Evaluation of automatic parallelization algorithms to minimize speculative parallelism overheads: An experiment

Kumar, Sudhakar; Singh, Sunil K.; Aggarwal, Naveen; Aggarwal, Kriti

doi:10.1080/09720529.2021.1951435

Cited by 21 publications

(8 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several important contributions in automatic parallelization are highlighted in the publications 25,39 40 and, DOACROSS 41 have been discussed among different automatic parallelization techniques as they are widely used in practice due to their less complexity.…”

Section: Related Workmentioning

confidence: 99%

“…Several important contributions in automatic parallelization are highlighted in the publications. 25,39 In this section DOALL 40 and, DOACROSS 41 have been discussed among different automatic parallelization techniques as they are widely used in practice due to their less complexity. By applying speculative parallelism, techniques like DOALL (Figure 1) and DOACROSS (Figure 1), multicore architectures can easily be exploited.…”

Section: Automatic and Speculative Parallelizing Techniquesmentioning

confidence: 99%

“…23 Speculative execution is used to express speculative parallelism of an interactive intelligent system using KL1, a concurrent logic programming language. 24 Automatic parallelization 25,26 is parallelizing sequential code automatically making use of several processors in a shared memory multiprocessor computer at the same time by converting it into multithreaded and vectorized code. These processors can be in the form of multicore chip architecture (MCA), 25,27,28 with different cores on a single chip.…”

Section: Introductionmentioning

confidence: 99%

“…24 Automatic parallelization 25,26 is parallelizing sequential code automatically making use of several processors in a shared memory multiprocessor computer at the same time by converting it into multithreaded and vectorized code. These processors can be in the form of multicore chip architecture (MCA), 25,27,28 with different cores on a single chip. Fully automated parallelization of sequential program is challenging because it requires complex program analysis, and the best solution may be reliant on parameter values unknown at the time of compilation.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

An efficient hardware supported and parallelization architecture for intelligent systems to overcome speculative overheads

Kumar

Singh

Aggarwal³

et al. 2022

Int J of Intelligent Sys

Self Cite

View full text Add to dashboard Cite

In the last few decades, technology advancements have paved the way for the creation of intelligent and autonomous systems that utilize complex calculations which are both time‐consuming and central processing unit intensive. As a consequence, parallel processing systems are gaining popularity to enhance overall computer performance. Programmers should be able to efficiently utilize available hardware resources with parallelization in an ideal world. Through the automatic parallelization of sequential code, multithreading can be executed without extra supervision. However, a wide range of software dependencies prevents this from being feasible. An architectural framework for speculative parallelization along with an efficient memory analysis and computational algorithms for the code generation are proposed that can provide optimal performance. Furthermore, a suitable support of hardware design as a runtime library to the proposed architectural framework is presented which can be used to recover misspeculated results during execution to minimize speculative parallelism overhead. The implementation makes use of the Low‐Level Virtual Machine compiler infrastructure and is tested on numerous benchmarks, thus making it highly scalable in terms of programming languages and architectures. According to our experimental results, there is significant potential for speedup increase. In comparison to the overall function speedup, that is, geomean speedup of 5.2× approximately when using the proposed architecture without hardware support, the proposed architectural framework and algorithm with hardware support give an average geomean speedup of 7.0× approximately on the given benchmark which is written in C/C++.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Automatic and Speculative Parallelizing Techniquesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

An efficient hardware supported and parallelization architecture for intelligent systems to overcome speculative overheads

Kumar

Singh

Aggarwal³

et al. 2022

Int J of Intelligent Sys

Self Cite

View full text Add to dashboard Cite

show abstract

“…The proposed advanced hardware-supported and parallelization architecture, designed for intelligent systems, offers improved computational capabilities that align with the objectives of implementing robust fault tolerance models in Peer-to-Peer networks [29]. Additionally, when integrated with a groundbreaking decentralized group key management scheme tailored for cloud-based vehicular IoT networks, it fortifies security measures and enhances the resilience and self-healing mechanisms within distributed P2P infrastructures [30] [18].…”

Section: Introductionmentioning

confidence: 99%

Adaptive Stochastic Fault Tolerance for Self-Healing P2P Networks

Kumar,

Goyal,

Singh

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

In the complex domain of reliable and flexible distributed systems, the challenging issue of Byzantine fault resilience is pervasive, particularly within the intricate framework of Peer-to-Peer (P2P) networks. The 'Adaptive Stochastic Fault Tolerance for Self-Healing P2P Networks' proposes a novel approach to self-healing in distributed peer-to-peer (P2P) systems. It combines ideas from stochastic Byzantine fault tolerance models with adaptive resilience strategies to detect and recover from failures within these complex networks by using probabilistic modeling. This allows P2P systems to adjust their resilience measures in real-time, effectively shielding themselves from unforeseen faults. Furthermore, the research provides extensive experimentation and empirical validation to demonstrate the effectiveness of the proposed approach.

show abstract

Deep Learning in Robotics for Strengthening Industry 4.0.: Opportunities, Challenges and Future Directions

Aggarwal

Singh

Chopra

et al. 2022

Studies in Computational Intelligence

View full text Add to dashboard Cite

Evaluation of automatic parallelization algorithms to minimize speculative parallelism overheads: An experiment

Cited by 21 publications

References 7 publications

An efficient hardware supported and parallelization architecture for intelligent systems to overcome speculative overheads

An efficient hardware supported and parallelization architecture for intelligent systems to overcome speculative overheads

Adaptive Stochastic Fault Tolerance for Self-Healing P2P Networks

Deep Learning in Robotics for Strengthening Industry 4.0.: Opportunities, Challenges and Future Directions

Contact Info

Product

Resources

About