Ultra-Low-Energy DSP Processor Design for Many-Core Parallel Applications
نویسندگان
چکیده مقاله:
Background and Objectives: Digital signal processors are widely used in energy constrained applications in which battery lifetime is a critical concern. Accordingly, designing ultra-low-energy processors is a major concern. In this work and in the first step, we propose a sub-threshold DSP processor. Methods: As our baseline architecture, we use a modified version of an existing ultra-low-power general purpose processor. Afterwards, we make some modifications to add new instructions to the processor instruction set for better adapting to signal processing applications. In the second step, employing sub-threshold cores in many-core architectures, we use the proposed processor as simple basic cores in a many-core architecture. Results: In comparison with the baseline architecture, these modifications reduce the program memory size about 42% in average. In addition, data memory accesses are reduced about 60% in average, and more than 90% speed-up is achieved. According to the improvements in total execution time (93%) and power consumption (27%), the total consumed energy is reduced about 95% in average with at most 2.6% area overhead and without increasing the process variation effects on processor specifications. Conclusion: The results show that for parallel applications, such as FFT in LTE standard, exploiting sub-threshold processors in a many-core architecture not only can satisfy the required performance, but also reduce the power consumption about 50% or even more.
منابع مشابه
DSP Processor Core-Based Wireless System Design
This thesis considers the design of wireless communications systems which are implemented as highly integrated embedded systems comprised of a mixture of hardware components and software. An introductionary part presents digital communications systems, classification of processors, programmable digital signal processing (DSP) processors, and development and implementation of a flexible DSP proc...
متن کاملEnergy-efficient Fine-grained Many-core Architecture for Video and DSP Applications
Many-core processor architecture has become the most promising computer architecture. However, how to utilize the extra system performance for real applications such as video encoding is still challenging. This dissertation investigates architecture design, physical implementation and performance evaluation of a fine-grained many-core processor for advanced video coding with a focus on intercon...
متن کاملLow Overhead Memory Subsystem Design for a Multicore Parallel DSP Processor
The physical scaling following Moore’s law is saturated while the requirement on computing keeps growing. The gain from improving silicon technology is only the shrinking of the silicon area, and the speedpower scaling has almost stopped in the last two years. It calls for new parallel computing architectures and new parallel programming methods. Traditional ASIC (Application Specific Integrate...
متن کاملDSP engine for ultra-low-power audio applications
An ultra-low-power DSP decimation/interpolation structure is described demonstrating how algorithmic and architectural schemes were employed for ultimate power efficiency in a DSP based chip set for audio applications. This circuit was designed and synthesised for a low VT 0.35 m CMOS process allowing Nyquist rate signals to be decimated from a high OSR frontend and interpolation post voice pro...
متن کاملCustomization of a CISC Processor Core for Low-Power Applications
This paper describes a core-customization process of a CISC processor core for a given application program. It aims at the power reduction in the CISC processor core by fully utilizing the microcode-based control scheme, that is one of the most characterizing features of a CISC processor. The optimization process includes two key techniques, generation of application-specific complex instructio...
متن کاملMany-Core Architecture Oriented Parallel Algorithm Design for Computer Animation
Many-core architecture has become an emerging and widely adopted platform for parallel computing. Computer animation researches can harness this advance in high performance computing with better understanding of the architecture and careful consideration of several important parallel algorithm design issues, such as computation-to-core mapping, load balancing and algorithm design paradigms. In ...
متن کاملمنابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ذخیره در منابع من قبلا به منابع من ذحیره شده{@ msg_add @}
عنوان ژورنال
دوره 8 شماره 1
صفحات 71- 84
تاریخ انتشار 2019-12-20
با دنبال کردن یک ژورنال هنگامی که شماره جدید این ژورنال منتشر می شود به شما از طریق ایمیل اطلاع داده می شود.
میزبانی شده توسط پلتفرم ابری doprax.com
copyright © 2015-2023