Parallelizing sparse Matrix Solve for SPICE circuit simulation using FPGAs
Authors:
- 1 December 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 97, 190-198
Abstract
Fine-grained dataflow processing of sparse matrix-solve computation (Ax¿ = b¿) in the SPICE circuit simulator can provide an order of magnitude performance improvement on modern FPGAs. Matrix solve is the dominant component of the simulator especially for large circuits and is invoked repeatedly during the simulation, once for every iteration. We process sparse-matrix computation generated from the SPICE-oriented KLU solver in dataflow fashion across multiple spatial floating-point operators coupled to high-bandwidth on-chip memories and interconnected by a low-latency network. Using this approach, we are able to show speedups of 1.2-64× (geometric mean of 8.8×) for a range of circuits and benchmark matrices when comparing double-precision implementations on a 250 MHz Xilinx Virtex-5 FPGA (65 nm) and an Intel Core i7 965 processor (45 nm).Keywords
This publication has 9 references indexed in Scilit:
- Towards reliable 5Gbps wave-pipelined and 3Gbps surfing interconnect in 65nm FPGAs2009
- Accelerating SPICE Model-Evaluation using FPGAs2009
- Parallel transistor level circuit simulation using domain decomposition methods2009
- Packet Switched vs. Time Multiplexed FPGA Overlay Networks2006
- Improved algorithms for hypergraph bipartitioning2002
- A parallel linear system solver for circuit simulation problemsNumerical Linear Algebra with Applications, 2000
- MonsoonACM SIGARCH Computer Architecture News, 1990
- Sparse Partial Pivoting in Time Proportional to Arithmetic OperationsSIAM Journal on Scientific and Statistical Computing, 1988
- The modified nodal approach to network analysisIEEE Transactions on Circuits and Systems, 1975