A team of researchers including University of Massachusetts Amherst engineers have proven that their analog computing device, called a memristor, can complete complex, scientific computing tasks while bypassing the limitations of digital computing.
Many of today’s important scientific questions—from nanoscale material modeling to large-scale climate science—can be explored using complex equations. However, today’s digital computing systems are reaching their limit for performing these computations in terms of speed, energy consumption and infrastructure.
nopanicitsmechanic on
I can’t even understand what they are saying but I’m so grateful to hear from this.
I still can’t understand why I’m waiting in front of my pc like 30 years ago if the new one has multiple times faster processors and memory.
Hope this makes it to my desktop one day.
ceelogreenicanth on
This is a good video on what is happening and how they would be useful to modern programming
Basically instead of running all the complex vector calculations using piece wise executions, you can run them directly in tandem with stored states in an analog chip. The states and the computations are the same and they can all be run in parallel. This would have a massive impact on AI which uses a lot of vector calculations.
Franklin_le_Tanklin on
I feel like we need a better dialogue about analog.
universalslab on
I have read the article in Science mag and it is very good.
PMzyox on
ROFL I literally was questioning my dad who worked on the first digital modulation of analog signals if they ever considered this very fact. He didn’t seem to even understand my ask. This is nuts.
Edit: I wish I had gone into this field. It’s an incredible time to be alive
Leave A Reply
Du musst angemeldet sein, um einen Kommentar abzugeben.
6 Kommentare
A team of researchers including University of Massachusetts Amherst engineers have proven that their analog computing device, called a memristor, can complete complex, scientific computing tasks while bypassing the limitations of digital computing.
Many of today’s important scientific questions—from nanoscale material modeling to large-scale climate science—can be explored using complex equations. However, today’s digital computing systems are reaching their limit for performing these computations in terms of speed, energy consumption and infrastructure.
I can’t even understand what they are saying but I’m so grateful to hear from this.
I still can’t understand why I’m waiting in front of my pc like 30 years ago if the new one has multiple times faster processors and memory.
Hope this makes it to my desktop one day.
This is a good video on what is happening and how they would be useful to modern programming
https://m.youtube.com/watch?v=LMuqWQcuy_0&pp=ygUbYWlhbm9tZXRyeSBhbmFsb2cgY29tcHV0aW5n
Basically instead of running all the complex vector calculations using piece wise executions, you can run them directly in tandem with stored states in an analog chip. The states and the computations are the same and they can all be run in parallel. This would have a massive impact on AI which uses a lot of vector calculations.
I feel like we need a better dialogue about analog.
I have read the article in Science mag and it is very good.
ROFL I literally was questioning my dad who worked on the first digital modulation of analog signals if they ever considered this very fact. He didn’t seem to even understand my ask. This is nuts.
Edit: I wish I had gone into this field. It’s an incredible time to be alive