Exactly. Someone please tell you-know-who to stop taking offense at these petty things.Titanio said:
Sony may lose grip in next game consoles war: Article
- Thread starter Deepak
- Start date
> "Especially if you are a journalist who is supposed to present an unbiased presentation of the data at hand?"
Maybe the journalist does not understand the information at hand?
> "The 360 has significantly better integer performance."
Does it? How do you come to that conclusion? From where I am sitting, all those SPE's running full bore, also provides more integer porformance than the Xbox 360 CPU. Every cycle not running a floating point operation, can operate on an vectorized integer operation.
Maybe the journalist does not understand the information at hand?
> "The 360 has significantly better integer performance."
Does it? How do you come to that conclusion? From where I am sitting, all those SPE's running full bore, also provides more integer porformance than the Xbox 360 CPU. Every cycle not running a floating point operation, can operate on an vectorized integer operation.
Alpha_Spartan
Regular
Thanks for proving that the PS2 was three times more powerful than the Xbox. That's what you get when you compare half a system to half a system.Edge said:
It came from MS engineers and was emailed to several gaming sites AFAIK, including IGN.
The fact that for every float ADD a SPE can do, it can do an integer ADD.
Based on what? An unoffical Major Nelson article? Or the offical MS document that compared PS3 and XB360 that was posted at Major Nelson?
Because the journaliset is taking what little he understands and is reporting it.
The journalist didn't. The journalist said the machine had twice the processing speed. That means overall (system TFlops figures from MS and Sony respectively).
Sorry? What processor doesn't exist?
Anyway, this is daft. You accept XeCPU has more integer performance than Cell based on no real world comparisons, yet you won't believe 2x the theoretical peak for Cell means it can attain 2x higher realworld performance over XeCPU because it's not proven in the real world. You make a reckless assertion that it's impossible for PS3 to be more than 2x as powerful in the realworld despite the fact on this forum we often cover the point that realworld efficiencies are more important than peak values and Cell provides a very different untested architecture that may or may not attain higher efficiences.
This is why these threads shouldn't be allowed. There's always at least one for every such thread that'll make rash claims that get 'debated' unintelligently. I concede. I accept Sony have lied to everyone, hoodwinked the entire press, it's all their doing and all the statics and specs that MS have put out there have nothing to do with it, and that it's impossible for a console of radically different processing architecture to another to process 2x as fast because, despite having a different and unproven architecture, you won't believe it. The journalists of this world aren't naive or misinformed but are being maliciously controlled by Ken 'Puppet-Meister' Kutaragi.
Edit : Fixing a quote, I see already we've sunk to 'XB was better than PS2/PS2 was better than XB' garbage. Please, for the sanity of the forum, killthe thread!
Alpha_Spartan said:
I know this has been explained to you a number of times, but you like that twisted argument to somehow compare it to this generation. It's like if you repeat that nonsense enough times, will people believe it? How many more on this forum believe that?
Here we go again:
1) 733 Mhz Celeron is far superior to the Emotion Engine on everything except floating point.
2) The GPU on the Xbox has massive floating point capability, that the Graphics Synthesizer was lacking. The GS has NO vector engine!!! NONE! ZERO! Do you understand that?
3) The Xbox has twice the external bandwidth and memory of the PS2.
4) The Xbox GPU was much more feature rich, than the PS2 GPU.
Thus as the specs bore out, makes the Xbox superior to the PS2. Easy to accept, and who denies this?
This generation:
1) GPU's are comparable.
2) CELL is a lot more powerful than the 360 CPU, thus giving the PS3 a TWICE performance advantage in that area.
Thus as the specs bore out, makes the PS3 superior to the 360.
Alpha_Spartan
Regular
And you still make this assumption with a question mark around the RSX. You have Sony's spec sheet, but...Edge said:
mckmas8808
Legend
Alpha_Spartan said:
Let's just stop this silly arguement. Can we start it when we get real RSX numbers. Please?
czekon said:
One gets the impression that Carmack isn't particularly fussed about CPU power as long as it's enough for his purposes. He couldn't have been more explicit about this at Quakecon - he's quite sceptical of the need for increasing CPU power vs increasing GPU power. So for him, two boxes may well be 6 of one and half a dozen of the other regardless of CPU differences - just as long as they're both enough on that side (and have great GPUs). Couple that with his scepticism of CPU parallelism and, well...
For what it's worth, we've heard opinion of greater difference too from other developers, and one wonders also why they think that..
Last edited by a moderator:
Alpha_Spartan
Regular
I implied no such thing. I'm just saying that all comparisons are futile until we have all the facts to have an informed opinion.Edge said:
Any conclusions as to which is more powerful means we're relying on marketing numbers. As far as I'm concerned you might as well say "PS3 is 1024 bit and the Xbox 360 is only 512 bit."
That's how silly this "terrorflop" shit sounds to me.
Alpha_Spartan
Regular
Moneyhats. The only non-ambiguous statement I've heard about PS3's power came from Factor5. And well, we know that it's moneyhats galore.Titanio said:
Alpha_Spartan said:
There've been a number now, actually, but I was specifically thinking of comments made by a certain third party developer who's actually working on a X360 game at the moment, when I made that post.
Oh, and certainly F5 aren't the only first/second party to have made that claim "unambiguously". You can take their words with a grain of salt if you wish, but I think it's interesting that, for now at least, MS's "moneyhatted" devs aren't making similar claims on its side (although I'd expect them to get round to it at some point!).
Last edited by a moderator:
scooby_dooby
Legend
Edge said:
Um, realworld efficiency for one thing.
Are you saying that FLOP counts are an effective way to gauge power when comparing different architectures?
There are many realworld cases where the hardware with the higher theoretical flop count underperforms the hardware with the lower peak FLOPS.
Why does everyone need to accept the PS3 as more powerful? Not a single game has been created yet. Is it really that out of the question to wait until we see the realworld performance of these two machines?
scooby_dooby said:
Read again, what I posted:
CELL has:
- More than twice the internal bandwidth
- More than twice the external bandwidth
- More than twice the number of processors
- More than twice the amount of on-chip memories
- More than twice the floating point rate
of the Xbox 360 CPU.
CELL is superior to the Xbox 360 in a number of CRITICAL areas that all help contribute to greater throughput.
I'm not just comparing GFLOP's.
Ummm, maybe because it's true. Why do you have a problem with people accepting this?
If I said the Xbox was more powerful than the PS2, people don't have a problem with this, so why is the current generation any different in the acceptance of one being more powerful than the other? Is it because people who are fans of the Xbox 360 are afraid that being seen as less powerful will limit it's chances at success?
Last edited by a moderator:
