Jim Keller on AI, RISC-V, Tenstorrent’s Move to Edge IP

Re:Jim Keller on AI, RISC-V, Tenstorrent’s Move to Edge IP by als0 on Tuesday June 13, 2023 @05:47PM (#36317972)

> The only counter for this is if x86 can crank performance per $TCO so far that the non-x86 branch can't compete in business terms, which has historically been the issue with ARM.

If we take AWS for example, isn't the performance per TCO better of an Arm-based Graviton instance better than x86? I don't think the historical issue you cite represents the future.

[ Parent | on HN ]

Re:Jim Keller on AI, RISC-V, Tenstorrent’s Move to Edge IP by cjsplat on Tuesday June 13, 2023 @06:10PM (#36318282)

Impossible to know from the outside.

We know what they are selling it for, but that isn't the same.

True TCO needs to include the cost to develop the chip - after all, that is folded into the x86 price.

If you assume that the Graviton project is $250M per chip design for the 3 iterations, and the online estimates of 1 million chips is accurate, then you need to add about $750 per CPU, beyond the probably $250 per chip fab'ed and packaged.

$1000 per chip gets you a lot of x86 horsepower.

[ Parent | on HN ]

Re:Jim Keller on AI, RISC-V, Tenstorrent’s Move to Edge IP by nl on Wednesday June 14, 2023 @12:07AM (#36321313)

$250M seems a massive overestimate given that the majority of the design is done by ARM and licensed from them.

[ Parent | on HN ]

Re:Jim Keller on AI, RISC-V, Tenstorrent’s Move to Edge IP by cjsplat on Wednesday June 14, 2023 @03:46PM (#36331540)

For example see :

https://www.semianalysis.com/p/the-dark-side-of-the-semicond...

I think you are overestimating the value and amount of help from ARM, especially in the more recent Graviton generations, but of course I don't know Amazon's actual chip cost profile.

[ Parent | on HN ]