Managing performance vs. accuracy trade-offs with loop perforation
Stelios Sidiroglou-Douskos,Sasa Misailovic,Henry Hoffmann,Martin Rinard +3 more
- pp 124-134
Reads0
Chats0
TLDR
The results indicate that, for a range of applications, this approach typically delivers performance increases of over a factor of two (and up to a factors of seven) while changing the result that the application produces by less than 10%.Abstract:
Many modern computations (such as video and audio encoders, Monte Carlo simulations, and machine learning algorithms) are designed to trade off accuracy in return for increased performance. To date, such computations typically use ad-hoc, domain-specific techniques developed specifically for the computation at hand. Loop perforation provides a general technique to trade accuracy for performance by transforming loops to execute a subset of their iterations. A criticality testing phase filters out critical loops (whose perforation produces unacceptable behavior) to identify tunable loops (whose perforation produces more efficient and still acceptably accurate computations). A perforation space exploration algorithm perforates combinations of tunable loops to find Pareto-optimal perforation policies. Our results indicate that, for a range of applications, this approach typically delivers performance increases of over a factor of two (and up to a factor of seven) while changing the result that the application produces by less than 10%.read more
Citations
More filters
Safe Planning And Control Of Autonomous Systems: Robust Predictive Algorithms
TL;DR: This work develops a robust, predictive control algorithm to control the the dynamical system to follow the trajectories generated by the rst part, within some desired bounds, and shows that this predictive algorithm remains feasible with respect to constraints while following a desired trajectory, and also stabilizes the dynamicals system under control.
Proceedings ArticleDOI
MinUn: Accurate ML Inference on Microcontrollers
TL;DR: MinUn as discussed by the authors is the first TinyML framework that holistically addresses these issues to generate efficient code for ARM microcontrollers (e.g., Arduino Uno, Due and STM32H747) that outperforms the prior TinyML frameworks.
A Cross-Layer Resilient Multicore Architecture
TL;DR: The idea of declarative resilience that selectively applies resiliency schemes to both crucial and non-crucial code is explained, and a cross-layer architecture is developed, through which hardware collaborates with software support to enable efficient resilience with holistic softerror coverage.
Proceedings ArticleDOI
Assertion-aware approximate computing design exploration on behavioral models
TL;DR: In this paper , the authors propose an ABV-based methodology to guide the AxC design exploration of behavioral descriptions and define a metric to predict the impact of approximating model statements on the design accuracy.
Proceedings ArticleDOI
Effective Performance Issue Diagnosis with Value-Assisted Cost Profiling
TL;DR: In this article , the authors introduce a new profiling methodology, value-assisted cost profiling, and a tool vProf, which continuously records values while profiling normal and buggy program executions.
References
More filters
Proceedings ArticleDOI
LLVM: a compilation framework for lifelong program analysis & transformation
Chris Lattner,Vikram Adve +1 more
TL;DR: The design of the LLVM representation and compiler framework is evaluated in three ways: the size and effectiveness of the representation, including the type information it provides; compiler performance for several interprocedural problems; and illustrative examples of the benefits LLVM provides for several challenging compiler problems.
Journal ArticleDOI
The JPEG still picture compression standard
TL;DR: The Baseline method has been by far the most widely implemented JPEG method to date, and is sufficient in its own right for a large number of applications.
Proceedings ArticleDOI
The PARSEC benchmark suite: characterization and architectural implications
TL;DR: This paper presents and characterizes the Princeton Application Repository for Shared-Memory Computers (PARSEC), a benchmark suite for studies of Chip-Multiprocessors (CMPs), and shows that the benchmark suite covers a wide spectrum of working sets, locality, data sharing, synchronization and off-chip traffic.
Related Papers (5)
Green: a framework for supporting energy-conscious programming using controlled approximation
Woongki Baek,Trishul Chilimbi +1 more