A complete implementation of the conjugate gradient algorithm on a reconfigurable supercomputer
- Los Alamos National Laboratory
- ORNL
The conjugate gradient is a prominent iterative method for solving systems of sparse linear equations. Large-scale scientific applications often utilize a conjugate gradient solver at their computational core. In this paper we present a field programmable gate array (FPGA) based implementation of a double precision, non-preconditioned, conjugate gradient solver for fmite-element or finite-difference methods. OUf work utilizes the SRC Computers, Inc. MAPStation hardware platform along with the 'Carte' software programming environment to ease the programming workload when working with the hybrid (CPUIFPGA) environment. The implementation is designed to handle large sparse matrices of up to order N x N where N <= 116,394, with up to 7 non-zero, 64-bit elements per sparse row. This implementation utilizes an optimized sparse matrix-vector multiply operation which is critical for obtaining high performance. Direct parallel implementations of loop unrolling and loop fusion are utilized to extract performance from the various vector/matrix operations. Rather than utilize the FPGA devices as function off-load accelerators, our implementation uses the FPGAs to implement the core conjugate gradient algorithm. Measured run-time performance data is presented comparing the FPGA implementation to a software-only version showing that the FPGA can outperform processors running up to 30x the clock rate. In conclusion we take a look at the new SRC-7 system and estimate the performance of this algorithm on that architecture.
- Research Organization:
- Los Alamos National Laboratory (LANL)
- Sponsoring Organization:
- DOE
- DOE Contract Number:
- AC52-06NA25396
- OSTI ID:
- 957777
- Report Number(s):
- LA-UR-08-04599; LA-UR-08-4599
- Journal Information:
- Journal: ACM TRETS (Transactions on Reconfigurable Tech and Systems and Systems), Journal Name: Journal: ACM TRETS (Transactions on Reconfigurable Tech and Systems and Systems)
- Country of Publication:
- United States
- Language:
- English
Similar Records
Non-preconditioned conjugate gradient on cell and FPGA based hybrid supercomputer nodes
Non-preconditioned conjugate gradient on cell and FPCA-based hybrid supercomputer nodes