Granular Traffic Analysis and Energy Modeling in NoC with Enhanced Data Transmission
Kulkarni Rashmi Manik1, S Arulselvi2, B Karthik3
1Kulkarni Rashmi Manik, Research Scholar, Department of ECE, Bharath Institute of Higher Education and Research, Chennai (Tamil Nadu), India.
2S.Arulselvi, Associate Professor, Department of ECE, Bharath Institute of Higher Education and Research, Chennai (Tamil Nadu), India.
3B.Karthik, Associate Professor, Department of ECE, Bharath Institute of Higher Education and Research, Chennai (Tamil Nadu), India.
Manuscript received on 07 March 2019 | Revised Manuscript received on 20 March 2019 | Manuscript published on 30 March 2019 | PP: 352-362 | Volume-8 Issue-5, March 2019 | Retrieval Number: E3296038519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Nowadays, all electronic gadgets and devices are in the race of most compact size and least power consumption. Along with it, we want device to do many jobs at a time. For that it needs to be laced with maximum computing power. CMP/Many core architectures are inn with this advancement. In CMP architectures, parallel task execution is done rather than executing task sequentially, as it is done in conventional programming. Network-on-chip (NoC) is the best approach for interconnecting complex CMP architectures. However, NoC consumes significant percentage of total power. Final objective is to design power efficient NoC. In CMP architecture, many data transfers are done simultaneously. It is required to evolve power saver NOC with unique task scheduling schemes. Our approach enhances network latency, network throughput along with energy reduction. It defines performance of the system with high speed transmission. It shows improvement in the system performance when experimented with various applications. Here, we concentrated on proper distribution of tasks and network traffic required for execution. One needs to balance between over and under utilization of resources. Analysis of both the cases is done in this article. Over utilization is injecting excess traffic in the network which leads to heat up problem. Under utilization is, PEs remaining idle for long time resulting in sluggish performance. Here we tried to list various innovative methods for saving network from reaching power wall. Energy modeling and granular traffic analysis gives us accurate estimation of device performance beforehand. Also, analysis is done for various topologies for different tasks.
Keyword: CMP, CWC, CWN, Energy Consumption Reduction, Network Latency, NoC, Network Throughput.
Scope of the Article: Information and Data Security