IBM analog AI chip could give the Nvidia H100 a run for its money
1–10 of 71 posts
Re: IBM analog AI chip could give the Nvidia H100 a run for its money
#2I thinks this type of paradigm shift is what will be needed for the next level of performance for AI. But it also seems like for that to be competitive with current methods, they need to reduce the size by a factor of 2-3 and also make bigger chips.
I just feel like IBM has a track record recently of doing great research but not actually manufacturing anything. Kind of like Google.
Re: IBM analog AI chip could give the Nvidia H100 a run for its money
#3I wonder how many years (if ever) it'll be before it's available for purchase, and I wonder what architecture Nvidia will be on by then - it won't be Hopper.
Re: IBM analog AI chip could give the Nvidia H100 a run for its money
#4The actual nature paper mentioned in the article: https://www.nature.com/articles/s41586-023-06337-5
IBM blog post: https://research.ibm.com/blog/analog-ai-chip-low-power
Also I'd like to mention that those chips are for inference only. You still need GPUs for training.
Re: IBM analog AI chip could give the Nvidia H100 a run for its money
#5I thinks this type of paradigm shift is what will be needed for the next level of performance for AI. But it also seems like for that to be competitive with current methods, they need to reduce the size by a factor of 2-3 and also make bigger chips. I just feel like IBM has a track record recently of doing great research but not actually manufacturing anything. Kind of like Google.
Usually IBM doesn't sell to the kind of HN crowd, rather people happy with Aix, IBM i and z/OS, DB2, cloud for mainframes, own JVM implementations, Java EE servers, offshoring services,...
Some of the research does end in such products, that are outside HN radar, because IBM isn't cool, yet many HN startups won't achieve a legacy like it and still be pumping money like IBM, even for boring business.
Re: IBM analog AI chip could give the Nvidia H100 a run for its money
#6I thinks this type of paradigm shift is what will be needed for the next level of performance for AI. But it also seems like for that to be competitive with current methods, they need to reduce the size by a factor of 2-3 and also make bigger chips. I just feel like IBM has a track record recently of doing great research but not actually manufacturing anything. Kind of like Google.
The closest equivalent Google has is the TPU which is very much a manufactured thing at large scale.
Re: IBM analog AI chip could give the Nvidia H100 a run for its money
#7I thinks this type of paradigm shift is what will be needed for the next level of performance for AI. But it also seems like for that to be competitive with current methods, they need to reduce the size by a factor of 2-3 and also make bigger chips. I just feel like IBM has a track record recently of doing great research but not actually manufacturing anything. Kind of like Google.
Usually IBM doesn't sell to the kind of HN crowd, rather people happy with Aix, IBM i and z/OS, DB2, cloud for mainframes, own JVM implementations, Java EE servers, offshoring services,... Some of the research does end in such products, that are outside HN radar, because IBM isn't cool, yet many HN startups won't achieve a legacy like it and still be pumping money like IBM, even for boring business.
>are outside HN radar, because IBM isn't cool
More like outside people's radar because IBM only sells to big companies.
Re: IBM analog AI chip could give the Nvidia H100 a run for its money
#8I thinks this type of paradigm shift is what will be needed for the next level of performance for AI. But it also seems like for that to be competitive with current methods, they need to reduce the size by a factor of 2-3 and also make bigger chips. I just feel like IBM has a track record recently of doing great research but not actually manufacturing anything. Kind of like Google.
Usually IBM doesn't sell to the kind of HN crowd, rather people happy with Aix, IBM i and z/OS, DB2, cloud for mainframes, own JVM implementations, Java EE servers, offshoring services,... Some of the research does end in such products, that are outside HN radar, because IBM isn't cool, yet many HN startups won't achieve a legacy like it and still be pumping money like IBM, even for boring business.
IBM revenue has been shrinking over the last 10 years. They aren't selling well.
Re: IBM analog AI chip could give the Nvidia H100 a run for its money
#9I thinks this type of paradigm shift is what will be needed for the next level of performance for AI. But it also seems like for that to be competitive with current methods, they need to reduce the size by a factor of 2-3 and also make bigger chips. I just feel like IBM has a track record recently of doing great research but not actually manufacturing anything. Kind of like Google.
Just a laymen here, but if the organic brain is something we're trying to model I always ached for some kind of analog processor for things like neural networks. Op-amps, not logic gates.
(Quick google found this fun hobbyist article of a perceptron built with op-amps: https://www.nutsvolts.com/magazine/article/the_perceptron_ci...)
Re: IBM analog AI chip could give the Nvidia H100 a run for its money
#10"can model up to 17 million parameters"
So about about 1000x away from being useful? Most current models are billions not millions.