Microsoft: Xbone Is 3x As Powerful Than X360 (Phil Spencer Twitter: It Was A Mistake)

[Michael-5]

HoloDust said:

Michael-5 said:

Either way, 9x, 10x, I won't argue that. When CGI says over 15x, then I'll call him out on that. 1)

1) If you compare just PS4's and PS3's GPU, than difference is most certainly more than 10x.

2) You're using FLOPS as only measure of systems capabilities - don't...as I said, shader performance skyrocketed in last gen, but other parameters have not...making overall performance jump around 10x from XBOX1 to 360 (which is insane in just 4 years, and is much more impressive than 10x or slightly more in 8 years)

3) Wiki page states 230 GFLOPS for Cell (that's PS3 CPU) - Cell has 1 PPE and 8 SPEs - each of these performs at 25.6GFLOPS, single precision. 1 SPE is inactive for yield issues, 1 is reserved for OS. So math is (1PPE + 6SPE)*25.6GFLOPS = 179.2GFLOPS available to devs (plus 176GFLOPS from GPU). Of course, unless you're Miyamoto Musashi of PS3 coding, you won't be able to see anyhere near this numbers.

4) Because core speed is completely irrelevant if you don't know other parameters. For example, 360 is running at 550MHz core clock, and it has 48*5 shaders (for total of 240). So in theory it can do 240 * 0.5GHz = 120 Goperations per second. Since each shader can do 1 multiply+1 add at the same time, whole GPU can perform 120*2= 240GFLOPS. That's in theory...360 is built on VLIW5 architecture (just like WiiU, while we're at it), so in most cases only 4 out 5 shaders in group will be working, bringing down that number effectively, and that's just for start.

PS3's GPU (RSX) does not have unified shaders, but instead 24 pixel and 8 vertex shaders, each capable of 10 operations per cycle. RSX runs at 550MHz, so math is: 24 * 0.55GHz * 10 + 8 * 0.55GHz * 10 = 176GFLOPS. This is theory again, because you need perfect alignment of loads on pixel and vertex shaders to achieve theoretical maximum.

PS4's core clock is 800MHz, and it has 1152 unified shaders, so math is 1152 * 0.8GHz * 2 = 1843.2GFLOPS. PS4's GPU is also built on GCN architecture, which has numerous improvements over VLIW5.

Same thing is when calculating theoretical pixel/texel fillrates - clock * number of ROPs (pixel) or clock * number of TMUs (texel) (360 has 16 TMUs and 8 ROPs, PS3 has 24 TMUs and 8 ROPs, PS4 has 72 TMUs and 32 ROPs).

On top of all this, you have memory bandwidth - good example how it affects same GPU at exactly same core clock speed are 3 HD5550 cards with 3 different memory bandwidths (12.8GB/s : 25.6GB/s : 51.2GB/s) - 30fps : 40fps : 49fps

So, as you can see, basing your comparisons on core clock (or GFLOPs for that matter) is...well, wrong. At the end of course, no matter how much theoretical data you have, you need real benchmarks, and that is only real measure of how certain GPUs perform (or compare). In this case...go to 1)

1) So I'm right when we talk about raw power, PS4 is about 10x as powerful as PS3, not up to 15x, or more powerful?

2) I don't undertand how the jump from XB1 to 360 is only 10x, when the GFLOPS diff is about 15x. I know you said I shouldn't use GFLOPs to measure, since stuff like shaders have improved drastically, but the lack of an improvement in shaders wouldn't make the performance jump smaller.

Either way, not worth arguing, you admit that in 4 years the graphical jump was more insane then current gen jump, and if I were to argue anything (why are we arguing about PS4's performance, we both agree 9/10x or so), that's my arguement. Also I would argue that we see less improvements with similar jumps in power because of dimishinging return. 600-6,000 polygons is noticable, but 60,000 to 600,000 polygons isn't really. PS4/One will look good because they can have so many objects on screen. Killzone for instance had a whole city rendered, well I would add.

3) Okay, makes sense, I read about those 8 CPU's, I didn't realize the 230GFLOPS value accounted for unused cells.

4) I follow you half way, LOL. You say I can't us GFLOPS to measure performance, but here you are calculating GFLOPs.

Where did you find out the number of unified shaders?

Also I'm not basing my comparisions on core clock speed. I said:

CGI-Quality said:

HoloDust said:

Pemalite said:

Michael-5 said:

The new GPU isn't that much faster then the one in PS3. 

I can't beleive I just read that.
A Geforce 7800 class GPU is not that much slower than a Radeon 7850 class GPU?

I know, I was also in "is this guy for real?" state when I've read it.

"Ignorance is bliss" I suppose...

Indeed, but all you can do is educate and hope it sinks in one day.

I didn't say it to downgrade PS4's performance, just to make a point that not everything on PS4 improved so drastically. I didn't say anything wrong, but people assumed I was implying something by saying that.

----

Basically, what I've learnt from you is that you can't directly measure PS4's performance based off its specs. GFLOPS seems the best way to estimate a number (What's a better way?), but you need a raw benchmark because things like Memory Bandwidth, fill rate, and bus (something I know was PS2's bottleneck) affect performance. With consoles, you won't get that, since PS3/PS4 games run off 1 setting, where PC games can be altered.

Now I have a question, if Memory bandwidth is only a 5x improvement in the PS4 (38.4 -> 192 GB/s), will that hinder and help the PS4's performance? Is there a linear relationship, or exponential?