Packet processing applications in networking equipment must fulfill very high throughput requirements. At the same time, packet processing differentiation by means of packet classification, such as voice vs. e-mail, or DiffServ, must be obeyed. An efficient way to fulfill both requirements is to use numerous hardware threads combined with thread prioritization. This paper proposes a new thread prioritization method for a hardware multi-threaded processor. The originality of the method is identified in the derivation mechanism of the thread priorities, which is based on inputs from three distinct sources; namely, the threads themselves, a control unit such as an operating system, and external sources such as timers or synchronization coprocessors. These sources are explicitly selected to fulfill the requirements of their distinct nature, namely software, middleware and hardware. The proposed method achieves the desired thread differentiation without hindering performance or increasing costs, as demonstrated by initial experimental results.
Keyword: Doring, Döring
By: Andreas Doering, Maria Gabrani
Published in: RZ3531 in 2004
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
Questions about this service can be mailed to reports@us.ibm.com .