Re:NUMA Is the New Network: Reshaping Per-Socket Microservic...
by ccgreg on Monday August 18, 2025 @12:08AM
(#44937322)
> The long and short of it is that if you’re building a HPC application, or are sensitive to throughput and latency on your cutting-edge/high-traffic system design, then you need to manually pin your workloads for optimal performance.
Last time I was architect of a network chip, 21 years ago, our library did that for the user. For workloads that use threads that consume entire cores, it's a solved problem.
I'd guess that the workload you had in mind doesn't have that property.
Last time I was architect of a network chip, 21 years ago, our library did that for the user. For workloads that use threads that consume entire cores, it's a solved problem.
I'd guess that the workload you had in mind doesn't have that property.