Design and evaluation of correlation accelerator in IEEE-802.11a/g receiver using a template-based Coarse-Grained Reconfigurable Array
- 1 October 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-6
Abstract
This paper presents the design and evaluation of a large scale template-based Coarse-Grained Reconfigurable Array (CGRA) generated accelerator that processes correlation algorithm for Timing Synchronization (TS) required in Orthogonal Frequency-Division Multiplexing (OFDM) receivers. The CGRA works as a coprocessor with a Reduced Instruction-Set Computing (RISC) processor. The CGRA accelerator is composed of 80 reconfigurable Processing Elements (PEs) to compute 80-point correlation in 1.8 μs when synthesized on an Field Programmable Gate Array (FPGA). The power consumption is estimated by simulating the postfit gate-level FPGA netlist of the TS accelerator followed by evaluation and comparison with other state-of-the-art platforms in terms of multiple performance metrics.Keywords
This publication has 15 references indexed in Scilit:
- Energy and power estimation of Coarse-Grain Reconfigurable Array based Fast Fourier Transform accelerators2012
- Evaluation of Radix-2 and Radix-4 FFT processing on a reconfigurable platform2010
- Systolic Algorithm Mapping for Coarse Grained Reconfigurable Array Architectures2010
- CREMA: A coarse-grain reconfigurable array with mapping adaptiveness2009
- A coarse-grain reconfigurable architecture for multimedia applications featuring subword computation capabilitiesJournal of Real-Time Image Processing, 2008
- A dedicated DMA logic addressing a time multiplexed memory to reduce the effects of the system bus bottleneck2008
- Measuring the Gap Between FPGAs and ASICsIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 2007
- General-Purpose Embedded Processor Cores – The COFFEE RISC Example2007
- ADRES: An Architecture with Tightly Coupled VLIW Processor and Coarse-Grained Reconfigurable Matrix2003
- PACT XPP—A Self-Reconfigurable Data Processing ArchitectureThe Journal of Supercomputing, 2003