Hacker News new | past | comments | ask | show | jobs | submit login

>Why is there more floating point and cryptographic performance?

You can infer this to N2 which ARM gave their own results [1], N2 uses SVE2 256bit.

[1] https://community.arm.com/arm-community-blogs/b/architecture...




N2 does not use 256b SVE2, though its cousin Neoverse V1 does. I think there's a very real chance that Grav3 is actually V1, not N2. (N2 uses 128b SVE vectors, as does the Cortex-A710 it's based on.)


Oh YES [1] . I got the two mixed up. I should have doubled checked. So it is V1.

The V1 design is available in both 7nm and 5nm.

Oh well I guess if AWS had it in 5nm they would have at least marketed it as such. So may be it is the same 7nm.

[1] https://images.anandtech.com/doci/16640/Neoverse_Intro_3.png




Join us for AI Startup School this June 16-17 in San Francisco!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: