scholarly journals Thread-Aware Mechanism to Enhance Inter-Node Load Balancing for Multithreaded Applications on NUMA Systems

2021 ◽  
Vol 11 (14) ◽  
pp. 6486
Author(s):  
Mei-Ling Chiang ◽  
Wei-Lun Su
Keyword(s):  
Load Balancing ◽  
Critical Path ◽  
Selection Procedure ◽  
Remote Memory ◽  
Data Mapping ◽  
Linux Kernel ◽  
Access Memory ◽  
Selection Policy ◽  
Benchmark Suite ◽  
Thread Mapping

NUMA multi-core systems divide system resources into several nodes. When an imbalance in the load between cores occurs, the kernel scheduler’s load balancing mechanism then migrates threads between cores or across NUMA nodes. Remote memory access is required for a thread to access memory on the previous node, which degrades performance. Threads to be migrated must be selected effectively and efficiently since the related operations run in the critical path of the kernel scheduler. This study focuses on improving inter-node load balancing for multithreaded applications. We propose a thread-aware selection policy that considers the distribution of threads on nodes for each thread group while migrating one thread for inter-node load balancing. The thread is selected for which its thread group has the least exclusive thread distribution, and thread members are distributed more evenly on nodes. This has less influence on data mapping and thread mapping for the thread group. We further devise several enhancements to eliminate superfluous evaluations for multithreaded processes, so the selection procedure is more efficient. The experimental results for the commonly used PARSEC 3.0 benchmark suite show that the modified Linux kernel with the proposed selection policy increases performance by 10.7% compared with the unmodified Linux kernel.

Machine learning for load balancing in the Linux kernel

2020 ◽  
Author(s):  
Jingde Chen ◽  
Subho S. Banerjee ◽  
Zbigniew T. Kalbarczyk ◽  
Ravishankar K. Iyer
Keyword(s):  
Machine Learning ◽  
Load Balancing ◽  
Linux Kernel

scholarly journals Agent Based Load Balancing in Grid Computing

2020 ◽  
Author(s):  
Wided Ali ◽  
Fatima Bouakkaz
Keyword(s):  
Load Balancing ◽  
Heterogeneous Systems ◽  
Agent Based ◽  
Selection Policy ◽  
Development Framework ◽  
Policy Selection ◽  
Proposed Model ◽  
Multi Agent ◽  
Location Policy ◽  
System Characteristics

Load-Balancing is an important problem in distributed heterogeneous systems. In this paper, an Agent-based load-balancing model is developed for implementation in a grid environment. Load balancing is realized via migration of worker agents from overloaded resources to underloaded ones. The proposed model purposes to take benefit of the multi-agent system characteristics to create an autonomous system. The Agent-based load balancing model is implemented using JADE (Java Agent Development Framework) and Alea 2 as a grid simulator. The use of MAS is discussed, concerning the solutions adopted for gathering information policy, location policy, selection policy, worker agents migration, and load balancing.

An Implementation of Trusted Key Management Protocol (TKMP) in Wireless Network

2020 ◽  
Vol 17 (12) ◽  
pp. 5243-5249
Author(s):  
R. Jayaprakash ◽  
B. Radha
Keyword(s):  
Load Balancing ◽  
Wireless Network ◽  
Key Management ◽  
Secure Communication ◽  
Homomorphic Encryption ◽  
Selection Procedure ◽  
Communication Technologies ◽  
Path Selection ◽  
Management Protocol ◽  
Key Management Protocol

The Trusted Key Management Protocol (TKMP) provides one of the most secure communication technologies in MANET cluster-based data protection. For security reasons, TKMP is a trusted key that can be sent to all nodes in the communication cluster. This document introduces the Trusted Key Management Protocol (TKMP) feature to improve the quality of secure communications over a cluster-based wireless network. The proposed TKMP execution process includes CBPPRS (Cluster Based Privacy Preserving Routing Selection), LBCPR (Load Balancing Cluster Based Privacy Routing) and DLBPS (Dynamic Load Balancing Privacy Path Selection) procedure. To lock the data from the malicious node, the Paillier Cryptosystem (PC) encrypts packets with homomorphic encryption. The trust score makes it easier to update routing information and improves network throughput. The experimental results show that the proposed TKMP method works better than the other Trust-ECC method.

Improving Communication and Load Balancing with Thread Mapping in Manycore Systems

2018 ◽  
Author(s):  
Eduardo H.M. Cruz ◽  
Matthias Diener ◽  
Matheus S. Serpa ◽  
Philippe Olivier Alexandre Navaux ◽  
Laercio Pilla ◽  
...  
Keyword(s):  
Load Balancing ◽  
Thread Mapping

Enhancing the Lifetime of a Phase Change Memory with Bit-Flip Reversal

2020 ◽  
Vol 29 (14) ◽  
pp. 2050219
Author(s):  
Bhukya Krishna Priya ◽  
N. Ramasubramanian
Keyword(s):  
Phase Change ◽  
Phase Change Memory ◽  
Random Access ◽  
Data Encryption ◽  
Access Memory ◽  
Promising Alternative ◽  
Desirable Feature ◽  
Benchmark Suite ◽  
Bit Flip ◽  
Change Memory

Phase Change Memory (PCM) has evolved as a promising alternative over Dynamic Random Access Memory (DRAM) in terms of cell density and leakage power. While non-volatility is a desirable feature, it gives rise to the possibility of the data being present even after the power is switched off. To secure the data, encryption is normally done by using the standard Advanced Encryption Standard (AES) algorithm. Encrypting the data results in huge number of bit-flips, which reduces the lifetime of a PCM. The proposed method increases the lifetime of PCM by reducing the number of bit-flips occurred due to the encryption of modified words only and leaving the unmodified words as they are. The generated encrypted text, which is written by using the bit-flips reversal method, reduces the number of cells involved in writing by approximately 25%. This method is implemented by using Gem5 simulator and is evaluated with splash2 benchmark suite. It is observed that the proposed method improves the lifetime of a PCM memory by 15% without consuming extra power.

VBalance: A selection policy of virtual machines for load balancing in cloud computing

2015 ◽  
Author(s):  
Filipe Fernandes S B de Matos ◽  
Joaquim Celestino ◽  
Andre Ribeiro Cardoso
Keyword(s):  
Cloud Computing ◽  
Load Balancing ◽  
Virtual Machines ◽  
Selection Policy

AN INTERCONNECT ALLOCATION ALGORITHM FOR PERFORMANCE-DRIVEN DATAPATH SYNTHESIS

1996 ◽  
Vol 06 (04) ◽  
pp. 403-423
Author(s):  
YOUNG-NO KIM ◽  
HAE DONG LEE ◽  
SUN YOUNG HWANG
Keyword(s):  
Load Balancing ◽  
Data Transfer ◽  
Critical Path ◽  
Experimental Results ◽  
Transfer Time ◽  
Clock Period ◽  
Allocation Algorithm ◽  
Critical Paths ◽  
Communication Lines ◽  
A Performance

This paper presents the design of a performance-driven interconnect allocation algorithm. The proposed algorithm is based on the idea that the data transfer time can be reduced by balancing the load for specific hardware modules on possible critical path, such that the clock period can be minimized. By performing load balancing for only the communication lines on critical paths, the proposed algorithm generates interconnection structures with minimum delays. Experimental results confirm the effectiveness of the algorithm by constructing the interconnection structures with minimized clock periods for several benchmark circuits available from the literature.

Process Scheduling in Heterogeneous Multiprocessor Systems Using Task Duplication

2010 ◽  
Vol 6 (1) ◽  
pp. 58-69 ◽  
Author(s):  
Pranay Chaudhuri ◽  
Jeffrey Elcock
Keyword(s):  
Critical Path ◽  
Scheduling Algorithm ◽  
Multiprocessor System ◽  
Process Scheduling ◽  
Algorithm Selection ◽  
Alternative Scheduling ◽  
Selection Policy ◽  
Task Duplication ◽  
Earliest Finish Time ◽  
Heterogeneous Multiprocessor

Scheduling tasks in heterogeneous parallel and distributed computing environments continues to be a challenging problem. In this paper, the authors investigate the Heterogeneous Earliest Finish Time (HEFT) algorithm, along with alternative scheduling policies for task prioritising phases and the Critical Path on a Processor (CPOP) for scheduling tasks on a heterogeneous multiprocessor system. The authors show that by combining the HEFT algorithm selection policy with the task duplication strategy, it is possible to further reduce the schedule length produced by both HEFT and CPOP. The process scheduling algorithm presented in this paper compares favourably with other algorithms that use a similar strategy. The proposed algorithm has a time complexity of ?(¦V¦2(p + d)), whererepresents the number of tasks, p represents the number of processors and d the maximum in-degree of tasks.

An effective selection policy for load balancing in software DSM

2002 ◽  
Author(s):  
Tyng-Yeu Liang ◽  
Ce-Kuen Shieh ◽  
Jun-Qi Li
Keyword(s):  
Load Balancing ◽  
Selection Policy ◽  
Software Dsm ◽  
Effective Selection
Sign in / Sign up

Export Citation Format

Share Document