Unmodified Software Research Articles

Optimized GPU-based post-processing for stereoscopic multi-projector display systems

To drive multi-projector display systems, the image content has to be post-processed to apply geometrical and photometrical correction algorithms. Since the optical path is shared for both views of a stereoscopic projector, we propose to eliminate redundant calculations by processing both views at once. We show that by exploiting the color similarities of stereoscopic image pairs, the cache efficiency of LUT-based color correction methods can be improved. Stereoscopic content is often transmitted in different formats where a single frame represents both views in a spatially multiplexed pattern, and display devices typically support only a subset of these formats, so that the need for conversion arises. We propose an algorithm to directly incorporate such format conversions into the post-processing and show that our combined approach can achieve significant performance improvements compared to the naive multi-pass implementation. The reduced overhead of the post-processing step increases the number of projectors which can be driven by a single GPU, which enables building larger or higher resolution displays at lower costs. The flexibility gained by the ability to process different input formats also greatly enhances the usability of powerwalls by allowing to implement the post-processing at different levels and working with unmodified software applications.

Performance tuning with instruction-level cost derived from call-stack sampling

Except for program-counter histogramming, most modern profiling tools summarize at the level of entire functions or basic blocks, with or without additional information such as calling context or call graphs. This paper explicates the value of information about the cost of specific instructions, relative to summaries that do not include it. A good source of this information is time-random sampling of the call stack. To get the diagnostic benefit of instruction costs it is not necessary to measure them with high precision or efficiency. In fact, manual sampling suffices quite well, when it can be used. Other benefits of call stack sampling are that it can be used with unmodified software and libraries, and it is easily confined to the time intervals of interest. As with other profiling techniques, it can be employed repeatedly to remove all significant performance problems in single-thread programs.

Kernel-level single system image for petascale computing

Scientific computing users typically prefer UNIX or UNIX-like operating systems as their runtime for managing software and hardware resources. These UNIX-like systems were originally designed for a single processor as well as for a broad range of programming and usage models. Although UNIX-like systems have successfully been modified to work in SMP or NUMA configuration, their internal structures remain relatively the same over the years. As we move toward the era of petascale computing, these UNIX-like systems are no longer suitable. For instance, the relative cost of supporting generic usages and system services will increase by a magnitude and thus affect the overall system performance; there are insufficient system services to globally manage parallelism, processes, and resources; users may not see the petascale system as a single powerful machine but rather as a set of multiple independent servers. A single system image (SSI) operating system is essential for efficiently manage parallelism, resources and processes as well as providing parallel processing transparency for a system possibly equipped with hundred thousand of processors. However, the success of a petascale SSI operating system goes beyond technical challenges. In particular, it must look very much like the normal UNIX, run unmodified software, scale incrementally, and equip with built-in high availability supports. This position paper focuses on these issues and discusses the development of a petascale SSI, based on an existing kernel-level SSI system, OpenSSI.

Scalability and accuracy in a large-scale network emulator

This paper presents ModelNet, a scalable Internet emulation environment that enables researchers to deploy unmodified software prototypes in a configurable Internet-like environment and subject them to faults and varying network conditions. Edge nodes running user-specified OS and application software are configured to route their packets through a set of ModelNet core nodes, which cooperate to subject the traffic to the bandwidth, congestion constraints, latency, and loss profile of a target network topology.This paper describes and evaluates the ModelNet architecture and its implementation, including novel techniques to balance emulation accuracy against scalability. The current ModelNet prototype is able to accurately subject thousands of instances of a distrbuted application to Internet-like conditions with gigabits of bisection bandwidth. Experiments with several large-scale distributed services demonstrate the generality and effectiveness of the infrastructure.

An architecture for knowledge-based front ends

Abstract The problem of constructing knowledge-based front-ends to existing software systems is considered. An architecture for such a front-end is proposed that has, as its central component, a module known as the Harness. The Harness provides the communication facilities required by the various elements of the knowledge-based front-end as well as handling the interactions with the user. It, therefore, extends the notion of a user-interface management system to be applicable to the problem of integrating diverse and unmodified software systems to provide a single user service together with the necessary support.