Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
JacobiX
on Sept 21, 2023
|
parent
|
context
|
favorite
| on:
Intel Xeon Max 9480 Deep-Dive 64GB HBM2e Onboard L...
The M1 Ultra has 800GB/s of memory bandwidth, on contrast HBM2E has 204.8 Gbps × 2 = 409.6 Gb/s
consp
on Sept 21, 2023
|
next
[–]
Is that available to any core or just a sum-all-up and has latency penalties when going around?
hypercube33
on Sept 21, 2023
|
parent
|
next
[–]
depends on NUMA node config so I believe this is combined on the whole chip if all cores are working on threads with their local 16GB HBM, theoretically.
wmf
on Sept 21, 2023
|
prev
|
next
[–]
GPUs use 4-6 stacks of HBM2 which is 1,840-2,760 GB/s. It's 2x-3x the bandwidth of M1/M2 Ultra.
Brian-Puccio
on Sept 21, 2023
|
prev
[–]
So 6,400 Gb/s compared to 409.6 Gb/s once you convert units?
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
