Scalable Algorithms for NFA Multi-Striding and NFA-Based Deep Packet Inspection on GPUs

Avalle, Matteo; Risso, Fulvio; Sisto, Riccardo

doi:10.1109/tnet.2015.2429918

Cited by 23 publications

(11 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The finding of this study shows that sleepiness is a precipitating factor for injuries among the EMS workers. This finding is in agreement with the existing literature which demonstrates 3 Respondents take a 48-hour shift and have 24 hours off with two extra days off per month. 4 Respondents take a 48-hour shift and have 24 hours off with one extra day off per month.…”

Section: Injurysupporting

confidence: 93%

See 1 more Smart Citation

Sleepiness and injury risk in emergency medical service workers in Taiwan

Lin

Huang²,

Chen

et al. 2020

PLoS ONE

View full text Add to dashboard Cite

Background Insufficient sleep is a common health and safety risk factor in high-impact workplaces where workers are required to take rotating shifts. However, studies on sleepiness-related risks and incidents, particularly among emergency medical services (EMS) workers are limited. Objective This study sought to investigate the prevalence of sleepiness and related workplace incidents among EMS workers. Methods This study utilized a cross-sectional survey design on a convenient sample of 500 EMS workers from 41 EMS squads across Taiwan. Data were collected using structured online questionnaires on workplace sleepiness and related safety incidents based on the Epworth Sleepiness Scale (ESS) and a modified 25-item EMS Safety Inventory respectively. Results With a response rate of 79.8% (n = 399), 36.9% of the respondents were identified as having mild daytime sleepiness, while 39.2% of the respondents were identified as having excessive daytime sleepiness. Multivariate analysis indicated that not only was working on rotating shifts the main cause of the high ESS scores among EMS workers, but also that higher ESS scores increased their risk of sustaining a workplace injury. Furthermore, ill-at-work incidents were associated with an increased risk of workplace-related injuries. Conclusion Overall, the findings indicated a correlation among working on rotation shifts, the prevalence of sleepiness, and a higher risk of workplace injury among EMS workers.

show abstract

Section: Injurysupporting

confidence: 93%

“…Sleepiness refers to a strong desire to fall asleep [3]. To show the seriousness of the sleepiness in the EMS department, it is worthy to put some statistics into perspective.…”

Section: Introductionmentioning

confidence: 99%

Sleepiness and injury risk in emergency medical service workers in Taiwan

Lin

Huang²,

Chen

et al. 2020

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…To increase the processing rate in regex/automata processing, a number of multi-stride (processing mutiple symbols per cycle) automata processing engines have been proposed on CPUs/GPUs [2,12,19,42,49] and FPGAs [21,42,52,53]. Yang et al [53] proposed a multi-symbol processing for regular expressions on FPGA and utilized both LUTs and BRAMs.…”

Section: Prior Workmentioning

confidence: 99%

“…However, this can be extremely inefficient, especially when the application alphabet (symbol-set) size is very small, and the number of rows in a subarray is more than required. For example, in genomics, the alphabets are A,T , C, and G, and a 2-bit automata organization with only 2 2 rows is enough to perform the string matching. This is 64× smaller than what existing spatial architectures provide!…”

Section: Introductionmentioning

confidence: 99%

FlexAmata: A Universal and Efficient Adaption of Applications to Spatial Automata Processing Accelerators

Sadredini

Rahimi

Lenjani

et al. 2020

Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Syste

View full text Add to dashboard Cite

Pattern matching, especially for complex patterns with many variations, is an important task in many big-data applications and maps well to finite automata. Recently, a variety of research has focused on hardware acceleration of automata processing, especially via spatial architectures that directly map the patterns to massively parallel hardware elements, such as in FPGAs and in-memory solutions. We observed that all existing automata-acceleration architectures are designed based on fixed, 8-bit symbol processing, derived from ASCII processing. However, the alphabet size in pattern-matching applications varies from just a few up to billions of unique symbols. This makes it difficult to provide a universal and efficient mapping of this wide variety of automata applications to existing automata accelerators.In this paper, we present FlexAmata, a compiler solution for efficient adaption of applications with any alphabet size to existing pattern-matching accelerators. We demonstrate that this can increase automata processing efficiency in two ways. First, this improves resource utilization for applications with small alphabets and enables hardware acceleration for applications with very large alphabets (which otherwise would not map to hardware accelerators). Second, this enables the exploration of optimized bitwidth processing for future spatial hardware accelerators. We leverage FlexAmata and investigate the hardware implications of different bitwidth processing rates on the two state-of-the-art spatial accelerators, Cache Automaton (CA) and FPGAs. Our exploration across a wide range of automata benchmarks reveals that 4-bit processing rate on CA and 16-bit processing rate

show abstract

“…To reduce cost of memory accesses, input symbols were loaded to shared memory [7,55], input data layout was changed [55] to avoid uncoalesced accesses, or vector loads were used [49]. Others used k-stride NFAs [8], which consume k bytes at a time, but can blow up the alphabet to |Σ| k . Some implementations place state transition tables in texture memory [49] or on-chip constant memory [7].…”

Section: Related Workmentioning

confidence: 99%

Why GPUs are Slow at Executing NFAs and How to Make them Faster

Liu

Pai

Jog

2020

Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Syste

View full text Add to dashboard Cite

Non-deterministic Finite Automata (NFA) are space-efficient finite state machines that have significant applications in domains such as pattern matching and data analytics. In this paper, we investigate why the Graphics Processing Unit (GPU)-a massively parallel computational device with the highest memory bandwidth available on generalpurpose processors-cannot efficiently execute NFAs. First, we identify excessive data movement in the GPU memory hierarchy and describe how to privatize reads effectively using GPU's on-chip memory hierarchy to reduce this excessive data movement. We also show that in several cases, indirect table lookups in NFAs can be eliminated by converting memory reads into computation, to further reduce the number of memory reads. Although our optimization techniques significantly alleviate these memory-related bottlenecks, a side effect of these techniques is the static assignment of work to cores. This leads to poor compute utilization, where GPU cores are wasted on idle NFA states. Therefore, we propose a new dynamic scheme that effectively balances compute utilization with reduced memory usage. Our combined optimizations provide a significant improvement over the previous state-ofthe-art GPU implementations of NFAs. Moreover, they enable current GPUs to outperform the domain-specific accelerator for NFAs (i.e., Automata Processor) across several applications while performing within an order of magnitude for the rest of the applications. CCS Concepts • Computing methodologies → Parallel algorithms; • Computer systems organization → Single instruction, multiple data; • Theory of computation → Formal languages and automata theory.

show abstract

Scalable Algorithms for NFA Multi-Striding and NFA-Based Deep Packet Inspection on GPUs

Cited by 23 publications

References 18 publications

Sleepiness and injury risk in emergency medical service workers in Taiwan

Sleepiness and injury risk in emergency medical service workers in Taiwan

FlexAmata: A Universal and Efficient Adaption of Applications to Spatial Automata Processing Accelerators

Why GPUs are Slow at Executing NFAs and How to Make them Faster

Contact Info

Product

Resources

About