The Looming Battle Over AI Chips
barrons.com
The Looming Battle Over AI Chips
1–10 of 89 posts
Re: The Looming Battle Over AI Chips
#2I just seem to bump into a paywall.
The premise from the title seems plausible, although NVIDIA seems to be catching up again fast.
Re: The Looming Battle Over AI Chips
#3Does anyone have a non-paywall but legitimate link to the story?
Re: The Looming Battle Over AI Chips
#4I just seem to bump into a paywall. The premise from the title seems plausible, although NVIDIA seems to be catching up again fast.
I was impressed enough with their CES demo to buy some stock. Isn’t the Volta at 15E9 transistors? It’s at the point only the big boys can play in that field due to fab costs, unless it’s disrupted due to some totally new architecture.
First time on HN I can read a paywalled article, as I have a Barron’s print subscription.
Re: The Looming Battle Over AI Chips
#5I just seem to bump into a paywall. The premise from the title seems plausible, although NVIDIA seems to be catching up again fast.
use the web button at the top - worked for me
Re: The Looming Battle Over AI Chips
#6Non paywall link: https://outline.com/FucjTm
Re: The Looming Battle Over AI Chips
#7Pretty soft article. General purpose processors no longer have the performance or energy efficiency that’s possible at scale. Further, if you have a choice to control your own destiny, why wouldn’t you choose to?
Re: The Looming Battle Over AI Chips
#8It would be interesting to try emulate a many-core CPU as a GPU program and then run an OS on it.
This sounds like a dumb idea, and it probably is. But consider a few things:
* NVIDIA GPUs have exceptional memory bandwidth, and memory can be a slow resource on CPU based systems (perhaps limited by latency more than bandwidth)
* The clock speed isn't that slow, it's in the GHz. Still one's clocks per emulated instruction may not be great.
* You can still do pipelining, maybe enough to get the clocks-per-instruction down.
* Branch prediction can be done with ample resources. RNN based predictors are a shoe-in.
* communication between "cores" should be fast
* a many-core emulated CPU might not do too bad for some workloads.
* It would have good SIMD support.
Food for thought.
Re: The Looming Battle Over AI Chips
#9Nvidia will almost certainly respond to this challenge with it's own specialized machine learning and inference chips. It's probably what Google, Facebook and others hope. Forcing Nvidia to work harder is enough for them.
Developing a new high performance microarchitecture for GPU or CPU is complex task. A new clean sheet design architecture takes 5-7 years even for teams that have been doing it constantly for decades in Intel, AMD, ARM or Nvidia. This includes optimizing the design into process technology, yield, etc. and integrating memory architectures. Then there is economies of scale and price points.
Nvidia's Volta microarchitecture design started 2013, launch was December 2017
AMD's zen CPU architecture design started 2012 and CPU was out 2017.
Re: The Looming Battle Over AI Chips
#10It would be interesting to try emulate a many-core CPU as a GPU program and then run an OS on it. This sounds like a dumb idea, and it probably is. But consider a few things: * NVIDIA GPUs have exceptional memory bandwidth, and memory can be a slow resource on CPU based systems (perhaps limited by latency more than bandwidth) * The clock speed isn't that slow, it's in the GHz. Still one's clocks per emulated instruct…
How would that work when the individual cores have to be running the same instructions at a time? Where’s the ability to emulate a CPU come from?