gem5-Approxilyzer: An Open-Source Tool for Application-Level Soft Error Analysis

Venkatagiri, Radha; Ahmed, Khalique; Mahmoud, Abdulrahman; Misailovíc, Saša; Marinov, Darko; Fletcher, Christopher W.; Adve, Sarita V.

doi:10.1109/dsn.2019.00033

Cited by 20 publications

(10 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The equivalence based Relyzer [37] uses the static analysis of flow control and dynamic analysis of data flow to capture the similarity degree of different instructions for fewer simulations with fault injection and higher efficiency. On the base of the existing Relyzer, Approxilyzer [38] and gem5-approxilyzer [39] were proposed via exploiting the one bit upset affecting the application-level output quality. However, the optimized Mentor Carlo simulation is still time consuming due to unavoidable simulations.…”

Section: Error Estimation Methodsmentioning

confidence: 99%

See 1 more Smart Citation

HEAP: A Holistic Error Assessment Framework for Multiple Approximations Using Probabilistic Graphical Models

Jiao

2020

Electronics

View full text Add to dashboard Cite

Approximate computing has been a good paradigm of energy-efficient accelerator design. Accurate and fast error estimation is critical for appropriate approximate techniques selection so that power saving (or performance improvement) can be maximized with acceptable output quality in approximate accelerators. In the paper, we propose HEAP, a Holistic Error assessment framework to characterize multiple Approximate techniques with Probabilistic graphical models (PGM) in a joint way. HEAP maps the problem of evaluating errors induced by different approximate techniques into a PGM issue, including: (1) A heterogeneous Bayesian network is represented by converting an application’s data flow graph, where various approximate options are {precise, approximate} two-state X*-type nodes, while input or operating variables are {precise, approximate, unacceptable} three-state X-type nodes. These two different kinds of nodes are separately used to configure the available approximate techniques and track the corresponding error propagation for guaranteed configurability; (2) node learning is accomplished via an approximate library, which consists of probability mass functions of multiple approximate techniques to fast calculate each node’s Conditional Probability Table by mechanistic modeling or empirical modeling; (3) exact inference provides the probability distribution of output quality at three levels of precise, approximate, and unacceptable. We do a complete case study of 3 × 3 Gaussian kernels with different approximate configurations to verify HEAP. The comprehensive results demonstrate that HEAP is helpful to explore design space for power-efficient approximate accelerators, with just 4.18% accuracy loss and 3.34 × 105 speedup on average over Mentor Carlo simulation.

show abstract

Section: Error Estimation Methodsmentioning

confidence: 99%

“…First is Mentor Carlo simulation to capture dynamic execution of applications exactly in approximate architectures. It often uses a large number of simulations to get the accurate statistical results [37][38][39]. This general-purpose approach provides dependable estimation, but requires too much time.…”

Section: Introductionmentioning

confidence: 99%

HEAP: A Holistic Error Assessment Framework for Multiple Approximations Using Probabilistic Graphical Models

Jiao

2020

Electronics

View full text Add to dashboard Cite

show abstract

“…They selected the UltraSPARC processor (8 cores, 64 threads) as Device Under Test (DUT) to characterize the effects of intermittent faults at the RTL level, and showed that some systematic events can be used as detection symptoms [28][29]. Rashid set up a pure software-based fault injector that is designed on SimpleScalar, and investigated the characteristic of intermittent faults at the application program level (Spec CPU2006) [30]. Hu et al set up a system-level fault injection platform based on the Simics simulator, and studied the impact of hardware fault on a multi-core system through software simulation, including operating system and application program [31].…”

Section: Fault Injectorsmentioning

confidence: 99%

End-to-end diagnosis of cloud systems against intermittent faults

Wang

Huo

2021

COMSIS J

View full text Add to dashboard Cite

The diagnosis of intermittent faults is challenging because of their random manifestation due to intricate mechanisms. Conventional diagnosis methods are no longer effective for these faults, especially for hierachical environment, such as cloud computing. This paper proposes a fault diagnosis method that can effectively identify and locate intermittent faults originating from (but not limited to) processors in the cloud computing environment. The method is end-to-end in that it does not rely on artificial feature extraction for applied scenarios, making it more generalizable than conventional neural network-based methods. It can be implemented with no additional fault detection mechanisms, and is realized by software with almost zero hardware cost. The proposed method shows a higher fault diagnosis accuracy than BP network, reaching 97.98% with low latency.

show abstract

“…There have been many studies on the effects of soft errors on CPUs and GPUs [25], [41], [65], [75], [104], [108], [110], deep learning accelerators [64], [83], and autonomous vehicle systems [9], [52], [53]. However, their impact on accelerators for robotics has not been studied.…”

Section: Introductionmentioning

confidence: 99%

“…Prior work on FI techniques for CPUs and GPUs [25], [41], [65], [79], [104], [110] has obtained significant reductions in the FI time. These FI tools and techniques are targeted towards specific languages, Instruction Set Architectures (ISA), or CPU/GPU system simulators and often exploit the microarchitecture or ISA to reduce the FI time and estimate the failure probability (Section 8).…”

Section: Introductionmentioning

confidence: 99%

Characterizing and Improving the Resilience of Accelerators in Autonomous Robots

Shah¹,

Xue²,

Pattabiraman³

et al. 2021

Preprint

View full text Add to dashboard Cite

Motion planning is a computationally intensive and well-studied problem in autonomous robots. However, motion planning hardware accelerators (MPA) must be soft-error resilient for deployment in safety-critical applications, and blanket application of traditional mitigation techniques is ill-suited due to cost, power, and performance overheads. We propose Collision Exposure Factor (CEF), a novel metric to assess the failure vulnerability of circuits processing spatial relationships, including motion planning. CEF is based on the insight that the safety violation probability increases with the surface area of the physical space exposed by a bit-flip. We evaluate CEF on four MPAs. We demonstrate empirically that CEF is correlated with safety violation probability, and that CEF-aware selective error mitigation provides 12.3×, 9.6×, and 4.2× lower Failures-In-Time (FIT) rate on average for the same amount of protected memory compared to uniform, bit-position, and access-frequency-aware selection of critical data. Furthermore, we show how to employ CEF to enable fault characterization using 23, 000× fewer fault injection (FI) experiments than exhaustive FI, and evaluate our FI approach on different robots and MPAs. We demonstrate that CEF-aware FI can provide insights on vulnerable bits in an MPA while taking the same amount of time as uniform statistical FI. Finally, we use the CEF to formulate guidelines for designing soft-error resilient MPAs.

show abstract

gem5-Approxilyzer: An Open-Source Tool for Application-Level Soft Error Analysis

Cited by 20 publications

References 38 publications

HEAP: A Holistic Error Assessment Framework for Multiple Approximations Using Probabilistic Graphical Models

HEAP: A Holistic Error Assessment Framework for Multiple Approximations Using Probabilistic Graphical Models

End-to-end diagnosis of cloud systems against intermittent faults

Characterizing and Improving the Resilience of Accelerators in Autonomous Robots

Contact Info

Product

Resources

About