Abstract-Automatic provenance capture from arbitrary applications is a challenging problem. Different approaches to tackle this problem have evolved, most notably a. system-event trace analysis, b. compile-time static instrumentation, and c. taint flow analysis using dynamic binary instrumentation. Each of these approaches offers different trade-offs in terms of the granularity of captured provenance, integration requirements, and runtime overhead. While these aspects have been discussed separately, a systematic and detailed study, quantifying and elucidating them, is still lacking. To fill this gap, we begin to explore these trade-offs for representative examples of these approaches for automatic provenance capture by means of evaluation and measurement. We base our evaluation on UnixBench-a widely used benchmark suite within systems research. We believe this approach will make our results easier to compare with future studies.
We propose ApproxHPVM, a compiler IR and system designed to enable accuracy-aware performance and energy tuning on heterogeneous systems with multiple compute units and approximation methods. ApproxH-PVM automatically translates end-to-end application-level quality metrics into accuracy requirements for individual operations. ApproxHPVM uses a hardware-agnostic accuracy-tuning phase to do this translation that provides greater portability across heterogeneous hardware platforms and enables future capabilities like accuracy-aware dynamic scheduling and design space exploration. ApproxHPVM incorporates three main components: (a) a compiler IR with hardware-agnostic approximation metrics, (b) a hardware-agnostic accuracy-tuning phase to identify error-tolerant computations, and (c) an accuracy-aware hardware scheduler that maps error-tolerant computations to approximate hardware components. As ApproxHPVM does not incorporate any hardware-specific knowledge as part of the IR, it can serve as a portable virtual ISA that can be shipped to all kinds of hardware platforms. We evaluate our framework on nine benchmarks from the deep learning domain and five image processing benchmarks. Our results show that our framework can offload chunks of approximable computations to special-purpose accelerators that provide significant gains in performance and energy, while staying within user-specified application-level quality metrics with high probability. Across the 14 benchmarks, we observe from 1-9x performance speedups and 1.1-11.3x energy reduction for very small reductions in accuracy. CCS Concepts: • Software and its engineering → Compilers.
No abstract
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.