Hacker News Reader

You are absolutely correct. I might be wrong but I've always heard that the general rule of thumb for gaming CPU purchases is get best single core speed if you aren't buying for a specific game. Also, I based my statement on my workloads which involves a lot of virtualization.

View on HN

The gaming market is in some ways on the trailing edge of technology. While they're often one of the first to embrace new hardware, they're very slow to adopt changes in software or architecture because the engines that drive most of that are few and tend to evolve slowly. Until Unreal Engine, Unity, or one of the other major game engines fully embrace an architecture that allows developers to easily saturate multiple cores, most games are still going to be bottlenecked by single core performance. On the other hand, it should be blatantly obvious to anyone even remotely connected with development that full multi-core utilization is the only way to keep improving performance going forward, so sooner or later the game engine developers are going to need to fully embrace that.

Unity's new Data-Oriented Technology Stack (DOTS) aims to take advantage of multi-threading by default. It's done transparently as far as it is possible, with the help of a new burst comipiler system, their new job system and the Entity Component System (ECS).

https://unity.com/dots

That's generally accurate. Per-thread ("single-thread") performance is the dominant factor in gaming performance. Even in multi-threaded games there is usually a critical thread that is limiting performance. Amdahl's Law: never not applicable.

Reply on news.ycombinator.com