...
首页> 外文期刊>International Journal of Innovative Research in Science, Engineering and Technology >DESIGN AND COMPARISON OF RISC PROCESSORS USING DIFFERENT ALU ARCHITECTURES
【24h】

DESIGN AND COMPARISON OF RISC PROCESSORS USING DIFFERENT ALU ARCHITECTURES

机译:使用不同的ALU架构设计和比较风险处理器

获取原文
   

获取外文期刊封面封底 >>

       

摘要

Building low-power, high speed systems have been in demand, in recent years, because of the fast growing technologies in mobile communication and computation. Arithmetic and Logic Unit is a core component of almost all computing machines and processors. This work involves the design and comparison of 3 different 16 bit RISC processors based on 3 different ALU architectures. The ALU architectures are differentiated based on consumer requirements, keeping in mind cost, speed and power. Comparisons are done on aspects of area occupied, speed and power consumption. The first ALU design is an economical design, less complex and low power. The second design is a high speed, low power model using Carry Look-Ahead Adders (CLAs) and Vedic multiplier. Extensive parallelism is seen in them. The third design is targeted for low power and compactness and uses Prefix adders and Booth multiplier. The design of the RISC processors also involves the design of memory and development of opcodes which are also included in this work. A typical RISC based program on circular convolution has been implemented on all of these for comparison purposes. Results prove that ALU2 is the fastest and also consumes very less power. It is 15% faster than ALU1 but also occupies 20% more area. ALU3 occupies 30% lesser area than ALU1 and is a low power model. Though moderate in performance, ALU1 is the easiest to design.
机译:近年来,由于移动通信和计算技术的快速发展,对构建低功耗,高速系统的需求不断增加。算术和逻辑单元是几乎所有计算机和处理器的核心组件。这项工作涉及基于3种不同的ALU架构的3种不同的16位RISC处理器的设计和比较。 ALU架构根据消费者需求进行区分,同时要考虑成本,速度和功能。在占地面积,速度和功耗方面进行比较。第一个ALU设计是一种经济的设计,不那么复杂且功耗低。第二种设计是使用进位超前加法器(CLA)和Vedic乘法器的高速,低功耗模型。在它们中可以看到广泛的并行性。第三种设计的目标是低功耗和紧凑性,并使用前缀加法器和Booth乘法器。 RISC处理器的设计还涉及存储器的设计和操作码的开发,这些工作也包括在内。为了进行比较,已在所有这些程序上实现了一个典型的基于RISC的循环卷积程序。结果证明,ALU2是最快的,而且功耗也非常低。它比ALU1快15%,但面积也要多20%。 ALU3的面积比ALU1小30%,是一种低功耗型号。尽管性能适中,但ALU1是最容易设计的。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号