View Single Post
Old 11-16-2007, 11:38 AM   #22
NatCh
Gizmologist
NatCh ought to be getting tired of karma fortunes by now.NatCh ought to be getting tired of karma fortunes by now.NatCh ought to be getting tired of karma fortunes by now.NatCh ought to be getting tired of karma fortunes by now.NatCh ought to be getting tired of karma fortunes by now.NatCh ought to be getting tired of karma fortunes by now.NatCh ought to be getting tired of karma fortunes by now.NatCh ought to be getting tired of karma fortunes by now.NatCh ought to be getting tired of karma fortunes by now.NatCh ought to be getting tired of karma fortunes by now.NatCh ought to be getting tired of karma fortunes by now.
 
NatCh's Avatar
 
Posts: 11,615
Karma: 929550
Join Date: Jan 2006
Location: Republic of Texas Embassy at Jackson, TN
Device: Pocketbook Touch HD3
Quote:
Originally Posted by nekokami View Post
I think the idea is to use static RAM for the working memory of the CPU... I am guessing it would be slower than dynamic RAM, but it would save the state when the CPU is not powered, so when power returns, one wouldn't have to load the OS again. Sort of. The CPU itself has registers, and they would lose their contents without power. Apart from the expense of creating a CPU that would use static memory for its registers (design, fabrication, etc.) it would probably be too slow to be workable. But the contents of the registers might be saved out to a special static memory module on power-off.

I only know enough about this level of hardware to be dangerous, though. Someone else will probably be able to point out why this wouldn't work.
Sounds like exactly the right track to me, nekokami, I don't have any background in CPU design though, and my semiconductor days are well behind me, but I still think you've got it pretty close. The only thing I'd point out is that Flash Memory response times are pretty quick these days, perhaps not yet quick enough but ....
NatCh is offline   Reply With Quote