They're questions that have heated up fan forums since the launch of the current console generation -- which one is really more powerful, the Xbox 360 or the PlayStation 3? Is all that business about developers' failure to grasp the advanced Cell architecture accurate? And which machine has stronger graphics potential?
Former IBM technical architect David Shippy, who worked on both the PS3's Cell-specific PPU chip and Xbox 360's Xenon CPU talks to Gamasutra as part of an in-depth interview, and shares his thoughts on the relative pluses and minuses of each console's architecture.
Shippy has co-authored a somewhat controversial new book called 'The Race For A New Game Machine' about his work at IBM on Power architecture chips used in both systems.
A recent Wall Street Journal article on the book claimed that the IBM, Toshiba, and Sony co-funded Cell developments essentially paved the way for IBM's contract with Microsoft for the Xenon CPU -- a claim that Shippy discusses in the feature.
But Gamasutra also asked him about the relative power of the two systems -- since he worked so intimately on them, does he have an opinion on which was the more powerful?
"I'm going to have to answer with an 'it depends,'" laughs Shippy, after a pause. "Again, they're completely different models. So in the PS3, you've got this Cell chip which has massive parallel processing power, the PowerPC core, multiple SPU cores… it's got a GPU that is, in the model here, processing more in the Cell chip and less in the GPU. So that's one processing paradigm -- a heterogeneous paradigm."
"With the Xbox 360, you've got more of a traditional multi-core system, and you've got three PowerPC cores, each of them having dual threads -- so you've got six threads running there, at least in the CPU. Six threads in Xbox 360, and eight or nine threads in the PS3 -- but then you've got to factor in the GPU," Shippy explains. "The GPU is highly sophisticated in the Xbox 360."
"At the end of the day, when you put them all together, depending on the software, I think they're pretty equal, even though they're completely different processing models," he concludes.
What about the familiar refrain that the PS3's architecture is overcomplicated, challenging developers to program effectively? "The Cell architecture, from a software programming standpoint, is definitely a new paradigm," Shippy concedes.
"And I think what the game community would argue is that, since it is different, initially it is harder to program the Cell chip -- it's not a traditional multiprocessor environment," he says.
"The real hardcore coders would argue that, once you do understand it and can program to it, you absolutely get the most out of the hardware, and really write some fairly low-level code that's really high performance," he adds.
"I think some of the bigger game houses that will write more high-level code would really prefer an Xbox 360 -- right out of the chute, it's easier to write code for. I think you can really leverage the Cell hardware technology -- but it is harder to get your head around."
A good explanation from a CPU designer viewpoint. I never thought 360 CPU was architectural based on Cell's design in more than 2%, but it takes technological advantages in low thermal generation and probably other lower level details like bus communication from the Cell.
Every way, I think the main problem of the PS3 is the GPU-Chipset design. It used an already outdated technology in the falling 2006 by using a classical (little modified) nVidia 7x00-like GPU, with a 256MB+256MB fragmented memory model. The GPU has no modern characteristics like Texture Arrays, Embeeded DRAM with rescalers, 32bit-HDR targets, or direct access to the CPU’s 2nd level cache (and some other DX10/DX11 jingles 360’s GPU has). So supposing a Console with an even more powerful CPU than Cell (let’s say twice as fast), it couldn’t be exploited if other elements of the graphic pipeline are as limited and slow.
In resume: Sony designers put a lot of strengths in CPU’s design but they did a bad work with the overall design, for a VideoGame machine’s perspective (IMHO).
It would be great an in-depth comparison of the GPUs and complete console architectures, not only their CPUs.
Every way, I think the main problem of the PS3 is the GPU-Chipset design. It used an already outdated technology in the falling 2006 by using a classical (little modified) nVidia 7x00-like GPU, with a 256MB+256MB fragmented memory model. The GPU has no modern characteristics like Texture Arrays, Embeeded DRAM with rescalers, 32bit-HDR targets, or direct access to the CPU’s 2nd level cache (and some other DX10/DX11 jingles 360’s GPU has). So supposing a Console with an even more powerful CPU than Cell (let’s say twice as fast), it couldn’t be exploited if other elements of the graphic pipeline are as limited and slow.
In resume: Sony designers put a lot of strengths in CPU’s design but they did a bad work with the overall design, for a VideoGame machine’s perspective (IMHO).
It would be great an in-depth comparison of the GPUs and complete console architectures, not only their CPUs.