Processor affinity

Processor affinity refers to the ability of an operating system to assign a specific task or process to a particular core or set of cores in a multi-core processor. This feature is also known as CPU pinning and is used to reduce cache interference and improve performance by ensuring that each program or application stays on the same processor during its entire execution. The Arbitrary Processor Affinity scheduler provides even more control by allowing users to specify affinity masks, which dictate which cores tasks are allowed to run on.From: Data Plane Development Kit (DPDK) [2020], Reduced O3 subsequence labelling: a stepping stone towards optimisation sequence prediction [2022], Real-Time Systems Development with RTEMS and Multicore Processors [2020]

Core-Based Parallelism

View Chapter

Purchase Book

Published in Heqing Zhu, Data Plane Development Kit (DPDK), 2020

Qun Wan, Heqing Zhu, Zhihong Wang

As the processor has the multicore architecture, by default, the OS task scheduler is responsible for running software on the cores. OS has an advanced mechanism, such as supporting the processor affinity (also known as CPU pinning), which allows a particular task (process) to run on the given core(s). This will give software with the dedicated core(s) as the execution resource.

Reduced O3 subsequence labelling: a stepping stone towards optimisation sequence prediction

View Article

Journal Information

Published in Connection Science, 2022

Yi-Ping You, Yi-Chiao Su

All of the evaluations in this study were conducted on a platform whose hardware and system details are indicated in Table 7. Processor affinity was used to ensure that each program or application stayed in the same processor during the whole execution in order to reduce cache interference. Meanwhile, there were no other processes running except the system processes in order to reduce any possible interference. The benchmarks we used to evaluate the modified SPEA2+ algorithm were collected from the test suite of the LLVM compiler infrastructure (Lattner & Adve, 2004), including loop_unroll from Adobe-C++ and two applications: libSVM and Hexxagon.

Processor affinity

Explore chapters and articles related to this topic

Core-Based Parallelism

Reduced O3 subsequence labelling: a stepping stone towards optimisation sequence prediction