Efficient Memory Management for High-Speed ATM Systems
نویسندگان
چکیده
ATM technology places strict performance requirements on ATM systems, especially considering the scalability of the SDH/SONET physical layer to high speeds. Throughput preservation of the link speed through protocols to a higher layer application is a known problem in high-speed communication systems. The problem is being addressed with design methodologies that offer high speed data paths, using specialized hardware, and increased processing power, commonly in the form of embedded processors. In this paper, we present a case study for a high-speed Queue Manager for ATM systems. The manager enables high-speed data transfer to/from system memory and management of logical data structures (queues). Furthermore, it provides high-speed and importantly, scalability and re-usability, so that it can be used in a wide range of ATM systems, such as workstation adapters, switches, routers, etc. In this work, we provide contributions in two directions. We describe an approach to develop a high-speed, scalable and re-usable memory manager for ATM systems, and then we provide an architecture and implementations in harware as well as in software for embedded systems. The results indicate the cost/performance trade-off’s and system scalability and thus, enable designers to choose the implementation that meets their target system requirements well.
منابع مشابه
High performance group communication services in ATM networks
Advanced applications, such as distributed multimedia applications, require efficient communication subsystems providing a variety of services. Existing communication systems face increasing difficulties in fulfilling these requirements. In particular, the efficient provision of reliable group communication services in ATM-Networks remains a major unresolved issue. This paper presents a novel f...
متن کاملPetri Net Modeling for Parallel Bank ATM Systems
In this paper the real time operation of an automatic teller machine (ATM) is analyzed using aTimed Petri Net (TPN) model. In the modeling, the probability of arrivals, the speed andattentiveness of customers (clients) are taken to account. Different parameters are based onthe statistical data. The model is simulated for 24 hours. The diagrams of number ofsucceeded customers, failed references ...
متن کاملLow Power March Memory Test Algorithm for Static Random Access Memories (TECHNICAL NOTE)
Memories are most important building blocks in many digital systems. As the Integrated Circuits requirements are growing, the test circuitry must grow as well. There is a need for more efficient test techniques with low power and high speed. Many Memory Built in Self-Test techniques have been proposed to test memories. Compared with combinational and sequential circuits memory testing utilizes ...
متن کاملDeadlock situations in TCP over ATM
The implementation of protocols, such as TCP/IP, and their integration into the operating system environment is very decisive for protocol performance. Putting TCP on high-speed networks, e.g. ATM, with large maximum transmission units causes the TCP maximum segment size to be relatively large. What Nagle’s consider “small” is not small anymore. We report on TCP/IP throughput performance measur...
متن کاملDynamic Partitioning: A Mechanism for Shared-Memory Management
In this paper, we propose a novel buffer management scheme in order to regulate the individual queue lengths in a shared-memory switch. The primary motivations of our scheme are: i) provide differentiated allocations to the queues sharing the memory, where the allocations are directly derived from the Call Admission Control (CAC) parameters; ii) allow for the co–existence of regulated and best-...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Design Autom. for Emb. Sys.
دوره 6 شماره
صفحات -
تاریخ انتشار 2001