Hacker News Reader

Comment by toast0 | Hacker News Reader

In my mind, SMT made more sense when core counts were low. These days, desktop use cases can more often run out of threads to run than places to run them. Server use cases can often run more threads, but it might not be useful to run 32 cpu threads if your NICs can only properly run 16 queues.

View on HN

For computational tasks, I've seen SMT give a roughly 50% performance increase compared to not using SMT on the same machine.

Much of that depends on how 'regular' the executions are. A highly optimized FFT or BLAS routine will benefit less than a sparse matrix computation, where part of the time is spent in indexing, rather than floating point operations.

Some SMT on/off benchmark comparisons on a Ryzen 3900x. Confirms your "sometimes 50+% / sometimes nothing" experience.

https://www.techpowerup.com/review/amd-ryzen-9-3900x-smt-off...

For highly optimized routines I'd tend to worry about not gaining anything due to be limited by cache speed, or even about losing performance on net due to cache thrashing.

There's no direct correlation between NIC queues and CPU threads. The days of dedicating one thread to each incoming connection and/or HTTP request are long behind us, not to mention there are many tasks that require a lot of processing with little to no network activity.

That's not true. NIC queues and CPUs are still very important to get good performance on servers by pinning different queues to different cores.

Only if your workload involves passing around a lot of network traffic (e.g. a load balancer) or is highly latency-sensitive.

I've got backend servers that routinely max out 32c/64t CPUs but push so little traffic that replacing the NIC with a cell phone modem would make no discernible difference. There are many types of server workloads where the NIC is not the bottleneck at all, so the parent's argument that low NIC queue counts make high CPU core counts useless is false.

The parent said "but it might not be useful". "Might" being an important word here.

"Server use cases can often run more threads, but it might not be useful" != "low NIC queue counts make high CPU core counts useless "

You're debating an argument that was never made.

There are many >100 core POWER8 or POWER9 systems running SAP HANA, Epic or Oracle with SMT4 or SMT8 today.

Reply on news.ycombinator.com