A Low-Power Multithreaded Processor for Software Defined Radio.

Journal of VLSI Signal Processing (Impact Factor: 0.73). 06/2006; 43:143-159. DOI: 10.1007/s11265-006-7267-1
Source: DBLP

ABSTRACT Embedded digital signal processors for software defined radio have stringent design constraints including high computational
bandwidth, low power consumption, and low interrupt latency. Furthermore, due to rapidly evolving communication standards
with increasing code complexity, these processors must be compiler-friendly, so that code for them can quickly be developed
in a high-level language. In this paper, we present the design of the Sandblaster Processor, a low-power multithreaded digital
signal processor for software defined radio. The processor uses a unique combination of token triggered threading, powerful
compound instructions, and SIMD vector operations to provide real-time baseband processing capabilities with very low power
consumption. We describe the processor’s architecture and microarchitecture, along with various techniques for achieving high
performance and low power dissipation. We also describe the processor’s programming environment and the SB3010 platform, a
complete system-on-chip solution for software defined radio. Using a super-computer class vectorizing compiler, the SB3010
achieves real-time performance in software on a variety of communication protocols including 802.11b, GPS, AM/FM radio, Bluetooth,
GPRS, and WCDMA. In addition to providing a programmable platform for SDR, the processor also provides efficient support for
a wide variety of digital signal processing and multimedia applications.

1 Bookmark
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Implementation of embedded systems-on-chip on modern field programmable gate arrays (FPGAs) chip is doable due to its large density. Architecture of multilevel computing focusing on its embedded processor is suggested in our project. The architecture design of embedded processor presents the challenges and opportunities that stem from the task coarse granularity and the large number of input and output for each task. Thus, we have designed a new architecture called Embedded Concurrent Computing (ECC). The entire embedded processor architecture is implemented on the FPGA chip using VHDL. We have synthesized and evaluated the embedded system based on an Altera environment by using a DE2 board. The performances of a realistic application show scalable speedups comparable to that of the simulation. Furthermore, the results show the accuracy of Extended Kalman Filter (EKF) rather than the Kalman Filter (KF) in identifying the landmarks and target in underwater environment, and the usefulness of the multiple filtering techniques when the nonlinearities are too large due to linearization errors. We believe that implementation has been achieved in providing low complexity in terms of FPGA resource usage and frequency. In addition, the design methodology allows the embedded processor to be scalable as the entire system grows.
    Signal and Image Processing Applications (ICSIPA), 2009 IEEE International Conference on; 01/2009
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: A stream is a sequence of similar data records with real-time throughput or bandwidth constraints attached to it. Examples include link-level en cryption in networks, video trans- coding, video compression, cellular telephony as well as the image and speech pA stream is a sequence of similar data records with real-time throughput or bandwidth constraints attached to it. Examples include link-level encryption in networks, video trans-coding, video compres- sion, cellular telephony as well as the image and speech processing. Stream programs consist of a data-flow network where the nodes called kernels represe nt simple algorithms that trans- form an input block to an output block with access to a limited amount of history. Stream processors are decoupled access/execute processors whose architecture has been optimized for the repeated application of stream computations to high bandwidth data-streams at very high levels of performance and energy efficiency. Stream processors have been extensively studied in academia by projects such as Stanford Imagine and MIT RAW. They made their commercial debut with the Cell, a broadband proces- sor from IBM that is the computing engine for the Sony PlayStation 3. The cellular telephony market has experienced rapid growth around the world and represents a significant opportunity for stream processors because this domain requires very hig h computation rates to reduce the bit error rate and to support high data rates, full motion vid eo and multimedia applications, and a variety of wireless standards. Simultaneously, they must also be energy efficient and flexible, have a low time to market, and be low cost. This article starts by providing an overview of the fundamental concepts behind stream processors, their applications to perception, media, wire less and scientific workloads, major research projects etc. It will elaborate on the nature of 3G a nd 4G wireless algorithms, archi- tectural approaches to optimize these algorithms as well as commercial processors that have been optimized for the wireless domain.
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: Software-defined radio (SDR) is an emerging technology that facilitates having multiple wireless communication protocols on one device. Previous work has shown that current W-CDMA, GPS, GSM, and WiMAX applications can run on this class of device while consuming significant processing power. Next generation wireless networks require speeds in excess of 50Mbps. Some of the fastest AES software im-plementations only achieve 20Mbps on our reference platform. In order to have secure software-defined radio, the security processing gap must be addressed. This paper presents instruction set architecture (ISA) extensions for the Sandblaster DSP. The Sandblaster DSP is a multithreaded processor for SDR that issues multiple operations each cycle and supports vector operations.
    International Journal of High Performance Systems Architecture 01/2010; 2.


Available from