Profile Guided Code Optimisation of Marshalling Routines
نویسنده
چکیده
The marshalling operation has often been identified as a performance bottleneck for high-speed network applications. In this paper, we propose the use of profile guided code generation of marshalling routines in order to better adapt performance optimisations of marshalling routines to the requirements of a specific application. We motivate this approach with a detailed case study and measurements of optimising marshalling for the X.400 e-mail application. Overall, using profile information allows us to achieve a performance improvement of 25 % ( reduction of communication latency by 50 us per message).
منابع مشابه
Improved Code Sharing in Dynamically Generated Marshalling Routines (full Paper) Paul Menage Improved Code Sharing in Dynamically Generated Marshalling Routines
marshalling routines (Full paper) Paul Menage [email protected] phone: +44 1223 331859, fax: +44 1223 334678 University of Cambridge Computer Laboratory New Museums Site, Pembroke Street Cambridge, UK, CB2 3QG Abstract Marshalling schemes for Inter-process Communication (IPC) systems can be classi ed as compiled or interpreted; each has advantages and disadvantages. This paper presents a...
متن کاملAutomatic Generation of Optimized Code for Marshalling Routines
We describe a new approach to the automatic generation of marshalling code which results in code that is fast and compact at the same time. The key insight behind our work is that certain types in an interface specification occur more often than others at run-time. We exploit this locality to solve a particularily difficult optimization problem in stub generators, namely the trade-off between c...
متن کاملOptimisation of simultaneous train formation and car sorting at marshalling yards∗
Efficient and correct freight train marshalling is vital for high quality carload freight transportations. During marshalling, it is desirable that cars are sorted according to their individual drop-off locations in the outbound freight trains. Furthermore, practical limitations such as non-uniform and limited track lengths and the arrival and departure times of trains need to be considered. Th...
متن کاملAutomated code generation for integrated layer processing
ALF (application level framing) and ILP (integrated layer processing) are protocol design and implementation concepts applied in high-performance communication architectures, e.g. to support multimedia applications. Writing ILP code is rather complex and, therefore, ILP code generation tools can reduce the time to develop efficient ILP protocol code significantly. This paper presents a tool, wh...
متن کاملEmergency department resource optimisation for improved performance: a review
Emergency departments (EDs) have been becoming increasingly congested due to the combined impacts of growing demand, access block and increased clinical capability of the EDs. This congestion has known to have adverse impacts on the performance of the healthcare services. Attempts to overcome with this challenge have focussed largely on the demand management and the application of system wide p...
متن کامل