A Prefetching IPC Mechanism for Low-Latency Transfer of Structured Data Cooperated with User Programs
نویسندگان
چکیده
An interprocess communication (IPC) mechanism has been developed that enables lowlatency communication of structured data. This is becoming more important for such applications as distributed query processing of object-oriented databases (OODB) and hyper-text world-wide web (WWW) pages. In these applications, a sender typically creates structured data and sends them to a receiver. The main obstacle to achieve highperformance IPC with this pattern of communication is the latency of the receiver, which is caused by network latency and the di erent data processing order between the sender and the receiver. The IPC mechanism uses three key techniques: memory mapping , typed prefetching and controlling the data-sending order . A prototype IPC mechanism, implemented as a library on DECstation 5000 running Mach 3.0, demonstrated that this IPC mechanism reduces latency in the communication of structured data compared with update-based and request-driven IPC mechanisms.
منابع مشابه
Latency Reduction and Tolerance in Distributed Digital Libraries
Caching and prefetching are well known to reduce and tolerate latency in distributed systems such as the World Wide Web (WWW). In the scientific world those techniques could be used for digital libraries, where latency is experienced in the retrieval of publications from publishers. This thesis is an investigation into the prospects of applying caching and prefetching in the context of distribu...
متن کاملLibrary-based Prefetching for Pointer-intensive Applications
Processor speed has been improving faster than memory latency for over two decades. Thus, an increased portion of execution time is spent stalling on loads, waiting for data from the memory hierarchy. Prefetching is an effective mechanism to hide memory latency for applications with low temporal locality. However, existing hardware prefetching techniques work well for array-based programs but n...
متن کاملA Status Report on Research in Transparent Informed Prefetching (CMU-CS-93-113)
This paper focuses on extending the power of caching and prefetching to reduce file read latencies by exploiting application level hints about future I/O accesses. We argue that systems that disclose high-level knowledge can transfer optimization information across module boundaries in a manner consistent with sound software engineering principles. Such Transparent Informed Prefetching (TIP) sy...
متن کاملGlobal-aware and multi-order context-based prefetching for high-performance processors
Data prefetching is widely used in high-end computing systems to accelerate data accesses and to bridge the increasing performance gap between processor and memory. Context-based prefetching has become a primary focus of study in recent years due to its general applicability. However, current context-based prefetchers only adopt the context analysis of a single order, which suffers from low pre...
متن کاملData Cache Prefetching with Perceptron Learning
Cache prefetcher greatly eliminates compulsory cache misses, by fetching data from slower memory to faster cache before it is actually required by processors. Sophisticated prefetchers predict next use cache line by repeating program’s historical spatial and temporal memory access pattern. However, they are error prone and the mis-predictions lead to cache pollution and exert extra pressure on ...
متن کامل