LOL, G5's Running All the 360 Demos @ E3!

Posted: Sat May 28, 2005 11:31 pm

Quote:

But floating point is precisely what you need for physics and games. In a game console I perfer the Cell processor. And maybe a video editting machine. In anything else, Cell sucks bad.

Whoever explained this to you explained it badly. What percentage of CPU ticks in a game do you think is spent on physics? 50%? 80%? Wrong.. it's somewhere between 1% and 5% - fact. It's also foolish to say "I prefer the cell" in games - nobody has ever really seen one or seen the SDK for it.

You say "a huge edge in physics". Well, let me give an analogy. You need to knock a nail into a piece of wood. It's a 1 inch nail. You can use a normal hammer, or a 300pound jack hammer. Which one knock the nail in best?

The rest of your argument was interesting - but again, I must reiterate the simple facts here.. In this generation, coders will be developing for PPC cores - because all 3 consoles use a G5 derived PPC core. They will *not* repeat *not* be developing for Cells SPE's, or MS's specific 3x2 layout. They will be developing threaded, portable code for PPC architecture. Given this, the 360 has already won - because it has 3 cores, which use relatively standard thread models. As I said before, 90% of games made will target this generalised X-Core PPC platform. So in effect, the PS3 has one processor, and the 360 has 3. End of story.

As for the media argument, I accept your point re. N64 - but ask yourself this... with the time and money MS have spent on the 360, do you really think they would make such a simple error? Remember - they are in constant discussion with all the big studios, and they know how big games will be..

Kai Regular Joined: 13 Jan 2005 Posts: 87

Quote:

The XBox 360, which will be designed for HDTV's (6-7 times the pixels), will need much higher resolution textures and models. It will definitely need bigger disks. Maybe not the launch games, but later on in the life it will be a big deal. Otherwise we'll see the same thing as we saw on GameCube, how games with FMV sequences for example have much lower quality video, or multiple disks (RE4 for example).

Dual-Layer DVD's Very Happy

8.7GB of goodness, i heard a rumour somewhere that xbox360 will eventually upgrade to one of the new standards somehow (HD-DVD or Blu-Ray forgot which one). That might just be a rumour/marketing stunt though

Posted: Sun May 29, 2005 4:38 pm

XCondor @ Sat May 28, 2005 11:31 pm wrote:

Quote:

But floating point is precisely what you need for physics and games. In a game console I perfer the Cell processor. And maybe a video editting machine. In anything else, Cell sucks bad.

Whoever explained this to you explained it badly. What percentage of CPU ticks in a game do you think is spent on physics? 50%? 80%? Wrong.. it's somewhere between 1% and 5% - fact. It's also foolish to say "I prefer the cell" in games - nobody has ever really seen one or seen the SDK for it.

The primary purpose of the CPU is for physics and AI calcs, is it not? How can it be only 5%? I'm not trying to be arguementative- please, enlighten me, I could do well to learn more.

Quote:

You say "a huge edge in physics". Well, let me give an analogy. You need to knock a nail into a piece of wood. It's a 1 inch nail. You can use a normal hammer, or a 300pound jack hammer. Which one knock the nail in best?

I'm thinking of one being able to control far more particles, have more realistic water effects, stuff like that. Not really a fair analogy.

Quote:

The rest of your argument was interesting - but again, I must reiterate the simple facts here.. In this generation, coders will be developing for PPC cores - because all 3 consoles use a G5 derived PPC core. They will *not* repeat *not* be developing for Cells SPE's, or MS's specific 3x2 layout. They will be developing threaded, portable code for PPC architecture. Given this, the 360 has already won - because it has 3 cores, which use relatively standard thread models. As I said before, 90% of games made will target this generalised X-Core PPC platform. So in effect, the PS3 has one processor, and the 360 has 3. End of story.

You do have a point there. Ported games will probably have bad PS3 performance. Only exclusive games will use the physics.

Quote:

As for the media argument, I accept your point re. N64 - but ask yourself this... with the time and money MS have spent on the 360, do you really think they would make such a simple error? Remember - they are in constant discussion with all the big studios, and they know how big games will be..

Their reasoning at this point seems to be that they feel that Sony beat them because of an earlier launch date. At least from the statements I've heard. They feel the PS2 won because of an early launch date, rather than being superior (which is probably true), so they're going to try to beat Sony to launch.

They might get the PS2 effect...or they might get the Dreamcast effect (namely, where Sony's hype and a weaker media made people hold off). We'll see.

Posted: Sun May 29, 2005 4:40 pm

TA_Superman @ Sat May 28, 2005 11:41 pm wrote:

Quote:

The XBox 360, which will be designed for HDTV's (6-7 times the pixels), will need much higher resolution textures and models. It will definitely need bigger disks. Maybe not the launch games, but later on in the life it will be a big deal. Otherwise we'll see the same thing as we saw on GameCube, how games with FMV sequences for example have much lower quality video, or multiple disks (RE4 for example).

Dual-Layer DVD's Very Happy

8.7GB of goodness, i heard a rumour somewhere that xbox360 will eventually upgrade to one of the new standards somehow (HD-DVD or Blu-Ray forgot which one). That might just be a rumour/marketing stunt though

The current XBox already runs dual layer DVD's, does it not?

Kai Regular Joined: 13 Jan 2005 Posts: 87

Yeah but i dont think any games have actually used all 8.7GB have they? name one if you can remember Very Happy

Team XLink Moderator Joined: 21 May 2004 Posts: 1536

TA_Superman @ Sun May 29, 2005 8:20 pm wrote:

Yeah but i dont think any games have actually used all 8.7GB have they? name one if you can remember Very Happy

yeah none used the full space on DL, but these below are using the DL:

Rally Sport 2 <biggest Xbox game i know, approx 6.20gb)
Dead or Alive Ultima
Jade Empire
Brute Force
Terminator 3 : ROTM
Metal Gear Solid 2
Max Payne

the ONLY reason M$ didn't include HD-DVD or Blu-ray is to keep the console price down. But game will use over 9gb in the Next gen console. They will end up using multiple discs swap methods.

Even if the games don't use that much space, then X360 been a media player and i can't even watch WMV-HD (Movies with 720p) files cos on average they are 12gb. Mad

Posted: Mon May 30, 2005 6:19 pm

TA_Superman @ Sun May 29, 2005 8:20 pm wrote:

Yeah but i dont think any games have actually used all 8.7GB have they? name one if you can remember Very Happy

Like said above, there are several games that use most of it.

Name one N64 game that used 64 MB of memory. There aren't any. Should we still be stuck on N64 cartridges?

Name one PSone game that used 700 MB of disk space. So, should the PS2 have stayed with CD's?

See the reasoning? There are currently games that use most of 8.7 GB. Next generation will require higher resolution textures (HD resolution is 6-7 times the pixels). Next generation games require higher detail models. FMV will be in high definition. etc. We NEED more space.

Redwolf is correct. M$ is being cheap. They got pwned on the first XBox in their bank account. Even for MICROSOFT it hurt. It would have bankrupt anyone else. They're actively trying to cut down costs, by taking out stuff like HD-DVD or Blu-ray, and the sound card (the processor is fast enough to do the audio processing).

Joined: 30 Jul 2006 Posts: 0

Quote:

Even for MICROSOFT it hurt

No, it didn't. MS's loss was about 400 million US - if you think that "hurts" MS, think again...

It always makes be laugh when people state that because MS lost money on Xbox, that they have been "pwned". Calling the Xbox "research" would be closer to the mark - and MS have done it well in this observers eyes.

Like XC said - the media choice for the xbox will be whatever the studios say they need - simple as that.

XC is also right with his Cell vs. 3x2 config argument - MS has basically won there already. There may be one or two "GT4's" for PS3 which are outstanding, but 90% of PS3 games will fall short of the 360 ports of the same game - by a long way.

I remember discussing this whole thing with XC right back when MS first announced the first Xbox. We pretty much agreed that there would be 3 stages - stage 1 being MS entering the market, losing money, but taking 2nd spot. Stage 2, MS achieves parity with Sony, and begins to take 3rd party studios. Stage 3, MS basically takes over the whole thing..

So far, 1 and 2 have come true...

The MS business machine is too big - Sony are developing (imo) in the wrong direction, they are losing some important 3rd party support, they have a (again imo) technically inferior platform. It's a matter of time.

You form your arguments pretty well Praxis - that's refreshing, a lot of people on these sort of boards are fanboys. I kinda like you, because you just seem to hate.. well... everything Very Happy

It's often prudent though, to look past specs and hype at the *business models* which these sort of companies execute - that's where people get "pwned", and in the last 20 years Gates has taken just about everyone on, usually on their turf, and always won (yes, often through unfair / illegal leveraging of his existing monopolies). Do not be suprised when the same tactics come out of the closet and unseat Sony.

TD

Posted: Tue May 31, 2005 1:30 am

TheDaddy @ Mon May 30, 2005 11:44 pm wrote:

Quote:

Even for MICROSOFT it hurt

No, it didn't. MS's loss was about 400 million US - if you think that "hurts" MS, think again...

It always makes be laugh when people state that because MS lost money on Xbox, that they have been "pwned". Calling the Xbox "research" would be closer to the mark - and MS have done it well in this observers eyes.

http://forum.pcvsconsole.com/viewthread.php?tid=11760&page=5

I would agree that it is research. They took a loss and are learning.
Look at the profits I just posted. Thats from the eight quarters from 2003-2004.

They lost $400 million in one QUARTER. Not total. Just ran the math- in 2003 and 2004, there is a $1.993 billion loss. I'll round that to 2.

A billion lost per year. That is pretty dang bad for MS.

Quote:

Like XC said - the media choice for the xbox will be whatever the studios say they need - simple as that.

What defines "need"? Is it whats best for the consumer, or what saves more money for the company?

Quote:

XC is also right with his Cell vs. 3x2 config argument - MS has basically won there already. There may be one or two "GT4's" for PS3 which are outstanding, but 90% of PS3 games will fall short of the 360 ports of the same game - by a long way.

I concede to this, but I emphasize that this is talking about PORTS, rather than exclusives. Exclusive PS3 games should come out best.

However, this is only in terms of PROCESSORS. In terms of graphics cards, we can't really tell yet, not enough details have been released.

Quote:

I remember discussing this whole thing with XC right back when MS first announced the first Xbox. We pretty much agreed that there would be 3 stages - stage 1 being MS entering the market, losing money, but taking 2nd spot. Stage 2, MS achieves parity with Sony, and begins to take 3rd party studios. Stage 3, MS basically takes over the whole thing..

I also have always believed that was their business plan. However, whether they will succeed or not is questionable. The competition is pretty strong. Sony has an insane hype engine, you know. Some people believe that Cell outperforms supercomputers at this point Rolling Eyes

Thing is, thats precisely what happened with PS2 vs Dreamcast. Let's compare.

The Dreamcast was, in reality, almost on par with the PS2 in graphics, but it had 1 GB disks while the PS2 had 4.7 GB disks and the PS2 came out later, almost 5 times the space.

Sony had the whole world believing that the Emotion Engine was so insanely powerful ("Toy Story-like graphics") that it'd blow the Dreamcast away, and that the Dreamcast disks were too small, as a result people held off from buying the Dreamcast, and the Dreamcast (despite being, in some ways, a better system) failed.

It could very well happen again. Sony has a lot of idiots believing that the Cell is the Greatest Thing Ever(tm) and outperforms modern supercomputer clusters. Sony also has disks that fit 6 to 12 times more data. History could very well repeat itself, with Sony hyping the PS3 to the point that people hold off from the X360. I don't think the X360 could possibly do quite as bad as the Dreamcast, but the Dreamcast effect could hurt it.

Quote:

The MS business machine is too big - Sony are developing (imo) in the wrong direction, they are losing some important 3rd party support, they have a (again imo) technically inferior platform. It's a matter of time.

You form your arguments pretty well Praxis - that's refreshing, a lot of people on these sort of boards are fanboys. I kinda like you, because you just seem to hate.. well... everything Very Happy

It's often prudent though, to look past specs and hype at the *business models* which these sort of companies execute - that's where people get "pwned", and in the last 20 years Gates has taken just about everyone on, usually on their turf, and always won (yes, often through unfair / illegal leveraging of his existing monopolies). Do not be suprised when the same tactics come out of the closet and unseat Sony.

TD

LOL, heh, thanks, I think Very Happy

In reality I don't hate everything...I'm just very outspoken about the things I don't like, so I show up/stand out the most in these debates.

Team XLink Moderator Joined: 21 May 2004 Posts: 1536

Praxis @ Tue May 31, 2005 1:30 am wrote:

Thing is, thats precisely what happened with PS2 vs Dreamcast. Let's compare.

The Dreamcast was, in reality, almost on par with the PS2 in graphics, but it had 1 GB disks while the PS2 had 4.7 GB disks and the PS2 came out later, almost 5 times the space.

Sony had the whole world believing that the Emotion Engine was so insanely powerful ("Toy Story-like graphics") that it'd blow the Dreamcast away, and that the Dreamcast disks were too small, as a result people held off from buying the Dreamcast, and the Dreamcast (despite being, in some ways, a better system) failed.

this is the only thing worring me to purchase Xbox360.

similarity for Dreamcast = X360
lower disk space, White console, VGA, On-line, Windows based SDK, even the ring of light logo is similer to DC..lol

Dreamcast(Sega/M$) vs PS2(Sony) may well be the same thing could happen to X360 vs PS3 as both are identical to what they have, can do and the time gap between release. I know how the Sony business scams works. Even if they use the old strategy that PS3 is out of stock due to too many pre-orders, the general public will fall for it and do pre-orders. Sony "knows" that most of thier market don't know much about gaming, only if they hear good things will make the public buy their product. Some people will buy PS3 just cos it can play blu-ray. Even the PS1 killed of N64, though N64 was better, so we can't exactly say due to the console coming later it will sell more cos it's powerfull. Another thing, Sony or the PlayStation is the Sequals... they keep releasing too many without that much improvement (MGS, Tekken, GT serious), specially Tekken 5 and MGS3 was total rubbish, yet general public will spend on the product.

i too think XC is right about his Cell vs. 3x2 config argument Smile

...but
General public (maybe give them another name, Zombies!!! ) not gonna work out the maths between the two consoles. Or judge the console for quality games etc... All they are hearing from Sony that PS3 is better then anything, better then anyother company could make. (even better then gods creations. Rolling Eyes

)

There is a limit for a company to lose money. I don't think M$ is looking to lose anymore. But as TD said about "stage"... i would love to see M$ in Stage 3..but is that to happen i'm not sure...

Posted: Tue May 31, 2005 5:28 am

Honestly, I don't want to see ANY company in stage 3. Any company controlling the market = bad. Look at Microsoft and Windows. 95% market share means they can charge ANY PRICE THEY WANT and people will have to buy it. Or Standard Oil is another example.

No company should have a monopoly, otherwise no competition causes big problems.

I WOULD like to see a 1v1 again. Like the PS1 vs N64 or Genesis vs SNES days. Three is, IMO, too many, and you end up with one getting left out. So while it's not very nice, I'm kinda hoping either Microsoft or Sony completely flops this round. Perferably Microsoft, as their bank account and ability to waltz in and buy any game company they want gives them an unfair (and illegal, but the antitrust guys seem to look the other way) advantage.

Personally, unless Nintendo completely screws up, I'm going to immediately buy a Revolution and wait to see who gets the best launch and has the best stuff between MS and Sony and buy one of them as well. It's just looking to be Sony at this point. Online Super Smash Bros + downloadable old games will keep me busy for a month while I watch. Unless one comes out with something so good I HAVE to buy it immediately.

Cell and X360 processors are tough to compare, there's not enough info to compare the graphics cards, but the rest of the hardware gives Sony an advantage (Blu-ray, Bluetooth w/7 controllers vs 4 controllers, dual 1080p support vs single 1080i support, PSP connectivity, free that we know of online play, etc) so far, but could also result in higher cost which would definitely affect my decision.

I just think that the Dreamcast effect, combined with the rushed launch date, might put Microsoft at serious risk, as theorized here.
http://weblog.bbzzdd.com/archives/000834.html
Very good article. A peice of it:

Quote:

Next-generation games are going to be a lot more complicated to develop than today's games. Even Microsoft's Xbox evangelist, J Allard, agrees. Developers are going to be faced with the option of either A) Throwing all of their resources into producing Xbox2 games which will only be purchased by a handful of early adopters or B) Continuing to support the over 120 million current generation consoles until all three major players are on roughly the same page technologically (late 2006 the earliest).

I wager that outside of a few first-party Xbox developers the lot of development shops will go with option B. The cash incentive for developing a two or three system port versus a complicated development effort for a system with a tiny userbase is just a no-brainer for the EAs and Capcoms of the world.

By time the Playstation 3 and Nintendo Revolution have shipped worldwide in 2006, the Xbox2 is going to be considered old technology by most gamers, even though the actual graphical difference between the next-gen consoles is predicted by most insiders to be negligible.

One only has to look at the Sega's ill-fated Dreamcast which shipped a mere five months before the Playstation 2 to wonder if history will repeat itself. For the most part the Dreamcast was graphically on par with the Playstation 2. However, one major component missing from the Dreamcast was a DVD drive. The Dreamcast was equipped with a modified CD drive which read propreitary one gigabyte discs. Gamers, arguably persuaded by Sony’s hype, simply looked to the better hardware. Who want's to play CDs when you can play CDs and DVDs? Fast-forward to 2005 and the Xbox2 is reported to only have a standard DVD9 drive while the Playstation 3 will house a Blu-Ray reader. As Will Smith once said, it's the new hotness versus the old busted up joint. Which would you rather have?

Microsoft had two things going for it this generation; superior hardware and Halo. It's becoming clear that they won't have a hardware advantage next generation. The hardware front will be even worse if the Xbox 2 internal hard drive (the main advantage of the current Xbox) becomes a taboo optional console add-on (developers never support add-ons), as is being reported.

Posted: Sun Jun 05, 2005 5:06 pm

CPU
The Xbox 360 processor was designed to give game developers the power that they actually need, in an easy to use form. The Cell processor has impressive streaming floating-point power that is of limited use for games.

The majority of game code is a mixture of integer, floating-point, and vector math, with lots of branches and random memory accesses. This code is best handled by a general purpose CPU with a cache, branch predictor, and vector unit.

The Cell’s seven DSPs (what Sony calls SPEs) have no cache, no direct access to memory, no branch predictor, and a different instruction set from the PS3’s main CPU. They are not designed for or efficient at general purpose computing. DSPs are not appropriate for game programming.

Xbox 360 has three general purpose CPU cores. The Cell processor has only one.

Xbox 360’s CPUs has vector processing power on each CPU core. Each Xbox 360 core has 128 vector registers per hardware thread, with a dot product instruction, and a shared 1-MB L2 cache. The Cell processor’s vector processing power is mostly on the seven DSPs.

Dot products are critical to games because they are used in 3D math to calculate vector lengths, projections, transformations, and more. The Xbox 360 CPU has a dot product instruction, where other CPUs such as Cell must emulate dot product using multiple instructions.

Cell’s streaming floating-point work is done on its seven DSP processors. Since geometry processing is moved to the GPU, the need for streaming floating-point work and other DSP style programming in games has dropped dramatically.

Just like with the PS2’s Emotion Engine, with its missing L2 cache, the Cell is designed for a type of game programming that accounts for a minor percentage of processing time.

Sony’s CPU is ideal for an environment where 12.5% of the work is general-purpose computing and 87.5% of the work is DSP calculations. That sort of mix makes sense for video playback or networked waveform analysis, but not for games. In fact, when analyzing real games one finds almost the opposite distribution of general purpose computing and DSP calculation requirements. A relatively small percentage of instructions are actually floating point. Of those instructions which are floating-point, very few involve processing continuous streams of numbers. Instead they are used in tasks like AI and path-finding, which require random access to memory and frequent branches, which the DSPs are ill-suited to.

Based on measurements of running next generation games, only ~10-30% of the instructions executed are floating point. The remainders of the instructions are load, store, integer, branch, etc. Even fewer of the instructions executed are streaming floating point—probably ~5-10%. Cell is optimized for streaming floating-point, with 87.5% of its cores good for streaming floating-point and nothing else.

Bandwidth
The PS3 has 22.4 GB/s of GDDR3 bandwidth and 25.6 GB/s of RDRAM bandwidth for a total system bandwidth of 48 GB/s.

The Xbox 360 has 22.4 GB/s of GDDR3 bandwidth and a 256 GB/s of EDRAM bandwidth for a total of 278.4 GB/s total system bandwidth.

Why does the Xbox 360 have such an extreme amount of bandwidth? Even the simplest calculations show that a large amount of bandwidth is consumed by the frame buffer. For example, with simple color rendering and Z testing at 550 MHz the frame buffer alone requires 52.8 GB/s at 8 pixels per clock. The PS3’s memory bandwidth is insufficient to maintain its GPU’s peak rendering speed, even without texture and vertex fetches.

The PS3 uses Z and color compression to try to compensate for the lack of memory bandwidth. The problem with Z and color compression is that the compression breaks down quickly when rendering complex next-generation 3D scenes.

HDR, alpha-blending, and anti-aliasing require even more memory bandwidth. This is why Xbox 360 has 256 GB/s bandwidth reserved just for the frame buffer. This allows the Xbox 360 GPU to do Z testing, HDR, and alpha blended color rendering with 4X MSAA at full rate and still have the entire main bus bandwidth of 22.4 GB/s left over for textures and vertices.

When you break down the numbers, Xbox 360 has provably more performance than PS3. Keep in mind that Sony has a track record of over promising and under delivering on technical performance. The truth is that both systems pack a lot of power for high definition games and entertainment.

However, hardware performance, while important, is only a third of the puzzle. Xbox 360 is a fusion of hardware, software and services. Without the software and services to power it, even the most powerful hardware becomes inconsequential. Xbox 360 games—by leveraging cutting-edge hardware, software, and services—will outperform the PlayStation 3.

GPU
Even ignoring the bandwidth limitations the PS3’s GPU is not as powerful as the Xbox 360’s GPU.

Below are the specs from Sony’s press release regarding the PS3’s GPU.

RSX GPU
• 550 MHz
• Independent vertex/pixel shaders
• 51 billion dot products per second (total system performance)
• 300M transistors
• 136 “shader operations” per clock

The interesting ALU performance numbers are 51 billion dot products per second (total system performance), 300M transistors, and more than twice as powerful as the 6800 Ultra.

The 51 billions dot products per cycle were listed on a summary slide of total graphics system performance and are assumed to include the Cell processor. Sony’s calculations seem to assume that the Cell can do a dot product per cycle per DSP, despite not having a dot product instruction.

However, using Sony’s claim, 7 dot products per cycle * 3.2 GHz = 22.4 billion dot products per second for the CPU. That leaves 51 – 22.4 = 28.6 billion dot products per second that are left over for the GPU. That leaves 28.6 billion dot products per second / 550 MHz = 52 GPU ALU ops per clock.

It is important to note that if the RSX ALUs are similar to the GeForce 6800 ALUs then they work on vector4s, while the Xbox 360 GPU ALUs work on vector5s. The total programmable GPU floating point performance for the PS3 would be 52 ALU ops * 4 floats per op *2 (madd) * 550 MHz = 228.8 GFLOPS which is less than the Xbox 360’s 48 ALU ops * 5 floats per op * 2 (madd) * 500 MHz= 240 GFLOPS.

With the number of transistors being slightly larger on the Xbox 360 GPU (330M) it’s not surprising that the total programmable GFLOPs number is very close.

The PS3 does have the additional 7 DSPs on the Cell to add more floating point ops for graphics rendering, but the Xbox 360’s three general purpose cores with custom D3D and dot product instructions are more customized for true graphics related calculations.

The 6800 Ultra has 16 pixel pipes, 6 vertex pipes, and runs at 400 MHz. Given the RSX’s 2x better than a 6800 Ultra number and the higher frequency of the RSX, one can roughly estimate that it will have 24 pixel shading pipes and 4 vertex shading pipes (fewer vertex shading pipes since the Cell DSPs will do some vertex shading). If the PS3 GPU keeps the 6800 pixel shader pipe co-issue architecture which is hinted at in Sony’s press release, this again gives it 24 pixel pipes* 2 issued per pipe + 4 vertex pipes = 52 dot products per clock in the GPU.

If the RSX follows the 6800 Ultra route, it will have 24 texture samplers, but when in use they take up an ALU slot, making the PS3 GPU in practice even less impressive. Even if it does manage to decouple texture fetching from ALU co-issue, it won’t have enough bandwidth to fetch the textures anyways.

For shader operations per clock, Sony is most likely counting each pixel pipe as four ALU operations (co-issued vector+scalar) and a texture operation per pixel pipe and 4 scalar operations for each vector pipe, for a total of 24 * (4 + 1) + (4*4) = 136 operations per cycle or 136 * 550 = 74.8 GOps per second.

Given the Xbox 360 GPU’s multithreading and balanced design, you really can’t compare the two systems in terms of shading operations per clock. However, the Xbox 360’s GPU can do 48 ALU operations (each can do a vector4 and scalar op per clock), 16 texture fetches, 32 control flow operations, and 16 programmable vertex fetch operations with tessellation per clock for a total of 48*2 + 16 + 32 + 16 = 160 operations per cycle or 160 * 500 = 80 GOps per second.

Overall, the automatic shader load balancing, memory export features, programmable vertex fetching, programmable triangle tesselator, full rate texture fetching in the vertex shader, and other “well beyond shader model 3.0” features of the Xbox 360 GPU should also contribute to overall rendering performance.

One of the great things about working at Xbox is that we have some of the smartest people in the world working on the Xbox 360. When Sony came announced the PS3, along with the product specs some of our team started looking at some of the numbers to see what they mean. Floating Point, shaders, bandwidth….what does it all mean. Clearly there are some numbers and stats that mean more to gaming then others, so the team cranked out some facts for everyone to absorb. Our world class technology team looked at the numbers and claims and decided to do what everyone else does: compare them to the PS3. The difference it that these guys are uniquely qualified to do so, and can cut through the smoke and mirrors to see what the real deal is. To that end, I present this summary, which I have broken up into four parts to make it more RSS Reader friendly.

Warning: Some of this stuff may make your head hurt, but these are the facts as they stand right now. Enjoy the read:

XBOX 360 / PLAYSTATION 3 PERFORMANCE COMPARISON

SUMMARY
Now that the Xbox 360 and PlayStation 3 specifications have been announced, it is possible to do a real world performance comparison of the two systems.

There are three critical performance aspects of a console:
• Central Processing Unit (CPU) performance.
o The Xbox 360 CPU architecture has three times the general purpose processing power of the Cell.
• Graphics Processing Unit (GPU) performance
o The Xbox 360 GPU design is more flexible and it has more processing power than the PS3 GPU.
• Memory System Bandwidth
o The memory system bandwidth in Xbox 360 exceeds the PS3’s by five times.

The Xbox 360’s CPU has more general purpose processing power because it has three general purpose cores, and Cell has just one.

Cell’s claimed advantage is on streaming floating point work which is done on its seven DSP processors.

The Xbox 360 GPU has more processing power than the PS3’s. In addition, its innovated features contribute to overall rendering performance.

Xbox 360 has 278.4 GB/s of memory system bandwidth. The PS3 has less than one-fifth of Xbox 360’s (48 GB/s) of total memory system bandwidth.

CONCLUSION
When you break down the numbers, Xbox 360 has provably more performance than PS3. Keep in mind that Sony has a track record of over promising and under delivering on technical performance. The truth is that both systems pack a lot of power for high definition games and entertainment.

However, hardware performance, while important, is only a third of the puzzle. Xbox 360 is a fusion of hardware, software and services. Without the software and services to power it, even the most powerful hardware becomes inconsequential. Xbox 360 games—by leveraging cutting-edge hardware, software, and services—will outperform the PlayStation 3.

Posted: Mon Jun 06, 2005 2:52 am

I can't believe you just quoted/plagiarized Major Nelson's comparison.

I'm sorry, but it's so badly done I'm almost crying in pain here.

I've refuted this so many times on so many boards I'm too tired to refute it all. Sorry.

But lookat his math. My. Gosh.

Firstly, GPU's- not enough info has been released to compare. He just compares shader performance.

Bandwidth. ROFL!!!!!

Quote:

Bandwidth
The PS3 has 22.4 GB/s of GDDR3 bandwidth and 25.6 GB/s of RDRAM bandwidth for a total system bandwidth of 48 GB/s.

The Xbox 360 has 22.4 GB/s of GDDR3 bandwidth and a 256 GB/s of EDRAM bandwidth for a total of 278.4 GB/s total system bandwidth.

Did he just do this?
Shocked

Okay, let me make a comparison.

There are two roads that are 100 miles in length.

Road one: 30 miles per hour for 99 miles, 100 miles per hour for 1 mile.

Road two: 30 miles per hour for 50 miles, 40 miles per hour for 50 miles.

Would you say road one has an average speed of 130 miles because you add 30 MPH + 100 MPH? Absolutely not! That's PRECISELY what this guy did!

XBox 360:
512 MB of RAM at 22.4 GB/s
A tiny 10 MB of EDRAM at 256 GB/s

See the point? A tiny TEN MEGS run at that high speed. EVERYTHING ELSE runs at 22.4 GB/s. You can't just add them together and say its 278 total system bandwidth because only like 1% of the system runs at ALMOST that speed (but less). Not one part of the system runs at that speed, and 99% of it runs at a tenth of that speed.

Meanwhile, PS3:
256 MB of RAM at 22.4 GB/s
256 MB of RAM at 25.6 GB/s

And IIRC the PS3 has more bandwidth for the processor.

This is just Microsoft hype. You realize Major Nelson works for MS, right?

I'm not even going to get in to his incapability to understand basic processor architecture. The X360 has an equally hard time with branches, not just the PS3. Check Arstechnica.

Posted: Mon Jun 06, 2005 2:53 am

Arstechnica:

Quote:

game developer comments (on the record and off the record) have Xenon's performance on branch-intensive game control, AI, and physics code as ranging from mediocre to downright bad. Xenon will be a streaming media monster, but the parts of the game engine that have to do with making the game fun to play (and not just pretty to look at) are probably going to suffer. Even if the PPE's branch prediction is significantly better than I think it is, the relatively meager 1MB L2 cache that the game control, AI, and physics code will have to share with procedural synthesis and other graphics code will ensure that programmers have a hard time getting good performance out of non-graphics parts of the game.

Furthermore, the Xenon may be capable of running six threads at once, but the three types of branch-intensive code listed above are not as amenable to high levels of thread-level parallelization as graphics code. On the other hand, these types of code do benefit greatly from out-of-order execution, which Xenon lacks completely, a decent amount of execution core width, which Xenon also lacks; branch prediction hardware, which Xenon is probably short on; and large caches, which Xenon is definitely short on. The end result is a recipe for a console that provides developers with a wealth of graphics resources but that asks them to do more with less on the non-graphical side of gaming.

Quote:

At any rate, Playstation 3 fanboys shouldn't get all flush over the idea that the Xenon will struggle on non-graphics code. However bad off Xenon will be in that department, the PS3's Cell will probably be worse. The Cell has only one PPE to the Xenon's three, which means that developers will have to cram all their game control, AI, and physics code into at most two threads that are sharing a very narrow execution core with no instruction window. (Don't bother suggesting that the PS3 can use its SPEs for branch-intensive code, because the SPEs lack branch prediction entirely.) Furthermore, the PS3's L2 is only 512K, which is half the size of the Xenon's L2. So the PS3 doesn't get much help with branches in the cache department. In short, the PS3 may fare a bit worse than the Xenon on non-graphics code, but on the upside it will probably fare a bit better on graphics code because of the seven SPEs

Arstechnica is an extremely well respected tech site. And extremely unbiased from what I've seen.

Posted: Mon Jun 06, 2005 3:49 am

Praxis @ Sun Jun 05, 2005 6:53 pm wrote:

Arstechnica:

Quote:

game developer comments (on the record and off the record) have Xenon's performance on branch-intensive game control, AI, and physics code as ranging from mediocre to downright bad. Xenon will be a streaming media monster, but the parts of the game engine that have to do with making the game fun to play (and not just pretty to look at) are probably going to suffer. Even if the PPE's branch prediction is significantly better than I think it is, the relatively meager 1MB L2 cache that the game control, AI, and physics code will have to share with procedural synthesis and other graphics code will ensure that programmers have a hard time getting good performance out of non-graphics parts of the game.

Furthermore, the Xenon may be capable of running six threads at once, but the three types of branch-intensive code listed above are not as amenable to high levels of thread-level parallelization as graphics code. On the other hand, these types of code do benefit greatly from out-of-order execution, which Xenon lacks completely, a decent amount of execution core width, which Xenon also lacks; branch prediction hardware, which Xenon is probably short on; and large caches, which Xenon is definitely short on. The end result is a recipe for a console that provides developers with a wealth of graphics resources but that asks them to do more with less on the non-graphical side of gaming.

Quote:

At any rate, Playstation 3 fanboys shouldn't get all flush over the idea that the Xenon will struggle on non-graphics code. However bad off Xenon will be in that department, the PS3's Cell will probably be worse. The Cell has only one PPE to the Xenon's three, which means that developers will have to cram all their game control, AI, and physics code into at most two threads that are sharing a very narrow execution core with no instruction window. (Don't bother suggesting that the PS3 can use its SPEs for branch-intensive code, because the SPEs lack branch prediction entirely.) Furthermore, the PS3's L2 is only 512K, which is half the size of the Xenon's L2. So the PS3 doesn't get much help with branches in the cache department. In short, the PS3 may fare a bit worse than the Xenon on non-graphics code, but on the upside it will probably fare a bit better on graphics code because of the seven SPEs

Arstechnica is an extremely well respected tech site. And extremely unbiased from what I've seen.

thx for the quote Praxis, looks like things are going 2 get really interesting for developers nd gamers in the coming years Smile

Posted: Mon Jun 06, 2005 5:19 am

Yeah, I have to say I was very surprised, I expected the PS3's huge floating point advantage would make it great for game data AND graphics but very difficult to program for and sucky for anything integer-related. Apparently due to the problems cited the SPE's are useless for game data and it only has one of the processors the X360 has for that (and the X360 processors suck at it at that), but on the other hand the SPE's should give a nice graphics boost.

PS3 should have better graphics for that assuming approximate equality in terms of graphics cards.
XBox 360 isn't designed well for non-graphics code, but PS3 is designed even worse for it, so X360 should do best.

Very interesting. I trust Arstechnica over my own impressions on the matter, they're extremely good and much more indepth than most sites.

IMHO, I think they're trying to optimize the systems to be the best for graphics and multimedia (Cell, 12 HD videos at once, for example) for both systems. To quote Sony, "The PS3 is not a games machine".

Nintendo might actually be given some catch-up room here if they design the system to be really good at game code, even if the processor is a bit slower it might be on par gamewise and even have the best phyisics because of the design. I'm curious if Nintendo will spin that to their advantage, or go with the same design (struggling on non-graphics code)...

Posted: Mon Jun 06, 2005 8:50 am

I'd say all the companies have something up their sleve. But I get the feeling M$'ll have the best one, for some reason. Probably a kickass launch title, maybe their Halo 2.5'll have the original storyline and an extension to the original or something. We can only hope.

TheDaddy @ Mon May 30, 2005 11:44 pm wrote:

Quote:

Even for MICROSOFT it hurt

No, it didn't. MS's loss was about 400 million US - if you think that "hurts" MS, think again...

Poor bill gates, I guess he'll have to wait untill next year to buy hawaii.

Posted: Mon Jun 06, 2005 3:16 pm

Like I said, their losses were about 400 million US...every quarter.

Over a billion a year.

Joined: 30 Jul 2006 Posts: 0

Quote:

Like I said, their losses were about 400 million US...every quarter.

Over a billion a year.

Certainly - a hell of a lot of money to lose. I think it's important to note 2 things though there. Firstly, a billion a year is a *lot* even for MS - so, would them spending that money not indicate that they fully intend to win, eventually, at any cost? It wouldn't be the first time Bill has won something by throwing money at it now, would it it Very Happy

Secondly, I think it shows how tough this market is for new guys. Say what you want about Xbox1, but imo it was a damn good machine - better (of *course* only imo) than ps2 - but they still lost a billion a year just getting in.

So I suppose my point would be, how are companies like Infinium Labs even *considering* entering console gaming?? How *can* they? For me, the answer is "they cant".

TD

Posted: Mon Jun 06, 2005 9:47 pm

Agreed there.

Hardware wise XBox WAS the most powerful system. That cannot be denied. I just don't like any of the games, sadly.

Anyway, we actually just finished studying protectionism in Political Science class. Dumping was one of the things we went over, as was subsidizing.

Dumping is when a country or corporation dumps its product on another market that they were not in before, that is, selling the product at a price so far below the cost of production that no one can compete, in order to force competitors out of the market.

It's actually illegal here in the U.S. but hardly ever enforced. That is, illegal for a corporation. But its very hard to prove the line between subsidizing and dumping in a court.

Anyway, IMHO Microsoft failed miserably. The intent was to dump the product, selling a vastly more powerful console at the same price as the competition, so as to steal their market share.

While they got a significant marketshare (15% worldwide), they failed to force ANY of their competitors out of business and failed to get a bigger marketshare than either of them. The dumping model involves taking huge losses in order to gain the largest market share, and they failed to do that.

Granted, they gained a good 15%, so it wasn't a total waste for MS. They're hoping to capitalize on it with the XBox 360. But it still didn't do near to what they want.

Anyway I pretty much agree with you. Infinium Labs...basicly doesn't stand a chance. Especially since they're following the XBox model. One of the reasons the XBox was more expensive was off the shelf PC parts. When you use custom hardware, its cheaper, as you had a hand in designing it and therefore get pretty much the best price. That's why Nintendo was able to sell the GameCube for $200 at a profit while Microsoft spend $400 to build every XBox. The GameCube was slower, but it wasn't TWICE as slow...

Microsoft learned and are going with custom hardware this time around. Infinium didn't learn and (if their console ever even is released) is going with the standard off the shelf components. And since they don't have the resources to enter the market the way Microsoft did...I don't see them having *any* chance.

I'm wondering if Microsoft is going to dump the X360 as well. If you fail once, try again. Or if they're going to try to sell for a profit (Nintendo made the biggest profit despite having the same 15% marketshare, why can't MS?).