@ Deneidez
The SPEs are really at the heart of the Cell design, they need the PPE just like you need your air to breathe, just like a car needs wheel to drive, are the wheels at the heart of a car?
Look at the SPEs as hard working super smart employees, they will wait for their boss (PPE) who isn't that smart at the stuff the SPEs are doing, but he knows how to drill his employees well.
Mike, I'm still waiting for your explanation for your contradictions. You have one post which says it's easier to attain peak performance on the Cell on the previous page, and another one saying the opposite in this one. I'd also like to know why you're citing me if you think I'm bogus.
All in all, you've contradicted yourself at least three times in this thread. Better go back to the basics and rethink some stuff.
My Mario Kart Wii friend code: 2707-1866-0957
It was answered on page 1:
It depends.
I go with the Cell, because what the Cell is great at, is far faster then any CPU, at any cost (up to 100x faster then the Xenon as very very specific tasks). The effects that can be done with what the Cell is good at will provide types of visuals we have never seen in a video game before. It's already been done with asset animations in Rachet and Clank, and some of the water effects in Lair (to bad that game sucks). Those things could not be done on the 360.
What the Xenon is better at, it is only marginally better, so what you gain is far less noticeable. Also, what the Xenon is better at, the PC is even better at, so a PC game will look better, and you won't see anything out of the 360 that makes you go "holy shit".
There ya go, about as non technical as I can get :)
| NJ5 said: Mike, I'm still waiting for your explanation for your contradictions. You have one post which says it's easier to attain peak performance on the Cell on the previous page, and another one saying the opposite in this one. I'd also like to know why you're citing me if you think I'm bogus. All in all, you've contradicted yourself at least three times in this thread. Better go back to the basics and rethink some stuff. |
Look achieving near peak performance has already been achieved as pointed out by research documents also linked to within this thread with regard to the Cell. Show me a document which shows similar efficiency with regard to the Xenon's 77 GFlops.
There are two things. 1 is being able to achieve near peak performance, 2 being able to yield results.
One example would be a Motorcycle can go faster and it's easier to reach its peak performance, but if it's your first time on a Motorcycle you may yield quicker results on a bike you have always used since you were a kid, but you won't reach your peak potential nomatter how much you work a sweat. The muscle's peak performance is higher if you would be able to perform optimal contractions.
Fishie said:
For something that was designed to BREAK THE WINTEL MONOPOLY(Kutaragi`s words not mine) that is a pretty collosal failure.
|
Are you referring to the cell or the emotion engine? I don't think either are suited for desktop processing.
@NNN2004 - You will not find the answers you seek on this forum or any other gaming forum for that matter. If you are truly interested in this topic, I recommend you read the following articles. They provide much better information than you will find on any gaming forum.
PS3 vs. Xbox 360 Comparison: http://www.anandtech.com/showdoc.aspx?i=2453
PS3 Cell: http://www.anandtech.com/cpuchipsets/showdoc.aspx?i=2379&p=8
If you really want to determine which system is more powerful, you should look at each console's best exclusives. This will give you an idea of their power. On the PS3 side you should look at Uncharted, GT5P, and Metal Gear Solid 4. I feel these are representative of the PS3's power at the moment.
Thanks for the input, Jeff.
Nice, now you want me to show you research on a proprietary and closed processor. A little more realism please.
My Mario Kart Wii friend code: 2707-1866-0957
cell is alround better than whats in 360
...not much time to post anymore, used to be awesome on here really good fond memories from VGchartz...
PSN: Skeeuk - XBL: SkeeUK - PC: Skeeuk
really miss the VGCHARTZ of 2008 - 2013...
It's all about how the processors have to be coded to. As a result of a little thing called in order processing being required by both the PS3 and the 360's CPUs both systems require significant optimization by developers. The Cell, however, requires *much* more optimization in code than the 360 does and so whatever its strengths may be on paper they are not likely to show up in the vast majority of PS3 games.
http://www.anandtech.com/video/showdoc.aspx?i=2453&p=5
Ever since the Pentium Pro, desktop PC microprocessors have implemented Out of Order (OoO) execution architectures in order to improve performance. We’ve explained the idea in great detail before, but the idea is that an Out-of-Order microprocessor can reorganize its instruction stream in order to best utilize its execution resources. Despite the simplicity of its explanation, implementing support for OoO dramatically increases the complexity of a microprocessor, as well as drives up power consumption.
In a perfect world, you could group a bunch of OoO cores on a single die and offer both excellent single threaded performance, as well as great multi-threaded performance. However, the world isn’t so perfect, and there are limitations to how big a processor’s die can be. Intel and AMD can only fit two of their OoO cores on a 90nm die, yet the Xbox 360 and PlayStation 3 targeted 3 and 9 cores, respectively, on a 90nm die; clearly something has to give, and that something happened to be the complexity of each individual core.
Given a game console’s 5 year expected lifespan, the decision was made (by both MS and Sony) to favor a multi-core platform over a faster single-core CPU in order to remain competitive towards the latter half of the consoles’ lifetime.
So with the Xbox 360 Microsoft used three fairly simple IBM PowerPC cores, while Sony has the much publicized Cell processor in their PlayStation 3. Both will perform absolutely much slower than even mainstream desktop processors in single threaded game code, but the majority of games these days are far more GPU bound than CPU bound, so the performance decrease isn’t a huge deal. In the long run, with a bit of optimization and running multi-threaded game engines, these collections of simple in-order cores should be able to put out some fairly good performance.
As we discussed in our Cell article, in-order execution makes a lot of sense for the SPEs. With in-order execution as well as a small amount of high speed local memory, memory access becomes quite predictable and code is very easily scheduled by the compiler for the SPEs. However, for the PPE in Cell, and the PowerPC cores in Xenon, the in-order approach doesn’t necessarily make a whole lot of sense. You don’t have the advantage of a cacheless architecture, even though you do have the ability to force certain items to remain untouched by the cache. More than anything having an in-order general purpose core just works to simplify the core, at the expense of depending quite a bit on the compiler, and the programmer, to optimize performance.
Very little of modern day games is written in assembly, most of it is written in a high level language like C or C++ and the compiler does the dirty work of optimizing the code and translating it into low level assembly. Compilers are horrendously difficult to write; getting a compiler to work is a pretty difficult job in itself, but getting one to work well, regardless of what the input code is, is nearly impossible.
However, with a properly designed ISA and a good compiler, having an in-order core to work on is not the end of the world. The performance you lose by not being able to extract the last bit of instruction level parallelism is made up by the fact that you can execute far more threads per clock thanks to the simplicity of the in-order cores allowing more to be packed on a die. Unfortunately, as we’ve already discussed, on day one that’s not going to be much of an advantage.
The Cell processor’s SPEs are even more of a challenge, as they are more specialized hardware only suitable to executing certain types of code. Keeping in mind that the SPEs are not well suited to running branch heavy code, loop unrolling will do a lot to improve performance as it can significantly reduce the number of branches that must be executed. In order to squeeze the absolute maximum amount of performance out of the SPEs, developers may be forced to hand code some routines as initial performance numbers for optimized, compiled SPE code appear to be far less than their peak throughput.
While the move to in-order architectures won’t cause game developers too much pain with good compilers at their disposal, the move to multi-threaded game development and optimizing for the Cell in general will be much more challenging.
| TheRealMafoo said: It was answered on page 1: It depends. I go with the Cell, because what the Cell is great at, is far faster then any CPU, at any cost (up to 100x faster then the Xenon as very very specific tasks). The effects that can be done with what the Cell is good at will provide types of visuals we have never seen in a video game before. It's already been done with asset animations in Rachet and Clank, and some of the water effects in Lair (to bad that game sucks). Those things could not be done on the 360. What the Xenon is better at, it is only marginally better, so what you gain is far less noticeable. Also, what the Xenon is better at, the PC is even better at, so a PC game will look better, and you won't see anything out of the 360 that makes you go "holy shit". There ya go, about as non technical as I can get :) |
Have you seen the water effects they're includig in Gears 2? Go watch that tech demo and tell me the 360 can't handle it.
Fishie said:
SPE`s are not cores, we went trough that shit already. A core can work independantly, the SPE`s cannot as they NEED feeder data from the PPC core. |
Um, actually, they can feed themselves with their own DMAs, as long as their localstore code knows where to look. They are independant processors. They could even feed themselves new instructions if they wanted -- that's not really something that's going to happen very often, but they could do it. They are no less indepedant than the "secondary" cores of the Xenon -- they just operate in a very different manner from the PPU, unlike the Xenon's extra cores do from its primary. They are capable of independant operation -- in fact, if they weren't, the cell would be horribly slow, as asynchronous processing wouldn't really be possible.
Claiming that they are "co-processors", or not independant cores... is just plain incorrect. They are capable of independant operation, without question. As a matter of fact, having a SPU feed itself data is one of the best ways to get awe-inspiring performance out of it, as no intervention from the PPU is required.
About Us |
Terms of Use |
Privacy Policy |
Advertise |
Staff |
Contact
Display As Desktop
Display As Mobile
© 2006-2025 VGChartz Ltd. All rights reserved.
