not be for Apple, but it looks like a great choice for a console.
Re:Great graphics, boring games (Score:3, Informative)
The D.O.A in DOA2 DOA3 DOA Ultimate, stands for "Dead or Alive"
My friends and I played WAY too much DOA2 a few summers back. We can still hear the theme music when we go to sleep.
Speaking of breasts in said games, if you increased the 'Age' statistic on the female characters (up to the arbitrary value of '99') their breasts grew in size. Nice one Team Ninja!
Re:Random Thoughts: 2 Words, Racing Games (Score:3, Informative)
You have a full size plastic assault rifle in Ghost squad. There's a switch that flips it between fully automatic and burstfire. There's also an action button on the gun to rescue hostages. There are also strategic decisions to make as you go through the levels (such as stay on the first to rescue hostages, go after the terrorists on floor 2, or enter a certain room with a flashbang). Sometimes your gun will turn into a sniper rifle and there will be sniper rounds. Lastly, the game lets you calibrate the gun when you start every game. This is great thinking ahead on the part of the game designers. I can't tell you how many times I've tried to play shooting games when the sights on the guns were very far off because the arcade operator didn't regularly calibrate them.
I never liked time crisis. Not sure why. It just never clicked with me.
This weekend I'm going to hit the Gameworks in Columbus, Ohio. Hopefully some quality arcade gaming will be had =]
Re:Xbox 360 twice as fast as Xbox? (Score:5, Informative)
"It is accurate that at this time we will not support high-definition [on Revolution]," Kaplan told IGN.com.
It's really hard to tell what will happen by the time it's released. The Gamecube is theoretically capable of 720p output, though the games only utilize 480p. Considering the video hardware that is being used, it's safe to assume that the Revolution is at least as capable as the Gamecube It's not going to matter all that much, because we're still going to be stuck with 480p DVD movies for a while. 480p is a form of SDTV. Even if it's not "HD", it's still much higher quality than any analog television. Your comment about the RCA analog television is grossly exaggerated.And let's be honest... All three systems will have hardware that's paractically the same, regardless of these cracked out specs and numbers (ironic isn't it that all three are using what is essentiall a next-gen Gamecube with PowerPC and ATI graphics). What it will really boil down to is the games.
Re:Xbox 360 twice as fast as Xbox? (Score:2, Informative)
Just a note on the DVD - xbox is limited to 2GB (around 1/2 of a single layer DVD). Xbox 360 will have access to 2 full layers - so it will have 4x the capacity.
Re:This just in... (Score:5, Informative)
On the PS3, we get 256 KB of memory with a vector processor running 3.2Ghz, and people are complaining? And we get a bunch of em. Whoever they talked to were not PS2 developers. The same people who made sweet PS2 games will be making sweet PS3 games, trust me. For everyone else it will be harder to get used to.
For one thing, you can kiss your virtual calls goodbye.
Here's your source (Score:4, Informative)
http://cube.ign.com/articles/522/522559p2.html [ign.com]
Q: Is Revolution "two-to-three times more powerful than GameCube"?
A: USA Today reported this news based on a comment from Nintendo of America's vice president of corporate affairs, Perrin Kaplan. The information was later determined to be false. We do not yet know how much more power Revolution wields over its predecessor.
Re:okay, i'll have a slug at it ... (Score:3, Informative)
Re:Xbox 360 twice as fast as Xbox? (Score:3, Informative)
Nintendo UNDERestimated the GameCube's performance (Score:3, Informative)
Contrast with Sony and MS whose claimed performance numbers for the last 6 years have been pure fantasy and/or hype.
ARTICLE TEXT (Score:4, Informative)
In our last article we had a fairly open-ended discussion about many of the challenges facing both of the recently announced next-generation game consoles. We discussed misconceptions about the Cell processor and its ability to accelerate physics calculations, as well as touched on the GPUs of both platforms. In the end, both the Xbox 360 and the PlayStation 3 are much closer competitors than you would think based on first impressions.
The Xbox 360's Xenon CPU features more general purpose cores than the PlayStation 3 (3 vs. 1), however game developers will most likely only be using one of those cores for the majority of their calculations, leveling the playing field considerably.
The Cell processor derives much of its power from its array of 7 SPEs (Synergistic Processing Elements), however as we discovered in our last article, their purpose is far more specialized than we had thought. Speaking with Epic Games' head developer, Tim Sweeney, he provided a much more balanced view of what sorts of tasks could take advantage of the Cell's SPE array.
The GPUs of the next-generation platforms also proved to be quite interesting. In Part I we speculated as to the true nature of NVIDIA's RSX in the PS3, concluding that it's quite likely little more than a higher clocked G70 GPU. We will expand on that discussion a bit more in this article. We also looked at Xenos, the Xbox 360's GPU and characterized it as equivalent to a very flexible 24-pipe R420. Despite the inclusion of the 10MB of embedded DRAM, Xenos and RSX ended up being quite similar in our expectations for performance; and that pretty much summarized all of our findings - the two consoles, although implementing very different architectures, ended up being so very similar.
So we've concluded that the two platforms will probably end up performing very similarly, but there was one very important element excluded from the first article: a comparison to present-day PC architectures. The reason a comparison to PC architectures is important is because it provides an evaluation point to gauge the expected performance of these next-generation consoles. We've heard countless times that these new consoles would offer better gaming performance than anything we've had on the PC, or anything we would have for a matter of years. Now it's time to actually put those claims to the test, and that's exactly what we did.
Speaking under conditions of anonymity with real world game developers who have had first hand experience writing code for both the Xbox 360 and PlayStation 3 hardware (and dev kits where applicable), we asked them for nothing more than their brutal honesty. What did they think of these new consoles? Are they really outfitted with the PC-eclipsing performance we've been lead to believe they have? The answer is actually quite frequently found in history; as with anything, you get what you pay for.
Learning from Generation X
The original Xbox console marked a very important step in the evolution of gaming consoles - it was the first console that was little more than a Windows PC.
The original Xbox was basically a PC
It featured a 733MHz Pentium III processor with a 128KB L2 cache, paired up with a modified version of NVIDIA's nForce chipset (modified to support Intel's Pentium III bus instead of the Athlon XP it was designed for). The nForce chipset featured an integrated GPU, codenamed the NV2A, offering performance very similar to that of a GeForce3. The system had a 5X PC DVD drive and an 8GB IDE hard drive, and all of the controllers interfaced to the console using USB cables with a proprietary connector.
For the most part, game developers were quite pleased with the original Xbox. It offered them a much more powerful CPU, GPU and overall platform than anything had before. But as time went on, there were definitely limitations that developers ran into with the first Xbox.
One of the biggest limitations
Anand Pulled the Article - Here is my cache (2/2) (Score:3, Informative)
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 ho