This is all well and good, but how does it even matter? We can only even see one, let alone work with it, if we worked at some particular division of google. This isn't consumer, pro-sumer, or commercial, it's in house only.
So they're basically saying that they have a new CPU for us to rent and isn't this wonderful...
Forgive me if I am recalling incorrectly, but it seemed to me that in years gone by, companies would be very happy to talk about their new products, telling you why it was awesome instead of just being paid to say that it's awesome.
It's literally the same as with AWS Graviton. You can use them directly, when running VMs on the Google Cloud, or indirectly by using higher level services that run on those VMs. Obviously, this is only consumer for a very limited user circle, but going by Gravitons success it will be in wide use by enterprises.
If you are talking about running it in your own data center, AWS at least has the option the run individual servers or pre build rack units locally, including using Graviton. Quick google says Google might have something similar, but I personally have no experience with it.
Another wave of lies? EPYC has already been shown beating all ARM designs including Nvidia's pompous superchip, sometimes by such a huge margin that it's embarrassing. No one is stupid. Stop lying, Google.
In some cases clients can work within the limitations and problems of the Arm design. But I agree that it's not the best option, especially with zen5 being released soon
You have to focus on just the EPYC 9554 (64 cores) and 9654 (96 cores) as the nearest points of comparison. However, also keep in mind that the GPTshop.ai CPU is powering both CPU and RAM on about 250 W, whereas those EPYC CPUs are using up to 360 W for just the CPU, alone.
It strikes me as odd that you think Google would intentionally pick an inferior CPU. Google's only incentive is to maximize perf/W. As long as absolute performance is reasonably competitive, you can more than make up for any performance deficit if your application scales.
We’ve updated our terms. By continuing to use the site and/or by logging into your account, you agree to the Site’s updated Terms of Use and Privacy Policy.
Facebook
Twitter
RSS
15 Comments
Back to Article
ballsystemlord - Tuesday, April 9, 2024 - link
This is all well and good, but how does it even matter? We can only even see one, let alone work with it, if we worked at some particular division of google. This isn't consumer, pro-sumer, or commercial, it's in house only.bubblyboo - Tuesday, April 9, 2024 - link
1st source, last sentence of 1st paragraph:"Axion delivers industry-leading performance and energy efficiency and will be available to Google Cloud customers later this year."
ballsystemlord - Wednesday, April 10, 2024 - link
So they're basically saying that they have a new CPU for us to rent and isn't this wonderful...Forgive me if I am recalling incorrectly, but it seemed to me that in years gone by, companies would be very happy to talk about their new products, telling you why it was awesome instead of just being paid to say that it's awesome.
autarchprinceps - Wednesday, April 10, 2024 - link
It's literally the same as with AWS Graviton. You can use them directly, when running VMs on the Google Cloud, or indirectly by using higher level services that run on those VMs.Obviously, this is only consumer for a very limited user circle, but going by Gravitons success it will be in wide use by enterprises.
autarchprinceps - Wednesday, April 10, 2024 - link
If you are talking about running it in your own data center, AWS at least has the option the run individual servers or pre build rack units locally, including using Graviton. Quick google says Google might have something similar, but I personally have no experience with it.Terry_Craig - Thursday, April 11, 2024 - link
Extremely limited use.mode_13h - Monday, April 15, 2024 - link
Why do you find this so threatening?Blastdoor - Wednesday, April 10, 2024 - link
Is there any information about who is fabricating this for them?seems like this is an example of the kind of business that Intel needs to win
Terry_Craig - Thursday, April 11, 2024 - link
Another wave of lies? EPYC has already been shown beating all ARM designs including Nvidia's pompous superchip, sometimes by such a huge margin that it's embarrassing. No one is stupid. Stop lying, Google.Dante Verizon - Saturday, April 13, 2024 - link
In some cases clients can work within the limitations and problems of the Arm design. But I agree that it's not the best option, especially with zen5 being released soonmode_13h - Monday, April 15, 2024 - link
With 64k pages, performance looks pretty competitive.https://www.phoronix.com/review/aarch64-64k-kernel...
You have to focus on just the EPYC 9554 (64 cores) and 9654 (96 cores) as the nearest points of comparison. However, also keep in mind that the GPTshop.ai CPU is powering both CPU and RAM on about 250 W, whereas those EPYC CPUs are using up to 360 W for just the CPU, alone.
It strikes me as odd that you think Google would intentionally pick an inferior CPU. Google's only incentive is to maximize perf/W. As long as absolute performance is reasonably competitive, you can more than make up for any performance deficit if your application scales.
mode_13h - Monday, April 15, 2024 - link
Phoronix also found that using Clang instead of GCC yielded an overall improvement of 8.6%.https://www.phoronix.com/review/nvidia-gh200-compi...
Google prefers Clang/LLVM, due to its superior static analysis (which is useful for finding security vulnerabilities).
charlesg - Thursday, April 11, 2024 - link
"Don't be evil" has turned into "Let's rule the world".google and alphabet should scare you.
GeoffreyA - Saturday, April 13, 2024 - link
I knew when they changed it to "Do the right thing" that something was fishy.mode_13h - Monday, April 15, 2024 - link
It's cute that Google's answer to Amazon's Graviton is called Axion. Now, we just need Microsoft to announce a cloud CPU called Muon or something.