Is MoSys the reason of an underpowered Revolution?

[Megadrive1988]

MoSys would not be the reason for an underpowered Revolution - that would be entirely upto Nintendo of Japan.

ATI, IBM, MoSys are only going to provide technologies which Nintendo asks for.

 

[Megadrive1988]

Hehe no man I ment 8bit = 1Byte so I defided it by 8 but that doesn't matter I misunderstood you aswell.



According to their own specs they're using PC1600 also PC3200 wasn't even finished by then.
The highest DDR available at that time was PC2700 or DDR333.

M$ would claim these phony bandwidth's because all the specs stated by M$ on the Xbox1 were phony.
M$ said the Xbox could do 125 million polygon/s, 2,93GFlop/s on the CPU, 80GFlop/s on the GPU, 4GTexel/s and 4GPixel/s of fillrates while in fact the Xbox can only do 10-15 million polygon/s PEAK only done in DOA Ultimate, 800-900MFlop/s on the CPU, 9,32GFlop/s on the GPU, 1,86GTexel/s and 932MPixel/s of fillrates.

Sony and Nintendo however didn't lie about their console specs allthough Sony always get accused of doing it while in fact their PS2 specs with the unveiling are the same as that of the final hardware.

Don't even get me started on the Xbox unveiling GDC2001 where M$ said the Xbox could do this and this is a direct quote from Edge UK:
1 billion polygon/s flatshaded
300 million polygon/s fully lit and fully textured
16 GTexel/s and 4 GPixel/s
100GB/s memory bandwidth

I don't remember that. the highest X-Box specs I remember seeing were:
300 million polygons per sec (flat shaded)
4800 megapixels / 4.8 gigapixels per sec pixel fillrate
4800 megatexels / 4.8 gigatexels per sec texel fillrate

I do remember some speculation about 16 pixel pipelines with 2 TMUs each, though. but nothing about 1 billion flatshaded polygons or 100 GB/sec memory bandwidth (that bandwidth spec is beyond present-day Xbox360 and PS3)

 

[OtakingGX]

I found this link to be interesting:

http://www.us.design-reuse.com/news/news6721.html?PHPSESSID=96be74e67bf2eb341ea78bd49656f318

NEC manufactured Flipper with imbedded DRAM as well as the 1T-SRAM system memory. Perhaps this time around we'll see SRAM instead of DRAM imbedded and more of it...

 

[Guden Oden]

Dude, for the millionth time, it's not DRAM in flipper, it's 1T SRAM.

...Which technically is DRAM for the most part, with integrated SRAM buffers to hide the delays normally associated with DRAM accesses and make it perform (pretty much) like SRAM.

 

[OtakingGX]

Dude, for the millionth time, it's not DRAM in flipper, it's 1T SRAM.

...Which technically is DRAM for the most part, with integrated SRAM buffers to hide the delays normally associated with DRAM accesses and make it perform (pretty much) like SRAM.

I've seen it alternately both ways, on chip 1T-SRAM and embedded DRAM. Now I know which is right.

So since 1T-SRAM was slightly less dense than DRAM, is 1T-SRAM-Q denser than standard embedded DRAM? The supposed IGN specs got me thinking. Since there have been 2 process shrinks since Flipper's 180nm, down to 90nm, how much die space would 88 MB of 1T-SRAM-Q take up? Less than twice Flipper's 3MB of 1T-SRAM by my calculations.

 

[Guden Oden]

So since 1T-SRAM was slightly less dense than DRAM, is 1T-SRAM-Q denser than standard embedded DRAM?

I wouldn't think so. The biggest area in 1T SRAM is definitely taken up by the dynamic memory cells themselves, and any improvement you make to those could be made to standard DRAM as well. AFAIK, the size difference in 1T SRAM-Q is in the additional bits and pieces, logic and SRAM, that standard DRAM does not have. So 1T SRAM-Q is still going to be bigger than DRAM, just not quite as much bigger.