Quality of service profiling

Abstract

Many computations exhibit a trade off between execution time and quality of service. A video encoder, for example, can often encode frames more quickly if it is given the freedom to produce slightly lower quality video. A developer attempting to optimize such computations must navigate a complex trade-off space to find optimizations that appropriately balance quality of service and performance. We present a new quality of service profiler that is designed to help developers identify promising optimization opportunities in such computations. In contrast to standard profilers, which simply identify time-consuming parts of the computation, a quality of service profiler is designed to identify subcomputations that can be replaced with new (and potentially less accurate) subcomputations that deliver significantly increased performance in return for acceptably small quality of service losses. Our quality of service profiler uses loop perforation (which transforms loops to perform fewer iterations than the original loop) to obtain implementations that occupy different points in the performance/quality of service trade-off space. The rationale is that optimizable computations often contain loops that perform extra iterations, and that removing iterations, then observing the resulting effect on the quality of service, is an effective way to identify such optimizable subcomputations. Our experimental results from applying our implemented quality of service profiler to a challenging set of benchmark applications show that it can enable developers to identify promising optimization opportunities and deliver successful optimizations that substantially increase the performance with only small quality of service losses.

On the potential of significance-driven execution for energy-aware HPC

“…This scheme achieves 90% or better accuracy of the output of applications even for 2×10 4 errors per second per core. Agarwal et al [1], Misailovic et al [13] and Rinard et al [15] propose a static analysisbased technique to reduce the number of iterations in a loop without compromising correctness. In the same context, Baek et al [3] provide a framework where the programmer specifies the functions and loops they want to approximate and the desired loss of Quality of Service (QoS).…”

Language and compiler support for auto-tuning variable-accuracy algorithms

“…Techniques such as Loop Perforation [10], Code Perforation [11], and Task Skipping [12], [13] automatically transform existing computations and/or programs to achieve higher performance. The resulting new computations may skip subcomputations (for example loop iterations or tasks) that may not be needed to achieve a certain level of accuracy.…”

Manipulating Program Functionality to Eliminate Security Vulnerabilities

“…This transformation typically changes the result that the system produces. But it is often possible to find time-consuming loops which still produce acceptable results after this transformation [11,9]. This mechanism can produce, automatically, a range of computations with different implementations that all provide acceptable results.…”