from Hacker News

AWS Graviton 3 Instances

by Trisell on 11/30/21, 5:16 PM with 110 comments

  • by ghshephard on 11/30/21, 5:36 PM

    So - for those deeper into security - is this useful?

    "Graviton3 processors also include a new pointer authentication feature that is designed to improve security. Before return addresses are pushed on to the stack, they are first signed with a secret key and additional context information, including the current value of the stack pointer. When the signed addresses are popped off the stack, they are validated before being used. An exception is raised if the address is not valid, thereby blocking attacks that work by overwriting the stack contents with the address of harmful code. We are working with operating system and compiler developers to add additional support for this feature, so please get in touch if this is of interest to you"

  • by ksec on 11/30/21, 7:40 PM

    >Graviton3 will deliver up to 25% more compute performance and up to twice as much floating point & cryptographic performance. On the machine learning side, Graviton3 includes support for bfloat16 data and will be able to deliver up to 3x better performance.

    >First in the cloud industry to be equipped with DDR5 memory.

    Quite hard to tell whether this is Neoverse V1 or N2. Since the description fits both . But this SVE extensions will move a lot of workload that previously wont suitable for Graviton 2

    Edit: Judging from Double floating point performance it should be N2 with SVE2. Which also means Graviton 3 will be ARMv9 and on 5nm. No wonder why TSMC doubled their 5nm expansion spending. It will be interesting to see how they price G3 and G2. And much lowered priced G2 instances will be very attractive.

  • by qbasic_forever on 11/30/21, 7:31 PM

    Where are Google and Azure with ARM instances? It's been nothing but crickets for years now... this is starting to get silly that their customers can't at least start getting workloads on a different architecture, nevermind get better performance per dollar, etc. too. The silence is deafening.

  • by talawahtech on 11/30/21, 5:25 PM

    I was wondering how they were going to manage the fact that AMDs Zen3 based instances would likely be faster than Graviton2. Color me impressed. AWS' pace of innovation is blistering.

  • by amelius on 11/30/21, 7:52 PM

    I really hate it that big companies are rolling their own CPU now. Soon, you're not a serious developer if you don't have your own CPU. And everybody is stuck in some walled garden.

    I mean, it's great that the threshold to produce ICs is now lower, but is this really the way forward? Shouldn't we have separate CPU companies, so that everybody can benefit from progress, not only the mega corporations?

  • by haukem on 11/30/21, 6:24 PM

    Does Graviton3 use the Neoverse V1? The Graviton2 used the Neoverse N1.

    The features listed here match the core: https://developer.arm.com/ip-products/processors/neoverse/ne...

    The N2 misses the bfloat, but it could be that the ARM marketing named it differently: https://developer.arm.com/ip-products/processors/neoverse/ne...

  • by Alex3917 on 11/30/21, 5:36 PM

    How long until we get T5g with Graviton3?

  • by kloch on 12/1/21, 2:22 AM

    DDR5? Can't wait to see how the memory bandwidth performs. I have a project that is memory bandwidth limited on c6gd instances.

  • by lostmsu on 11/30/21, 7:42 PM

    Any benchmarks? I'd like to see Geekbench 5 results from a full-sized one socket instance.

  • by givemeethekeys on 11/30/21, 9:20 PM

    Side-note: Polly's intonation makes for a fairly confusing listening session.

  • by sabujp on 11/30/21, 8:08 PM

    yeah signed stack pointers is a thing since at least 2017 : https://lwn.net/Articles/718888/

  • by 2-718-281-828 on 12/1/21, 9:53 AM

    are ARM (Advanced RISC Machine) and Arm the same?

  • by aclelland on 11/30/21, 6:35 PM

    So that's the c6g and c7g but x86 instances are still on c5. Will AWS ever release an x86 computing instance again or is this just a sign that x86 has reached peak performance on AWS?

  • by jfbaro on 11/30/21, 6:06 PM

    This seems to be a good fit Lambda as well. Looking forward to seeing more information about the CHIP design and capabilities.