Multi-core optimization

Multi-core optimization is a broad topic, and there is a broad array of differing hardware. However, we can discuss a little about the best way to achieve ideal multi-core efficiency.

First, what are you looking to achieve, exactly? Well, maximum utilization of available cores, reduced resource contention, reduced wait states, and faster execution. That sure sounds good, eh? Unfortunately, no magic button exist that will make all that happen.

What we can do is make sure our cores are 'partitioned' to our applications by setting the CPU affinity of processes. In some cases, such 'partitioning' can boost performance, especially with this new per-core frequency scaling both AMD and Intel have come out with.

Process Lasso can apply default CPU affinities for processes (so its threads stay on the same cores every time it runs) AND it can even temporarily change the CPU affinity based on certain triggers, or when system responsiveness is low. Magic pill it isn't, but greater control it is.

Best of all, Process Lasso is no massive .NET or Rapid Application Development software - Process Lasso is old-school unmanaged native C++, consuming virtually no system resources in comparison to most applications.

DRAFT

This article is part of a collection of information available at Bitsum Technologies as part of our Process Lasso software.

Get Process Lasso to experience the benefits of automated process priority adjustment and more.

These two words are synonoms, though in this world of rapidly evolving technology they have changed a bit. CPU is now used to represent a single physical unit, where-as core is used to represent one of many CPUs on a single die. In this way, it can be confusing. Just remember, 4 cores really means 4 CPUs all on one chip.

I want to remind people that CPU utilization occurs in micro-bursts, and the % use per second is not a perfect representation of how fast or slow a CPU is. That is to say, just because that metric shows only 75% of a CPU consumed, that doesn't mean that you had an 'extra' 25% laying around. The speed at which that 75% was executed matters too. At best this metric gives you some idea of how CPU intensive your operations are.