Intel® Integrated Performance Primitives Developer Guide and Reference

ID 790148
Date 11/07/2023
Public

A newer version of this document is available. Customers should click here to go to the newest version.

Document Table of Contents

Using Shared L2 Cache

Several functions in the signal processing domain are threaded on two threads intended for the Intel(R) Core™ 2 processor family, and make use of the merged L2 cache. These functions (single and double precision FFT, Div, and Sqrt ) achieve the maximum performance if both two threads are executed on the same die. In this case, the threads work on the same shared L2 cache. For processors with two cores on the die, this condition is satisfied automatically. For processors with more than two cores, set the following OpenMP* environmental variable to avoid performance degradation:

KMP_AFFINITY=compact

Product and Performance Information

Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex.

Notice revision #20201201