Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

IBM scientists say radical new ‘in-memory’ architecture will speed up computers

kurzweilai.net

Post reply on HN
Print view View original

11–20 of 138 posts

Re: IBM scientists say radical new ‘in-memory’ architecture will speed up computers

#11

Post by Illniyar »

otakucode wrote: post #2

This is the promise of memristors. Despite innumerable articles being written about neuromorphic architectures like they'll be something miraculous, this ability to change from functioning as a bit of memory to being a bunch of functional logic on the fly at the speed of a memory read? That's going to be crazy. It will open up possibilities that we probably can't even imagine right now. I've never understood why peop…

I thought memristors is RAM that doesn't lose state when losing electricity.

Is this article about memristors? That wasn't clear. Can memristors perform computations?

Re: IBM scientists say radical new ‘in-memory’ architecture will speed up computers

#12

Post by deepsun »

otakucode wrote: post #2

This is the promise of memristors. Despite innumerable articles being written about neuromorphic architectures like they'll be something miraculous, this ability to change from functioning as a bit of memory to being a bunch of functional logic on the fly at the speed of a memory read? That's going to be crazy. It will open up possibilities that we probably can't even imagine right now. I've never understood why peop…

Maybe for the same reason as people don't get more excited about quantum computers -- they can replace basically everything as well, yet we don't see them around.

Re: IBM scientists say radical new ‘in-memory’ architecture will speed up computers

#14

Post by naasking »

amelius wrote: post #6

What they describe sounds like a pipeline architecture or a systolic array, or a network of interconnected computers. None of these are new concepts from an architectural point of view, but the actual dimensioning could be new.

> None of these are new concepts from an architectural point of view, but the actual dimensioning could be new.

Depends what you mean by "architecture". I disagree that a network of computers is comparable to colocating a computing unit with its memory. There are orders of magnitude in difference in communication costs and failure modes, so at some point you just have to acknowledge that the models are fundamentally different, and should be treated as such.

Certainly they are Turing equivalent, so they aren't more "powerful" in a computability sense, we but what's more interesting is the tradeoffs in computational complexity.

Re: IBM scientists say radical new ‘in-memory’ architecture will speed up computers

#15

Post by PeachPlum »

Sounds very much like Content Addressable Parallel Processors such as the one that powered the Staran air traffic control system.

Caxton Foster's book is the major text I know on the subject.

https://en.wikipedia.org/wiki/Content_Addressable_Parallel_P...

Re: IBM scientists say radical new ‘in-memory’ architecture will speed up computers

#17

Post by ericd »

Illniyar wrote: post #11
otakucode wrote: post #2

This is the promise of memristors. Despite innumerable articles being written about neuromorphic architectures like they'll be something miraculous, this ability to change from functioning as a bit of memory to being a bunch of functional logic on the fly at the speed of a memory read? That's going to be crazy. It will open up possibilities that we probably can't even imagine right now. I've never understood why peop…

I thought memristors is RAM that doesn't lose state when losing electricity. Is this article about memristors? That wasn't clear. Can memristors perform computations?

I'm not an expert on this, but I think you might be thinking of nvram/non volatile RAM, "memristor" is a portmanteau of memory and transistor, so I'd expect that they have properties of both.

Re: IBM scientists say radical new ‘in-memory’ architecture will speed up computers

#18

Post by paulddraper »

deepsun wrote: post #12
otakucode wrote: post #2

This is the promise of memristors. Despite innumerable articles being written about neuromorphic architectures like they'll be something miraculous, this ability to change from functioning as a bit of memory to being a bunch of functional logic on the fly at the speed of a memory read? That's going to be crazy. It will open up possibilities that we probably can't even imagine right now. I've never understood why peop…

Maybe for the same reason as people don't get more excited about quantum computers -- they can replace basically everything as well, yet we don't see them around.

And of course, people do get excited about quantum computers...millions and millions of $ a year excited.

But yeah, their mostly non-existance is exactly why people aren't more existed.

Re: IBM scientists say radical new ‘in-memory’ architecture will speed up computers

#19

Post by ChuckMcM »

deepsun wrote: post #12
otakucode wrote: post #2

This is the promise of memristors. Despite innumerable articles being written about neuromorphic architectures like they'll be something miraculous, this ability to change from functioning as a bit of memory to being a bunch of functional logic on the fly at the speed of a memory read? That's going to be crazy. It will open up possibilities that we probably can't even imagine right now. I've never understood why peop…

Maybe for the same reason as people don't get more excited about quantum computers -- they can replace basically everything as well, yet we don't see them around.

If you open the box their wave state collapses and they are either excited or bored. :-)

(ok that was a long way to make a Schrödinger joke) There are a lot of people who are very excited about Quantum computers and working on them, as they get more 'real' people on the fence move over, etc. I watched this on a smaller scale with 3D printers, as only a few people were excited about them and then as they demonstrated more and more interesting things the wave of excited people expanded outward from that core.

Re: IBM scientists say radical new ‘in-memory’ architecture will speed up computers

#20

Post by austin_y »

dTal wrote: post #9
xellisx wrote: post #5

Earlier quoted context omitted.

Well with most claims that generalize computing power, such as the title of this, it's mostly aimed at something more specialized. "The researchers believe this new prototype technology will enable ultra-dense, low-power, and massively parallel computing systems that are especially useful for AI applications." So it seems that would benefit AI/Machine Learning more than GP processing, from that statement.

I'm not so sure. CPUs are stupidly fast, now - the bottleneck is virtually always the time it takes to move data in and out of memory. What if, instead of trying to bring the data to the calculation, you brought the calculation to the data? You could speed up everything . Fun to think about: in this scenario, the main job of an "optimizing compiler" would be to organize things spatially so that, as a calculation move…

Brings to mind images of Conway's Game of Life, with computations moving about a grid of memory as they create and destroy new bits of data.
Post reply on HN