11–20 of 347 posts
Oof. Double-precision is only 2.5x better, which is less impressive than 20x for float. I still haven't found anything more cost-effective for double precision data processing (cost + dev time) than a rack full of used Xeons...
Oof. Double-precision is only 2.5x better, which is less impressive than 20x for float. I still haven't found anything more cost-effective for double precision data processing (cost + dev time) than a rack full of used Xeons...
The double-precision number probably best represents the generational improvement. The 20x 32-bit floating point improvement is probably achieved by comparing doing full FP32 calculations on the previous generation vs doing TF32 calculations on Ampere. This would not be an apple-to-apple comparison as the TF32 result is less precise. That said, it is probably not terribly important for deep learning at least, given t…
Considering how big the die is (826mm^2 @ TSMC 7nm) and how many transistors there are, they really must have beefed up the TensorCores much more than the general compute units.
Oof. Double-precision is only 2.5x better, which is less impressive than 20x for float. I still haven't found anything more cost-effective for double precision data processing (cost + dev time) than a rack full of used Xeons...
I'm curious: why exactly do you need double precision digits? Not dismissing, just wondering what kind of application needs it.
I guess people do store intermediate results in floats in order to take advantage of GPU acceleration. However, once you do that, you have to be careful in your programming and pay a lot more attention to underflow, overflow, and numerical accuracy. People who write scientific software usually also aren't experts in numerical analysis. Even if the code you write reliably works with floats, the library you use might not be. It's just a huge pain to make sure everything is accurate.
Oof. Double-precision is only 2.5x better, which is less impressive than 20x for float. I still haven't found anything more cost-effective for double precision data processing (cost + dev time) than a rack full of used Xeons...
I'm curious: why exactly do you need double precision digits? Not dismissing, just wondering what kind of application needs it.
I'm confused. Is there any relationship between the recent Ampere Arm64 servers ( https://news.ycombinator.com/item?id=22475036 ) and Nvidia's "Ampere Architecture", or is it just a case of them using the same name?
They're both named after the famous mathematician and physicist. https://en.wikipedia.org/wiki/Andr%C3%A9-Marie_Amp%C3%A8re
I'm confused. Is there any relationship between the recent Ampere Arm64 servers ( https://news.ycombinator.com/item?id=22475036 ) and Nvidia's "Ampere Architecture", or is it just a case of them using the same name?
I'm confused. Is there any relationship between the recent Ampere Arm64 servers ( https://news.ycombinator.com/item?id=22475036 ) and Nvidia's "Ampere Architecture", or is it just a case of them using the same name?
If someone thinks the question is stupid or not doesn't mean that a downvote is warranted. (nor an upvote, answer the question and move on.)
To answer though; it's just a coincidence, as you might already know Nvidia uses famous scientists (especially in the field of electricity) as the names of their microarchitectures.
* Volta (Alessandro Volta, inventor of the electric battery)
* Tesla (inventor/designer of A/C current)
* Maxwell (James Clerk Maxwell, founder of electromagnetic radiation)
* Pascal (Blaise Pascal, lots of science around "pressure", arguably his work led to the creation of vacuum tubes used in early computers)
Ampere (from André-Marie Ampère, who lent his name to his discovery and classification of "amps") is just an electrical scientists name.
Coincidentally a new company founded in 2017 decided that it was a good name for them, and thus the confusion.