You are here: NI Home > Support > Product Reference > Manuals > LabVIEW 8.2 Help

Hyperthreading is a feature of some versions of the Intel Pentium 4 and later. A hyperthreaded computer has a single processor but acts as a computer with a multiprocessor. When you launch the Windows Task Manager on a hyperthreaded computer and click the Performance tab, the Windows Task Manager displays the usage history for two CPUs.

A hyperthreaded processor acts like multiple processors embedded on the same microchip. Some of the resources on the chip are duplicated, such as the register set. Other resources are shared, such as the execution units and the cache. Some resources, such as the buffers that store micro operations, are partitioned, with each logical processor receiving a portion.

Optimizing an application to take advantage of hyperthreading is similar to optimizing an application for a multiprocessor system, but there are some differences. For example, a hyperthreaded computer shares the execution units, and a dual-processor computer contains two complete sets of execution units. Therefore, any application that is limited by floating-point execution units performs better on the multiprocessor computer because you do not have to share the execution units. The same principle applies with cache contention. If two threads try to access the cache, the performance is better on a multiprocessor computer, where each processor has its own full-size cache.