System-Level Design Space Exploration

B Sharat Chandra Varma, Kolin Paul, M Balakrishnan

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

In this chapter, we discuss the design space exploration carried out to accelerate de novo genome assembly using FPGAs. It is well known that as systems become more complex, one moves up the abstraction level for design space exploration through simulation. This is essential for managing complexity. Normally, higher abstraction levels imply faster and wider design space exploration but come at the price of lower accuracy. The focus of this chapter is on high-level design space exploration. The exploration was carried out at three levels. In this chapter, we propose modeling at three different levels: high-level algorithm model using ‘C’ followed by cycle-accurate model using System-C, and finally RTL component model using VHDL. We classify the parameters that can be studied using these three models.
LanguageEnglish
Title of host publicationArchitecture Exploration of FPGA Based Accelerators for BioInformatics Applications
Pages101-116
Number of pages16
Volume55
ISBN (Electronic)978-981-10-0591-6
DOIs
Publication statusPublished - 3 Mar 2016

Fingerprint

Computer hardware description languages
Field programmable gate arrays (FPGA)
Genes

Keywords

  • Processing Element
  • Clock Cycle
  • Critical Path
  • Hardware Implementation
  • Performance Number

Cite this

Varma, B. S. C., Paul, K., & Balakrishnan, M. (2016). System-Level Design Space Exploration. In Architecture Exploration of FPGA Based Accelerators for BioInformatics Applications (Vol. 55, pp. 101-116) https://doi.org/10.1007/978-981-10-0591-6_7
Varma, B Sharat Chandra ; Paul, Kolin ; Balakrishnan, M. / System-Level Design Space Exploration. Architecture Exploration of FPGA Based Accelerators for BioInformatics Applications. Vol. 55 2016. pp. 101-116
@inbook{ba6704aafe6e4ea5808f441554bd64a4,
title = "System-Level Design Space Exploration",
abstract = "In this chapter, we discuss the design space exploration carried out to accelerate de novo genome assembly using FPGAs. It is well known that as systems become more complex, one moves up the abstraction level for design space exploration through simulation. This is essential for managing complexity. Normally, higher abstraction levels imply faster and wider design space exploration but come at the price of lower accuracy. The focus of this chapter is on high-level design space exploration. The exploration was carried out at three levels. In this chapter, we propose modeling at three different levels: high-level algorithm model using ‘C’ followed by cycle-accurate model using System-C, and finally RTL component model using VHDL. We classify the parameters that can be studied using these three models.",
keywords = "Processing Element, Clock Cycle, Critical Path, Hardware Implementation, Performance Number",
author = "Varma, {B Sharat Chandra} and Kolin Paul and M Balakrishnan",
year = "2016",
month = "3",
day = "3",
doi = "10.1007/978-981-10-0591-6_7",
language = "English",
isbn = "978-981-10-0589-3",
volume = "55",
pages = "101--116",
booktitle = "Architecture Exploration of FPGA Based Accelerators for BioInformatics Applications",

}

Varma, BSC, Paul, K & Balakrishnan, M 2016, System-Level Design Space Exploration. in Architecture Exploration of FPGA Based Accelerators for BioInformatics Applications. vol. 55, pp. 101-116. https://doi.org/10.1007/978-981-10-0591-6_7

System-Level Design Space Exploration. / Varma, B Sharat Chandra; Paul, Kolin; Balakrishnan, M.

Architecture Exploration of FPGA Based Accelerators for BioInformatics Applications. Vol. 55 2016. p. 101-116.

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - System-Level Design Space Exploration

AU - Varma, B Sharat Chandra

AU - Paul, Kolin

AU - Balakrishnan, M

PY - 2016/3/3

Y1 - 2016/3/3

N2 - In this chapter, we discuss the design space exploration carried out to accelerate de novo genome assembly using FPGAs. It is well known that as systems become more complex, one moves up the abstraction level for design space exploration through simulation. This is essential for managing complexity. Normally, higher abstraction levels imply faster and wider design space exploration but come at the price of lower accuracy. The focus of this chapter is on high-level design space exploration. The exploration was carried out at three levels. In this chapter, we propose modeling at three different levels: high-level algorithm model using ‘C’ followed by cycle-accurate model using System-C, and finally RTL component model using VHDL. We classify the parameters that can be studied using these three models.

AB - In this chapter, we discuss the design space exploration carried out to accelerate de novo genome assembly using FPGAs. It is well known that as systems become more complex, one moves up the abstraction level for design space exploration through simulation. This is essential for managing complexity. Normally, higher abstraction levels imply faster and wider design space exploration but come at the price of lower accuracy. The focus of this chapter is on high-level design space exploration. The exploration was carried out at three levels. In this chapter, we propose modeling at three different levels: high-level algorithm model using ‘C’ followed by cycle-accurate model using System-C, and finally RTL component model using VHDL. We classify the parameters that can be studied using these three models.

KW - Processing Element

KW - Clock Cycle

KW - Critical Path

KW - Hardware Implementation

KW - Performance Number

U2 - 10.1007/978-981-10-0591-6_7

DO - 10.1007/978-981-10-0591-6_7

M3 - Chapter

SN - 978-981-10-0589-3

VL - 55

SP - 101

EP - 116

BT - Architecture Exploration of FPGA Based Accelerators for BioInformatics Applications

ER -

Varma BSC, Paul K, Balakrishnan M. System-Level Design Space Exploration. In Architecture Exploration of FPGA Based Accelerators for BioInformatics Applications. Vol. 55. 2016. p. 101-116 https://doi.org/10.1007/978-981-10-0591-6_7