[flagged]
Bubble Memory
21–30 of 30 posts
Re: Bubble Memory
#22Earlier quoted context omitted.
FRAM is also used in all modern MSP430 microntrollers from Texas Instruments. Amazing technology
That reminds me of core memory, which is also nonvolatile and for a long time was the primary memory of many computer systems. I suspect "growing up" with a system where the computer itself is nonvolatile (turn it off, move it, turn it on, it's doing exactly what it was doing when it was turned off) changed the way people looked at computers vs modern systems. It's too bad intel didn't push harder on their optane stu…
Nonvolatile memory has advantages, but also disadvantages.
In a computer that would have only non-volatile memory it would be difficult to ensure that things that must be secret remain secret.
Various events like power failures or software bugs could prevent the erasure of the secrets when they are no longer required.
Total memory encryption, like first introduced in server CPUs by AMD, and then followed by Intel, could solve this problem, but even that depends on the CPU having internal memory that is volatile, so this allows only the reduction of the amount of volatile memory that is needed, not its complete elimination.
Re: Bubble Memory
#23I remember a lot of talk about how transformative bubble memory was going to be circa 1980 and then quit hearing about it.
Indeed.
The bubble memory was doomed by the fact that it had to be made from material that was patterned, by using photolithography or similar means.
Because of this, even if its structure was simpler than that of semiconductor memories, its bit density could not be increased much over that of semiconductor memories and its fabrication technology was not significantly cheaper.
Being much slower than random-access memory, while not having much cost advantage, made it non-competitive.
In contrast, the memories that use a homogeneous recording material with bits defined by the movement of a recording head, in the form of disks or tapes, compensate their slowness by having a much lower price per bit.
Thus bubble memories were too expensive in comparison with HDDs and too slow in comparison with DRAM, so no application remained for them in a computer that used DRAM and HDDs.
Re: Bubble Memory
#24I remember a lot of talk about how transformative bubble memory was going to be circa 1980 and then quit hearing about it.
Indeed. The bubble memory was doomed by the fact that it had to be made from material that was patterned, by using photolithography or similar means. Because of this, even if its structure was simpler than that of semiconductor memories, its bit density could not be increased much over that of semiconductor memories and its fabrication technology was not significantly cheaper. Being much slower than random-access mem…
Flash is patterned. There is talk about patterned surfaces for HDD but who knows if it will ever see the light of day.
Re: Bubble Memory
#25In Patriot Games by Tom Clancy, there is a scene early in the book where Jack Ryan is talking about the laptop he is using to write his book. I don't remember the exact specs but am 100% sure he mentions that it has bubble memory.
I just read the book and it does. I had to look it up when I read it because this was before my time.
Re: Bubble Memory
#26Robert Silverberg's novel "Shadrach In The Furnace", published in the 1970s, had a mention of some data being transported on a "billion-bit bubble chip". In retrospect, that's entertaining in 3 ways: 1) bubble memory didn't go anywhere, and 2) a billion bits is no longer an unthinkable amount of data, 3) solid state memory (which we'll take to include bubble chips here) still hasn't surpassed rotating memory (hard drives, tapes) at least in cost per bit. Maybe someday but not yet.
Re: Bubble Memory
#27I find pretty interesting that the memory is not perfect out of the fab and its defects are coded on its label, hence these defects can be loaded to the device using it as a map, so it can work around these loops while working. Now, this is even true for flash memory, but this is handled at the controller level and its dynamic during its initial "formatting" at the factory, so it's completely hidden from the host unl…
Hard disks used to come with a paper label listing their bad sectors. (They still come with a list, it's just now it is hidden in the firmware like you describe.)
I remember someone writing a rant against having the list in firmware and managed automatically by the drive. If the list was on the host side, your software could route around the bad sectors and minimize the total amount of seek time during a program run. But with the drive managing bad sector redirection, you could never predict read latency since any read could get re-routed to a spare sector by the drive, adding latency outside your control. Everything still became automatic though.
You could buy disk packs with no bad sectors back then if you wanted that ("bit error free"). They cost extra but the premium wasn't all that high. Of course they could still develop bad sectors later.
Re: Bubble Memory
#28Earlier quoted context omitted.
Indeed. The bubble memory was doomed by the fact that it had to be made from material that was patterned, by using photolithography or similar means. Because of this, even if its structure was simpler than that of semiconductor memories, its bit density could not be increased much over that of semiconductor memories and its fabrication technology was not significantly cheaper. Being much slower than random-access mem…
Flash is patterned. There is talk about patterned surfaces for HDD but who knows if it will ever see the light of day.
Which is why flash remains much more expensive than HDDs.
Flash is also much faster than a bubble memory, because it provides random access to blocks, even if a block is read sequentially. Thus flash was positioned in a good spot in a hierarchy of memories where a compromise is made between access speed and cost per bit.
To achieve a similar speed, a bubble memory would have to store a block, e.g. 4 kB, per bubble ring and have a huge number of bubble rings (i.e. billions, to compete with the current flash memories) to which random access would have to be provided by semiconductor ICs handling the multiplexing and demultiplexing of data.
Due to mixing ferromagnetic and semiconductor technologies, it is very unlikely that such a device could be made at an acceptable price.
Re: Bubble Memory
#29Earlier quoted context omitted.
Indeed. The bubble memory was doomed by the fact that it had to be made from material that was patterned, by using photolithography or similar means. Because of this, even if its structure was simpler than that of semiconductor memories, its bit density could not be increased much over that of semiconductor memories and its fabrication technology was not significantly cheaper. Being much slower than random-access mem…
Flash is patterned. There is talk about patterned surfaces for HDD but who knows if it will ever see the light of day.
Flash only got competitive after both HDDs and DRAM scaling slowed, allowing it to catch up, and end up in an interesting position between them.
There are about a dozen upcoming memory technologies with better theoretical headroom waiting in the wings for DRAM and Flash scaling to slow down. In the early 10's it really looked like Flash was about to be replaced, but then Samsung managed to move Flash to the third dimension. Very soon, either DRAM does the same, or it gets replaced by something.
Re: Bubble Memory
#30See also: https://en.wikipedia.org/wiki/Ferroelectric_RAM , which has been used in a few quite popular systems as well (e.g. the PS2 memory card supposedly uses it for some high-rewrite-count operations).
FRAM is also used in all modern MSP430 microntrollers from Texas Instruments. Amazing technology
Very few of the MSP430s actually use FRAM, last I checked -- it's limited in both size and speed. (My understanding is that the FRAM speed is substantially better than Flash speed, but they treat it like SRAM for XIP, with I think two cycle waits up to 25 MHz or something, vs Flash where the expectations for XIP are much lower, so higher clock speeds are supported with more wait states.) The family is split between Flash (the majority) and the FRAM parts.