News for hackers. Stuff that matters.
Re:Computing Performance on the Horizon by rbanffy on Monday July 05, 2021 @06:26PM (#27742382)
I have an enormous respect for Brandon Gregg, but this "one socket ought to be enough for anyone" is something I saw too many people get burned with.

I mean, it should, but who knows what the next version of Slack will need...

Re:Computing Performance on the Horizon by hinkley on Monday July 05, 2021 @07:58PM (#27742959)
Still feels to me like we should be going the other way - kick more and more things off of the motherboard and support them with discrete - potentially customized - processors of their own.

Between io_uring and current or future facilities of eBPF, we have a lot of tools on deck for pipelining IO operations, and once you have a way to pipeline IO operations, the latency is not the only bottleneck. Then it’s a matter of how much bandwidth you can push between two processes, or processors.

Re:Computing Performance on the Horizon by nine_k on Tuesday July 06, 2021 @01:31AM (#27744534)
OK, it must be a compute-heavy load that does little random memory access, but works mostly on compact in-cache structures and maybe does sustained sequential memory accesses. With that, it's not suitable to offload to the GPU.

What could it be? Serious question.

Re:Computing Performance on the Horizon by dragontamer on Tuesday July 06, 2021 @10:11AM (#27748829)
Database with a large portion of data in-memory.

* Second socket increases the memory channels and RAM available: 16-channel dual-EPYC with 8TB of RAM will be faster than 4TB of RAM on single-EPYC 8-channel.

* SQL optimizers automatically search for sequential scans, because sequential scans are faster.

* While JOIN can be done in GPU space, GPUs have extremely low memory capacity (only 80GB on the latest A100 that costs $10,000+). CPU will be faster because you can keep a much larger dataset hot in RAM. Your 80GB of VRAM on a GPU means nothing if your dataset is in the multi-TB range. (8TB of CPU-RAM on the other hand, serves as a reasonable cache)

Re:Computing Performance on the Horizon by rbanffy on Wednesday July 07, 2021 @02:49PM (#27764499)
More sockets add memory controllers, but we can also think about moving HBM closer to the cores as a L4 cache or scratch memory that’s not expected to be synchronised with other cores/sockets.