FPGA Fabric Specific Optimization for RTL Design

Aqib Perwaiz, Hamid M kamboh, Shoab A Khan

Abstract


This paper proposes a technique custom to the optimization requirements suited for a particular family of Field Programmable Gate Arrays (FPGAs). As FPGAs have introduced reconfigurable black boxes there is a need to perform optimization across FPGAs slice fabric in order to achieve optimum performance. Though the Register Transfer Level (RTL) Hardware Descriptive Language (HDL) code should be technology independent but in many design instances it is imperative to understand the target technology especially once the target device embeds dedicated arithmetic blocks. No matter what the degree of optimization of the algorithm is, the configuration of target device plays an important role as far as the device utilization and path delays are concerned

Full Text:

PDF

References


Xcell Journal “Achieve high performance with vertex 5 FPGA”,fourth quarter 2006.

K.Satoh, J.Tada, H.Yanagida, and Y.tamura,”Parallel Image Reconstruction Operation By dedicated Hardware for three Dimensional Ultrasound Imaging”,pp.1522-1525, Proc of IEEE UFFC, Nov. 2007

Keshab.k.parhi, “Pipelined and parallel recursive and adaptive filters” chapter 10 of pipelined adaptive digital filters

Keshab.k.parhi, “Bit level Arithmetic architectures” chapter 13 of pipelined adaptive digital filters

Vojin G. Oklobodzija, “The Computer Engineering Handbook”, CRC Press

Anna Kuncheva and George Yanchev, “ Synthesis and implementation of DSP Algorithm in Advanced Programmable architectures” Proc of ISCCS 2008.

Antoli Sergyienko, Volodymir Lepekha, Juri Kanevski and Przemyslaw Soltan, “ Implementation Of IIR Digital Filters In FPGA” Poland.

Shanthala S and S.Y.Kulkarni, “Hight speed and low power FPGA Implementation Of FIR Filter for DSP Applications”,European Jounral of scientific research ISSN 1450-216x Vol.31 No.1(2009), PP. 19-28.

Xilinx Co.,:Xcell journal vol.58.59”,2007 Spring.

D.Phanthavong,”Designing with dsp 48 blocks using precision synthesis,”Xcell Journal, 2005.

Ki-seon Cho, Jong, Jin Seok, Goang Choi, “54x54 bit Radix 4 Multiplier based on modified booth algorithm”, ACM 2003 1-58113-677.

Aqib Perwaiz and Shoab .A .Khan “ Effect of Bit Precision on hardware complexity for DDFS architecture”, IEEE Conference






Copyright (c) 2016 Aqib Perwaiz, Shoab A Khan, Hamid M kamboh

Powered By KICS