Mathematical Model of Energy Consumption of A Hierarchical Shared Bus Interconnection Communication Network of an On-Chip Multiprocessor

نویسندگان

  • Oladayo O. Olakanmi
  • Adeboye Olatunbosun
چکیده

Energy consumption is one of the performance issues in multiprocessor design. Apart from being critical for power critical systems, it determines the amount of heat dissipates by the system. That is, as the energy consumption rate reduces heat dissipation reduces. Many research efforts had gone into the different design schemes for reducing multiprocessors’ energy consumption. However, it has been observed that there is a distinct relationship between energy consumed and the interconnection network engaged by the multiprocessors. In this paper, an energy consumption model was developed for a bus based interconnection network multiprocessor. The model established a linear relationship between bit energy of multiprocessor shared bus interconnection network and length of the bus covered during the bus cycle. This was used to obtain the maximum energy and bit energy consumed by the multiprocessor. The obtained bit energy (Pwbit) was compared with the bit energy of other interconnection networks in order to determine and evaluate the interconnection network which consumes least energy during bits transition. The bit energy obtained (2.45x1021 J) for the hierarchical shared bus interconnection network was much lower than the results reported for Crossbar (2.2 x 10-13 J), Banyan 2x2 (1.1 x 10-12 J), Batcher 2x2 (1.2 x 10-12 J), Banyan 4x4 (1.4 x 10-14 J), Banyan 16x16 (1.5 x 10-14 J) and Banyan 32x32 (2.2 x 10-14 J) interconnection networks. This indicates that the use of hierarchical shared bus interconnection network in the multiprocessor reduces its energy consumption. Keyword: Energy consumption; multiprocessor; interconnection network (IN); shared bus

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Interconnection between Peripherals in SoC'S Using CDMA Technique

NoC (network On Chip) is an efficient approach to design the communication subsystem between IP Cores in SoC (System On Chip). In this paper a communication infrastructure design using CDMA (Code division multiple access) based shared bus architecture for core-to-core communication in NoC is presented. CDMA has been proposed as an alternative way for interconnect of IP cores in a SoC design, or...

متن کامل

Performance Analysis of a New Neural Network for Routing in Mesh Interconnection Networks

Routing is one of the basic parts of a message passing multiprocessor system. The routing procedure has a great impact on the efficiency of a system. Neural algorithms that are currently in use for computer networks require a large number of neurons. If a specific topology of a multiprocessor network is considered, the number of neurons can be reduced. In this paper a new recurrent neural ne...

متن کامل

Performance Analysis of a New Neural Network for Routing in Mesh Interconnection Networks

Routing is one of the basic parts of a message passing multiprocessor system. The routing procedure has a great impact on the efficiency of a system. Neural algorithms that are currently in use for computer networks require a large number of neurons. If a specific topology of a multiprocessor network is considered, the number of neurons can be reduced. In this paper a new recurrent neural ne...

متن کامل

Merging, sorting and matrix operations on the SOME-Bus multiprocessor architecture

Due to advances in fiber-optics and VLSI technology, interconnection networks which allow multiple simultaneous broadcasts are becoming feasible. This paper presents the multiprocessor architecture of the Simultaneous Optical Multiprocessor Exchange Bus (SOME-Bus), and examines the performance of representative algorithms for matrix operations, merging and sorting, using the message-passing and...

متن کامل

Distributed-Shared-Memory Support on the Simultaneous Optical Multiprocessor Exchange Bus

This paper examines the performance of distributed-shared-memory systems based on the Simultaneous Optical Multiprocessor Exchange Bus (SOME-Bus) using queueing network models and develops theoretical results which predict processor utilization, message latency and other useful measures. It also presents simulation results which compare the performance of the SOME-Bus, the mesh and the torus us...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2017