• Hey Guest. Check out your NeoGAF Wrapped 2025 results here!

360 Gpu Exposed, 4XMSAA etc , and PS3GPU was a late change.

Vennt said:
I don't know, when he starts off with the flawed "3 cores vs 1 core" argument it kinda puts the rest of his PS3 analysis into question don't you think?

What's flawed about that claim, though? All he says is "general purpose processing power". Isn't that true? The 360 has three full, general purpose cores, each with a single VMX (SIMD flop unit, akin to MMX/SSE, etc. on desktop cpus). The Cell has one fully general purpose core (running at the same clock speed as the 360's three cores, and similar in architecture) with seven SIMD flop-specialized SPEs.

Whether that's going to be a worthwhile advantage when it comes to games is another question entirely. History would certainly suggest that the Cell's FLOP advantage is going to be much more important, but that doesn't mean that the 360's general purpose horsepower is going to necessarily be useless.
 
slidewinder said:
What's flawed about that claim, though? All he says is "general purpose processing power". Isn't that true? The 360 has three full, general purpose cores, each with a single VMX (SIMD flop unit, akin to MMX/SSE, etc. on desktop cpus). The Cell has one fully general purpose core (running at the same clock speed as the 360's three cores, and similar in architecture) with seven SIMD flop-specialized SPEs.

Whether that's going to be a worthwhile advantage when it comes to games is another question entirely. History would certainly suggest that the Cell's FLOP advantage is going to be much more important, but that doesn't mean that the 360's general purpose horsepower is going to necessarily be useless.

From my understanding, it is a valid graph...but a meaningless statistic. Unless we're running spreadsheets or web browsers, it's kind of a useless point.
 
AB 101 said:
That settles it.

3 general purpose processor > 1 general and 7 specialized ones!


Close thread.

Just give up already?!

index.7.gif


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

index.8.gif

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

index.3.gif

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

index.4.gif

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.

I have closed comments on this series of posts, except part 4 in


http://www.majornelson.com/2005/05/20/xbox...s3-part-1-of-4/
 
So that means X360 will open and close my windows icons a millisecond faster? Strange comparison. In my opinion the term general should never be used with consoles since they are specialized products.
 
Pedigree Chum said:
Not if Kojima has anything to say about it.

I think it was G4 who had a special on MGS and I seem to recall Kojima saying that he's leaving the MGS series- not sure if it's after MGS 4 or what though.
 
3rdman said:
From my understanding, it is a valid graph...but a meaningless statistic. Unless we're running spreadsheets or web browsers, it's kind of a useless point.

That bad, huh? So AI, for example, can be better done on the SPE/VMX than on a general purpose core?

Seems like physics for sure could. What was MS thinking with the three cores, then? Surely if they just wanted two more VMX units they would've designed them around a single core.
 
"Even ignoring the bandwidth limitations the PS3’s GPU is not as powerful as the Xbox 360’s GPU.

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."





...
 
slidewinder said:
That bad, huh? So AI, for example, can be better done on the SPE/VMX than on a general purpose core?

Seems like physics for sure could. What was MS thinking with the three cores, then? Surely if they just wanted two more VMX units they would've designed them around a single core.
I do think one of the cores is being used for audio.
 
Mrbob said:
So that means X360 will open and close my windows icons a millisecond faster? Strange comparison. In my opinion the term general should never be used with consoles since they are specialized products.

How many website this makes now that said overall x360 is more powerful than PS3? I know its getting to be a handful.

but their all wrong right?
 
"Xbox Live's Major Nelson's unofficial blog"

:lol

jesus you xbots will believe anything my god.

this just in Sony's President states they have a service better than xbox live. i believe them!! :lol
 
What is going on with Xbox fan sites?

Both Major Tom and TeamXbox have posted the absolute most pathetic "analysis" of the two systems, I think we've ever seen. Even worse than that first "analysis" from neowin or whatever that said that the Xbox360 GPU was actually twice as fast as initially indicated.

http://www.majornelson.com/2005/05/20/xbox-360-vs-ps3-part-1-of-4/

and

http://features.teamxbox.com/xbox/1160/Xbox-360-Playstation-3-Performance-Comparison/p1/

Now, teamxbox has always been a somewhat biased site, but I'm not aware of any actual patently false news stories (and they title it as a "Press Release") that they've done.

And Major Tom claims that the "Xbox team" has figured this out.

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:

Maybe these guys are right and have discovered some huge discrepancies??

But if not, they are out and out lying.

Don't give me they made simple 'calculation' mistakes, or misunderstood the specs. Both sites have an obvious agenda and are reporting to have "figured" it out from a very definative standpoint.
 
Ghost of Bill Gates said:
How many website this makes now that said overall x360 is more powerful than PS3? I know its getting to be a handful.

but their all wrong right?

viral marketing at its best (worst)

PS3 is more powerful this gen, deal with it.
 
Where is this quote from?
Hajaz said:
"Even ignoring the bandwidth limitations the PS3’s GPU is not as powerful as the Xbox 360’s GPU.

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."





...
 
Does anyone find weird that even if the RSX can use the 256 XDR main ram, the CPU can't?
That will be a big hit in perfomance in non-gfx operations.

In a ex. scenario a dev. can choose to use only 128mb for vram in the xbox360 (even if he can use 256 he takes the decision of don't do that because the game isn't graphical intensive and he can use the rest for world simulation, ai, etc. in the PS3 you can only use the 256mb
because you can't run those process in a GPU.
besides the retail HD on the xbox360 can make the things a lot better.
 
slidewinder said:
That bad, huh? So AI, for example, can be better done on the SPE/VMX than on a general purpose core?

Seems like physics for sure could. What was MS thinking with the three cores, then? Surely if they just wanted two more VMX units they would've designed them around a single core.


I'm NOT the best person to answer this...3 cores with two threads each. Each and any thread can be used to any number of things...AI, audio, etc. What each thread does is dependent on the developer. You could even unload some of the graphics work off of the GPU in a manner similiar to the Getaway Demo Sony showed.

Also, its a little unfair to call the CPU totally "general" because they are highly modified and specialized for gaming and its shared memory.
 
viral marketing at its best (worst)

PS3 is more powerful this gen, deal with it.

You have to admit they are doing a decent job of it. Before ps3 was announced people thought it would blow xbox 360 out of the water, now they are happy to settle for "slightly more powerfull".
 
slidewinder said:
The Cell has one fully general purpose core (running at the same clock speed as the 360's three cores, and similar in architecture) with seven SIMD flop-specialized SPEs.

The SPEs are more general than that. Your biggest concern with the SPEs would be data access, not computational capability. To ignore the SPEs entirely when "counting" general purpose performance is misleading.

The comparisons made by Major Nelson are simply......crazy. Unbelievable. Shameless.

Comparing "effective" memory bandwidth to 2% of memory versus physical bandwidth to 100% of PS3's memory is just not right. Why shouldn't we start, say, including bandwidth to the local memory in the SPEs in this equation? Oh right....that'd just make the X360 numbers look trivial.

His shading op figures for the respective GPUs are a nonsense. He's counting more than ATi count, and then assumes NVidia counted their ops the same way he did :lol

This is like asking Sony to step you through the X360 architecture and compare to PS3. Its fodder for the misinformed fanboy - if you want to be misled, then trust in these articles.
 
Why are some people concerned about his platform of choice being more or less powerful than the other? I must be the only f*cktard on this board that doesn't give a damn about graphical superiority.
 
TheDuce22 said:
You have to admit they are doing a decent job of it. Before ps3 was announced people thought it would blow xbox 360 out of the water, now they are happy to settle for "slightly more powerfull".

The truth will come out and I think you'll see that these "analysis" are flawed to the core. And it's going to happen pretty soon, because I think there will be a certain amount of pressure to do so. I doubt we've seen any legitimate (with some more correct than others) breakdown of these systems as we've barely gotten any information to this point.

Somebody is going to be served some crow and it will be very interesting to see who it is?
 
sonycowboy said:
The truth will come out and I think you'll see that these "analysis" are flawed to the core. And it's going to happen pretty soon, because I think there will be a certain amount of pressure to do so.

Agreed.

It's very very easy to say now that PS3 is more than slightly more powerful than X360, on balance. But some of us actually like to be able to back ourselves up before making such claims. Articles like this are just capitalising on this "non-certain" interim period where we're lacking specific detail on both systems that would absolutely confirm the likelihood that's already presented itself.

People complain about Sony BS, but I've never seen them stoop to such a level of FUD as this MS article. But then I guess MS invented FUD.
 
Razoric said:
Nothing else to say to someone who prints lies and posts links with false information. ;)


He's quite simply unbelievable. The campaigns that have been started this week are at a level that I've simply never seen. The mobilization is beyond what moveon.com was ever able to achieve.
 
The truth will come out and I think you'll see that these "analysis" are flawed to the core. And it's going to happen pretty soon, because I think there will be a certain amount of pressure to do so.

The truth wont actually come out untill we see the games from both sides. There is no risk in playing this little numbers/hype game. Sony will have more ammo as we get closer to launch but its not like they havent started allready saying the killzone cg was "realtime gameplay". At this point they are losing, its understandable considering how far the system is from launching.
 
That article is crap. The only interesting thing mentioned is its transistor counts...330m. Presumable that is GPU+Edram.
 
sonycowboy said:
He's quite simply unbelievable. The campaigns that have been started this week are at a level that I've simply never seen. The mobilization is beyond what moveon.com was ever able to achieve.

I think Viral Marketers have to print out entire threads or at least submit the link of their "work" to their boss. I'm gonna make that douche earn his paycheck. ;)
 
3rdman said:
That article is crap. The only interesting thing mentioned is its transistor counts...330m. Presumable that is GPU+Edram.

There's other website article links in this thread if you don't like one.. do a little research on them and you will see there's no bias...but make sure to take off your goggles.
 
Ghost of Bill Gates said:
There's other website article links in this thread if you don't like one.. do a little research on them and you will see there's no bias...but make sure to take off your goggles.

I have a quick question for you? Are you Deadmeat? And I'm being serious here. If not, do you know who he is?
 
gofreak said:
It's very very easy to say now that PS3 is more than slightly more powerful than X360, on balance. But some of us actually like to be able to back ourselves up before making such claims. Articles like this are just capitalising on this "non-certain" interim period where we're lacking specific detail on both systems that would absolutely confirm the likelihood that's already presented itself.

I totally agree.
And I'm really confident that all missing infos like the full RSX specs will come up in time for TGS along with the first real PS3 trailers.If we're lucky PS3 could even be playable in some form at TGS.As for the BS fanboys spread because they can't accept reality it's not really something new.
I still remember Sega fans claiming in their tech articles written after PS2 was introduced that because of the 4MB of Vram PS2 couldn't handle more polygons than DC :lol :D History repeats.
 
Razoric said:
I think Viral Marketers have to print out entire threads or at least submit the link of their "work" to their boss. I'm gonna make that douche earn his paycheck. ;)

I thought 'viral marketers' were not allowed on GAF? :)
 
So after it's proven that PS3 is far more powerful than Xbox 360 will they go back to "graphics dont matter, xbox live"? Curious....
 
maybe just for fun?!--> MS under powered the alpha kits to throw off sony... and then bam at e3 their system is just as powerful? and with a harddrive the system will cost less? sony has to recoup the money spent on BR&Cell


but anyways.... why isn't nintendo in this thread? does anyone care about the next nintendo system? where are the specs? do they even want to be placed in the same league as MS/Sony? or in two/three months the release specs that blow away what MS/Sony is doing?

A-IMO this is going to be the genesis/snes.... both will have awesome games, doesn't matter what system you own.
 
gofreak said:
The SPEs are more general than that. Your biggest concern with the SPEs would be data access, not computational capability. To ignore the SPEs entirely when "counting" general purpose performance is misleading.
Yea, you're right. Every SPE has an integer execution unit for one thing, and they are a lot more than some kind of "hyper MMX" units in general, for another. That article, which is a good read for ignorant people like myself, also specifically mentions AI (along with physics) as one of the things the SPEs will excel at, which answers one of my questions.

gofreak said:
The comparisons made by Major Nelson are simply......crazy. Unbelievable. Shameless.

Comparing "effective" memory bandwidth to 2% of memory versus physical bandwidth to 100% of PS3's memory is just not right. Why shouldn't we start, say, including bandwidth to the local memory in the SPEs in this equation? Oh right....that'd just make the X360 numbers look trivial.
Yea, even I knew that part was completely bogus.
AB 101 said:
That settles it.

3 general purpose processor > 1 general and 7 specialized ones!
I didn't mean anything like that. I just figured that those three general purpose processors would be good for something, that they might in some way help make up the known FLOP gap. Looks like that won't really be the case, though.
 
Razoric said:
So after it's proven that PS3 is far more powerful than Xbox 360 will they go back to "graphics dont matter, xbox live"? Curious....

Did you tested the final hardware of both consoles?
even with the recent specs you can see that both consoles are very close.
 
Xbox 360 has 10 extra megs of RAM inside!

X360 wins!

Seriously, with these next gen consoles I don't think you can break down the CPU/GPU performance seperately anymore and analyze them individually. How these next gen systems are designed you really need to take the whole setup into equation.
 
Top Bottom