31–40 of 266 posts
Earlier quoted context omitted.
There's an interesting rumor that says AMD is building an ARM SoC for OEMs...
Didn't they build the architecture and then chuck it?
Earlier quoted context omitted.
Like Amazon? You know you can get an ARM server there any day of the week for extremely reasonable prices? Edit: to clarify, I mean on AWS, not from the Amazon store.
Reasonable is relative to what you want to do: Cloud instances are only cheap if your machines are usually idle, and you overprovisioned your datacenter massively. Cloud instances are only cheap if there is no great amount of output/input data to transfer like simulation results or large model input datasets. Cloud instances are only cheap if you don't need assurances about locality or security for compliance. Cloud…
Earlier quoted context omitted.
Like Amazon? You know you can get an ARM server there any day of the week for extremely reasonable prices? Edit: to clarify, I mean on AWS, not from the Amazon store.
Reasonable is relative to what you want to do: Cloud instances are only cheap if your machines are usually idle, and you overprovisioned your datacenter massively. Cloud instances are only cheap if there is no great amount of output/input data to transfer like simulation results or large model input datasets. Cloud instances are only cheap if you don't need assurances about locality or security for compliance. Cloud…
Earlier quoted context omitted.
There's an interesting rumor that says AMD is building an ARM SoC for OEMs...
If I were them I wouldn't even bother with anything pre-Arm v9. That's going to draw all the hype, especially when Apple announces the Arm v9-based M2 next year. And then I'm sure most sheep-like OEMs will say "Oh, we want THAT, too. Where is it - we want it yesterday!" But AMD won't be able to provide one too soon, because they would've gone all in on Arm v8, and they'd want to squeeze at least a couple of generatio…
Earlier quoted context omitted.
The removing of 32bit support in Catalina was definitely a bad thing for many, who are using x86-Macs, but for someone interesting in an ARM-based Mac, shouldn't play a role.
> shouldn't play a role. Until it does. Some future MacOS may need support of some new architecture feature, then it'll be "better buy an Arm13 mac if you want to run MacOS 2023!". Apple doesn't have a very good track record about supporting their own old hardware in new MacOS releases. Several iMacs and MacMinis come to mind. Their past behaviour sets a benchmark for their future behaviour, and since there are no re…
Earlier quoted context omitted.
Like Amazon? You know you can get an ARM server there any day of the week for extremely reasonable prices? Edit: to clarify, I mean on AWS, not from the Amazon store.
If I can't get a machine for local development I wouldn't care personally. I like the idea of many many threads as I work a lot with data, but i need something like a PC to try things on. Also, don't really like vendor lock-in.
I thought it would be horrible, but after a brief adjustment period it turned out to be okay-ish for my current work.
These things look awesome, but are pretty expensive, still. I'd love to put an ARM server in my homelab, but the price range between 100$ (RPi & Co) and 10000$ (enterprise server) seems pretty empty right now :/
There are several multi-board RPi&Co solutions. Pine64 has some interesting offerings in this space.
Pine64 SOPINE Clusterboard https://www.pine64.org/clusterboard/
Earlier quoted context omitted.
There's an interesting rumor that says AMD is building an ARM SoC for OEMs...
Didn't they build the architecture and then chuck it?
For a little while there was one partner who used it for Gluster ( or similar ) storage nodes.
It fit into the model of Arm processors that were performant enough to be the glue between hard disks or flash and a reasonably fast network. But after the PCI lanes were all dispatched there wasn't a lot of compute for applications on top.
These things look awesome, but are pretty expensive, still. I'd love to put an ARM server in my homelab, but the price range between 100$ (RPi & Co) and 10000$ (enterprise server) seems pretty empty right now :/
You can get SolidRun HoneyComb[0] for ~$1000, it has 16 cores with supposedly reasonable performance. [0] https://www.solid-run.com/arm-servers-networking-platforms/h...
