Pema is right, it was on the same package, they moved it to on-die after redesign and it ended up being faster so they had to gimp it down. Wii U is on-die to start with so it doesn't have the same problems. Stop arguing with him on this one.

yep, no pint at all, its clear that even if you have the evidence on your face and deny it, then your intentions are not to uncover the truth

yep, the 360 gpu and edram where on the saje package, not die

but

the xbox  rops where on the same die with the edram

here, check it yourself

http://meseec.ce.rit.edu/551-projects/spring2012/2-4.pdf

"

Supportfor a superset ofDirectX 9.0c APIDirectX Xbox 360, and Shader Model 3.0+

• 500 MHz, 10 MiB daughter embeddedDRAM (at 256GB/s)framebuffer on 90 nm, 80 nm(since 2008) or 65nm(since 2010).

– NEC designed eDRAM die includes additional logic (192 parallel pixel processors)for color, alpha compositing, Z/stencil buffering, and anti‐aliasing called

“Intelligent Memory”, giving developers 4‐sample anti‐aliasing at very little performance cost.

– 105million transistors

– 8 RenderOutput units

"

You do know whats a Render Output Unit I suppose right?

"

The one key area of bandwidth, that has caused a fair quantity of controversy in its inclusion of specifications, is that of bandwidth available from the ROPS to the eDRAM, which stands at 256GB/s. The eDRAM is always going to be the primary location for any of the bandwidth intensive frame buffer operations and so it is specifically designed to remove the frame buffer memory bandwidth bottleneck - additionally, Z and colour access patterns tend not to be particularly optimal for traditional DRAM controllers where they are frequent read/write penalties, so by placing all of these operations in the eDRAM daughter die, aside from the system calls, this leaves the system memory bus free for texture and vertex data fetches which are both read only and are therefore highly efficient. Of course, with 10MB of frame buffer space available this isn't sufficient to fit the entire frame buffer in with 4x FSAA enabled at High Definition resolutions and we'll cover how this is handled later in the article.

"

so, the same applies for wii u gpu and edram since are in the same die, just like xbox rops and the edram where in the same die

read the article dude

LOL WHAT? They are both important, you can't think of it as the same thing as a PC to start with, if you look at how the circuit is laid out on the Wii U, then you'd know that all the memory are very close together so it's good for fast fetching and plenty for it to work with the 32MB eDRAM after compression is involved.

It doesn't matter whether their brought out or not, they obviously have some agenda.

History tells me that you didn't know how to do math LOL. I wonder how hard figuring out the pixel output of the WII U was ? The ones who are uneducated will continue to fear and I obviously abide by the rules. 

quite the arguent of the guy who didnt know how to calculate bandwidth and had to be shooled

quite the argument who jumps to conclusions like the wiiu edram bandwidth without bases to back it up

quite the arguiment for someone who needs the same schooling over and over by shines sae comments

quite the argumment who doesnt want to admit defeat when he has clearly been  beaten

quite the argument of someone with a clear agenda to troll the wiiu hardware and cant even do a better job than what reggie does in his work

Remember, the "It can do more with less" phrase. The WII U will probably run some modern efficient algorithm to achieve those affects. Relax, there will be more important parts of the WII U such as it's modern architecture and that's the real advantage with the WII U. 

I still wonder if the eDRAM implementation is similar to intel iris pro 5200. 

relax, if it looks like this then no

if it looks like this then yes

What's even more important is the main memory bandwidth in WII Us case. What's the problem with it thinking that it's like a PC ? All next gen consoles are literally dumbed down PCs much like the PS360 was. Fast fetching is nice and all but if I want to access a massive amount of textures ? (Something that is fairly limited by the main memory bandwidth.) Compression can only take you so far. 

Didn't you get exposed by Pemalite ? If I were I would drop the talk and move on to another thread. 

Wow I really pity you then. Your obsessing another man over the internet so much that I got you to hate me LOL. Damn you must of got mind bended so much by me and pemalite LMAO. 

Still haven't answered my math question yet ?