Application Source Research Articles

Method-level phase behavior in java workloads

Java workloads are becoming more and more prominent on various computing devices. Understanding the behavior of a Java workload which includes the interaction between the application and the virtual machine (VM), is thus of primary importance during performance analysis and optimization. Moreover, as contemporary software projects are increasing in complexity, automatic performance analysis techniques are indispensable. This paper proposes an off-line method-level phase analysis approach for Java workloads that consists of three steps. In the first step, the execution time is computed for each method invocation. Using an off-line tool, we subsequently analyze the dynamic call graph (that is annotated with the method invocations' execution times) to identify method-level phases. Finally, we measure performance characteristics for each of the selected phases. This is done using hardware performance monitors. As such, our approach allows for linking microprocessor-level information at the individual methods in the Java application's source code. This is extremely interesting information during performance analysis and optimization as programmers can use this information to optimize their code. We evaluate our approach in the Jikes RVM on an IA-32 platform using the SPECjvm98 and SPECjbb2000 benchmarks. This is done according to a number of important criteria: the overhead during profiling, the variability within and between the phases, its applicability in Java workload characterization (measuring performance characteristics of the various VM components) and application bottleneck identification.

"Patch on demand" saves even more time? [network security

Zero-day attacks are those for which users receive no prior warning and thus have no preventive measures in place. We integrate the vulnerability discovery, patch generation, and patch application cycles into a system that automatically detects a new attack, analyzes its modus operandi, determines the best software patch, and applies it at the desired level of granularity LAN, enterprise, or Internet-wide. We develop a vaccination system that automatically generates patches to protect an application's source code.

Module reuse by interface adaptation

AbstractThis paper describes a language called Nimble that allows designers to declare how the actual parameters in a procedure call are to be transformed at run time. Normally, programmers must edit an application's source in order to adapt it for reuse in some new context where the interfaces fail to match exactly (e.g. the parameters may appear in a different order, data types may not exactly match, and some data may need to be either initialized or masked out when the reusable module is integrated within a new application.) But Nimble allows programmers to adapt the interfaces of existing software without having to operate on the source manually. As a result, existing software may be easily reused in a broader range of applications, and software libraries do not need to store many variants of a component that differ only in how the interfaces are used. Nimble has been implemented on a variety of Unix hosts, and is part of a broader reuse project at the University of Maryland. Our current system is suitable for use either in conjunction with existing module interconnection languages, or stand‐alone with C, Pascal and Ada source programs.