Devi, Anant and Gandhi, Maulik and Varghese, Kuruvilla and Gope, Dipanjan (2013) Hardware Accelerator for 3D Method of Moments based Parasitic Extraction. In: IEEE Electrical Design of Advanced Packaging and Systems Symposium (EDAPS), DEC 12-15, 2013, Nara, JAPAN, pp. 100-103.
PDF
iee_ele_des_adv_pac_sys_sym_100_2013.pdf - Published Version Restricted to Registered users only Download (422kB) | Request a copy |
Abstract
A Field Programmable Gate Array (FPGA) based hardware accelerator for multi-conductor parasitic capacitance extraction, using Method of Moments (MoM), is presented in this paper. Due to the prohibitive cost of solving a dense algebraic system formed by MoM, linear complexity fast solver algorithms have been developed in the past to expedite the matrix-vector product computation in a Krylov sub-space based iterative solver framework. However, as the number of conductors in a system increases leading to a corresponding increase in the number of right-hand-side (RHS) vectors, the computational cost for multiple matrix-vector products present a time bottleneck, especially for ill-conditioned system matrices. In this work, an FPGA based hardware implementation is proposed to parallelize the iterative matrix solution for multiple RHS vectors in a low-rank compression based fast solver scheme. The method is applied to accelerate electrostatic parasitic capacitance extraction of multiple conductors in a Ball Grid Array (BGA) package. Speed-ups up to 13x over equivalent software implementation on an Intel Core i5 processor for dense matrix-vector products and 12x for QR compressed matrix-vector products is achieved using a Virtex-6 XC6VLX240T FPGA on Xilinx's ML605 board.
Item Type: | Conference Proceedings |
---|---|
Additional Information: | Copyright for this article belongs to the IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA |
Department/Centre: | Division of Electrical Sciences > Electronic Systems Engineering (Formerly Centre for Electronic Design & Technology) |
Date Deposited: | 13 Jan 2015 05:14 |
Last Modified: | 13 Jan 2015 05:14 |
URI: | http://eprints.iisc.ac.in/id/eprint/50657 |
Actions (login required)
View Item |