Licensing coming to a datacenter near you soon courtesy of Oracle/Broadcom You asked for an alternative to per core now we charge the same per GB of RAM. you have 6TB, that will be $500K per server please.
This already exists on the IBM side for mainframes as you order the hardware and then need licensing to enable the memory you paid for physically.
Intel tried to do something similar in the Sky Lake/Cascade Lake generations by limited memory capacity on lower end chips and requiring otherwise identical but more expensive models to leverage the full capabilities of the hardware.
With CXL and being able to leverage the PCIe bus for additional memory, it will be interesting to see how software companies license that since it will appear as another NUMA node but without any compute attached to it.
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
4 Comments
Back to Article
Threska - Friday, March 22, 2024 - link
Soon memory will be as big as the computer it's plugged into.schujj07 - Friday, March 22, 2024 - link
I would love these in my data center.lorribot - Friday, March 22, 2024 - link
Licensing coming to a datacenter near you soon courtesy of Oracle/BroadcomYou asked for an alternative to per core now we charge the same per GB of RAM. you have 6TB, that will be $500K per server please.
Kevin G - Monday, March 25, 2024 - link
This already exists on the IBM side for mainframes as you order the hardware and then need licensing to enable the memory you paid for physically.Intel tried to do something similar in the Sky Lake/Cascade Lake generations by limited memory capacity on lower end chips and requiring otherwise identical but more expensive models to leverage the full capabilities of the hardware.
With CXL and being able to leverage the PCIe bus for additional memory, it will be interesting to see how software companies license that since it will appear as another NUMA node but without any compute attached to it.