News for hackers. Stuff that matters.

A comment on An inside look at the custom CPUs in Tesla's Dojo Supercomputer. Parent comment

Re:An inside look at the custom CPUs in Tesla's Dojo Superco... by vlovich123 on Friday August 20, 2021 @09:08PM (#28253151)
Moore’s law is quite dead. Transistor density isn’t doubling. We’re still getting speed increases due to architectural improvements, but transistor density is capping out because thermals are a problem. That’s why you see these massive wafer designs and they’re not shrinking.
[ Parent | on HN ]
Re:An inside look at the custom CPUs in Tesla's Dojo Superco... by pabs3 on Friday August 20, 2021 @09:46PM (#28253318)
Both TSMC and Intel have transistor density increases on their process roadmaps, although they definitely aren't doubling.
[ Parent | on HN ]
Re:An inside look at the custom CPUs in Tesla's Dojo Superco... by WoodenChair on Friday August 20, 2021 @09:18PM (#28253199)
> Transistor density isn’t doubling.

It pretty much continues to double: https://en.m.wikipedia.org/wiki/Transistor_count#/media/File...

[ Parent | on HN ]
Re:An inside look at the custom CPUs in Tesla's Dojo Superco... by Baeocystin on Friday August 20, 2021 @09:44PM (#28253309)
Raw transistor count isn't the same as density.
[ Parent | on HN ]
Re:An inside look at the custom CPUs in Tesla's Dojo Superco... by WoodenChair on Friday August 20, 2021 @10:24PM (#28253539)
Sure, but if you look at the raw transistor count of a series of similarly sized dies (take Apple's A series for example), it holds up. It only doesn't hold up if you look at Intel the last 5 years. If you look at series' made on TSMC or Samsung, it holds up.
[ Parent | on HN ]
Re:An inside look at the custom CPUs in Tesla's Dojo Superco... by smolder on Saturday August 21, 2021 @04:29AM (#28255243)
If you look at CPU performance relative to density as it has progressed over the last few decades, there's a clear decline in speed improvement. Denser only means faster to a point, regardless of Intel's process update failures.
[ Parent | on HN ]
Re:An inside look at the custom CPUs in Tesla's Dojo Superco... by WoodenChair on Saturday August 21, 2021 @03:57PM (#28260043)
Not sure what you’re replying to. The statement I’m replying to didn’t say anything about performance. It said “ Transistor density isn’t doubling.”
[ Parent | on HN ]
Re:An inside look at the custom CPUs in Tesla's Dojo Superco... by smolder on Monday August 23, 2021 @12:25AM (#28272326)
I have always looked at Moore's "law" as a proxy for performance, so I felt it was relevant, if tangential.
[ Parent | on HN ]
Re:An inside look at the custom CPUs in Tesla's Dojo Superco... by chrisseaton on Friday August 20, 2021 @10:17PM (#28253492)
Moore’s law was about count, not density.
[ Parent | on HN ]
Re:An inside look at the custom CPUs in Tesla's Dojo Superco... by AussieWog93 on Friday August 20, 2021 @10:43PM (#28253651)
I mean, strictly speaking, you're technically correct. Informally, though, it's a proxy for transistor density.
[ Parent | on HN ]
Re:An inside look at the custom CPUs in Tesla's Dojo Superco... by shadilay on Friday August 20, 2021 @11:08PM (#28253789)
It was about cost. https://hasler.ece.gatech.edu/Published_papers/Technology_ov...
[ Parent | on HN ]
Re:An inside look at the custom CPUs in Tesla's Dojo Superco... by jhgb on Saturday August 21, 2021 @01:07AM (#28254376)
Yes, count for optimum cost per transistor. So perhaps GP's statement was incomplete but not wrong.
[ Parent | on HN ]