Single-language runtime systems, in the form of Java virtual machines, are widely deployed platforms for executing untrusted mobile code. These runtimes provide some of the features that operating systems provide: inter-application memory protection and basic system services. They do not, however, provide the ability to isolate applications from each other, or limit their resource consumption. This paper describes KaffeOS, a system that provides these features for a Java runtime. The KaffeOS architecture takes many lessons from operating system design, such as the use of a user/kernel boundary.The KaffeOS architecture supports the OS abstraction of a process in a Java virtual machine. Each process executes as if it were run in its own virtual machine, including separate garbage collection of its own heap. The difficulty in designing KaffeOS lay in balancing the goals of isolation and resource management against the goal of allowing direct sharing. Overall, KaffeOS is up to 11% slower than the freely available JVM on which it is based, which is an acceptable penalty for the safety that it provides. KaffeOS is substantially slower than commercial JVMs, but exhibits much better performance scaling in the presence of uncooperative code.

This paper describes a novel approach to providing modular and extensible operating system functionality and encapsulated environments based on a synthesis of microkernel and virtual machine concepts. We have developed a software-based virtualizable architecture called Fluke that allows recursive virtual machines (virtual machines running on other virtual machines) to be implemented efficiently by a microkernel running on generic hardware. A complete virtual machine interface is provided at each level; efficiency derives from needing to implement only new functionality at each level. This infrastructure allows common OS functionality, such as process management, demand paging, fault tolerance, and debugging support, to be provided by cleanly modularized, independent, stackable virtual machine monitors, implemented as user processes. It can also provide uncommon or unique OS features, including the above features specialized for particular applications' needs, virtual machines transparently distributed cross-node, or security monitors that allow arbitrary untrusted binaries to be executed safely. Our prototype implementation of this model indicates that it is practical to modularize operating systems this way. Some types of virtual machine layers impose almost no overhead at all, while others impose some overhead (typically 0-35%), but only on certain classes of applications.

Pattern-based Representation (PBR) is a novel approach to improving the performance of Sparse Matrix-Vector Multiply (SMVM) numerical kernels. Motivated by our observation that many matrices can be divided into blocks that share a small number of distinct patterns, we generate custom multiplication kernels for frequently recurring block patterns. The resulting reduction in index overhead significantly reduces memory bandwidth requirements and improves performance. Unlike existing methods, PBR requires neither detection of dense blocks nor zero filling, making it particularly advantageous for matrices that lack dense nonzero concentrations. SMVM kernels for PBR can benefit from explicit prefetching and vectorization, and are amenable to parallelization. We present sequential and parallel performance results for PBR on two current multicore architectures, which show that PBR outperforms available alternatives for the matrices to which it is applicable.

Abstract. DataScript is a language to describe and manipulate binary data formats as types. DataScript consists of two components: a constraint-based specification language that uses DataScript types to describe the physical layout of data and a language binding that provides a simple programming interface to script binary data. A DataScript compiler generates Java libraries that are linked with DataScript scripts. DataScript specifications can be used to describe formats in a programmatic way, eliminating the vagaries and ambiguities often associated with prosaic format descriptions. The libraries generated by the DataScript compiler free the programmer from the tedious task of coding input and output routines. More importantly, they assure correctness and safety by validating both the input read and the output generated. We show examples that demonstrate that DataScript is simple, yet powerful enough to describe many commonly used formats. Similar to how scripting languages such as Perl allow the manipulation of text files, the libraries generated by the DataScript compiler can be used to quickly write scripts that safely manipulate binary files.

No abstract