[DaleDe]

Originally Posted by NatCh

I think we have a semantic confusion going on here: ROM (or Read Only Memory), flash (and yes, it does exist, Palm, for example, has had it for years) or otherwise, is for storing information that doesn't change very often. It's not where you'd want to do calculations. In fact, since it's memory, all it can really do is store data.

Actually it can store Programs as well as data (to be more precise) and with the technology pioneered by Palm it can even be used when a program is running. This technology is called 'run in place'. Without this technology the program had to be copied into RAM to run it.

True ROM could only be written into once and was then static. Later versions allowed the ROM to be re-written but only be erasing and re-writing the whole thing. A limited number or re-writes were permitted. The latest ROM is called Flash ROM and can be written by updating individual information without redoing the whole thing. However, as compared to RAM there is a speed penalty for this. This sort of ROM is used in Flash Drives such as CF cards and SD cards.

What you're talking about sounds interesting, though, yvanleterrible, kind of like a distributed processor, with static rather than dynamic memory, so that its state is saved even without power, and it can pick right back up where it left off when the power comes back on.

This is done may several devices today, again most notably by Palm and more recently by Windows Mobile. Generally there is a scratch area in RAM for temporary calculations but it does appear to allow you to pick back up (almost) from where you left off. Again there is a performance penalty for this.

Back when I was designing my own e-ink reader (totally dreamware, but I thought about it a lot), I envisioned a system that would use static ram to boot, run a single function, then shut down. If it doesn't have to load a full OS then it could be very fast booting indeed.

Static RAM is good but you really only need it for keeping temporary stuff. The boot can be done from ROM and the OS can run from ROM. This is generally the rule today. 'Run in place' with judicious use of discipline in programming can make this pretty fast. Unfortunately more Linux systems do not have this technology (but some do)

For instance, I saw the "next page button" booting the device, running a routine to display a page, and then calculating the next page for display and storing it in a static buffer before shutting back down. The idea I had was to have the current, previous and next pages all stored in static buffers all the time (when they weren't being generated, anyway), or to have the file processed upon loading so that a book would be pre-generated as "pages" and stored that way, so that all the Next button would have to do is turn on, load the next page, and shut back down. All the pages would effectively be memory spaces and would just have to be transfered to the display, which would also kinda be a memory space. I wanted to take advantage of that to capture handwritten notes.

I don't think I'm explaining it clearly, but hopefully the idea is coming through somehow.

There is room for this sort of thing and it is being done on eBook reading devices. If the book format is page oriented and can be pre-paged this is fairly simple. Not all book formats are pre-paged.

Dale