International Journal of Enhanced Research in Management & Computer Applications, ISSN: 2319-7471 Vol. 2 Issue 8, Sept.-Oct., 2013, pp: (17-23), Available online at: www.erpublications.com Page | 17 A review on microprocessor with multi-core Anil Kumar 1 , Anil Saini 2 1,2 Assistant Professor, Dept. of Computer Science & Applications Kurukshetra University, Kurukshetra, Haryana, India ABSTRACT: As we know that Microprocessors is a device which can perform the operation in microseconds. Each generation of processors grows a small type, but faster dissipated more heat and more consumed the power. A number of techniques such as data levels of parallelism, instruction levels of parallelism, thread level parallelism and simultaneous multi threading (SMT) already exists which make the big improvement in the performance of microprocessor cores. This paper present evolution of different types of microprocessor and multi-core processor followed by introducing the technologies and its advantages in modern world and also explain the currently challenges faced by multi-core processors and microprocessors. KEYWORDS: Microprocessor, Core Processors, multi threading technologies, software challenges hardware parallelism, and High performance computing (HPC), SMT. 1. INTRODUCTION The Industry of microprocessor continues to have great valuable in the course of technological advancements since their existence in 1970s [1]. The improving market and the demand for faster performance drove the industry to manufacture faster and smarter chips. One of the most classical and given techniques to improve performance is to clock the chip at higher frequency which enables the processor to execute the programs in a much quicker time [2, 3] and the industry has been following this trend from 1983– 2002 [4]. Additional techniques have also been devised to improve performance including parallel processing, data level parallelism and instruction level parallelism which have all proven to be very effective [5]. One such technique which improves significant performance boost is multi-core processors. Multi-core processors have been in existence since the past decade. Around 1945, mathematician John von Neumann with John Mauchly creating of an Electronic Discrete Variable Automatic Computer, more famously known as the EDVAC. The Von Neumann suggested the stored-program model of computing. In the architecture of von Neumann, the sequence of instructions is known as program which is stored sequentially in the memory of computer. The program‟s instructions are executed one after the other in a linear format; single-threaded manner [7]. At present Von Neumann architectures are widely used class of architectures because of their relative simplicity and effectiveness for general computation tasks like in architecture family of IBM series [6]. As time went on, advancements in mainframe technology expanded upon the ideas presented by von Neumann. In the 1960s saw the advent of time- sharing operating systems. Run on large mainframe computers, these operating systems first introduced the concept of concurrent execution of program. Many numbers of users could access simultaneously a single mainframe computer and submit jobs for processing. The operating system handled the details of allocating Central Processing Units (CPU) time for each individual program. At this time, concurrency existed at the processing level, and this type of job of task switching was left to the systems making programmer [1]. 2. EVOLUTION OF MULTI-CORE PROCESSOR The microprocessors have always been designed for their performance and cost keeping in mind. Gordon Moore who was the founder of Intel Corporation predicted that the number of transistors on a chip will almost be double once in every two year to meet this ever growing demand which is popularly known as Moore‟s Law in the semiconductor industry [3, 9, 10]. In present days the integrated circuit processing technology increasing integration density which has made it possible to integrate one billion transistors on a single chip for the improved performance [8,11]. However, the performance increase by micro-architecture governed by Pollack‟s rule is roughly proportional to square root of increase in complexity [12]. This would mean that doubling the logic on a processor core would only improve the performance by 42%. In advanced fabrication chip techniques there is big problem of bottleneck, power dissipation issues. From studied on it we can say that the transistor leakage current increases as the chip size reduced further and it will increases the static power dissipation to large values as shown in figure1 below [12, 13]. There is one change means to improve the performance and is to increase the frequency of operation which makes it fast execution of programs [3, 10]. As we increases the frequency beyond this limit it will increases power dissipation again [1].