SC20 Is Everywhere We Are

SC20 Virtual Platform
An Integer Arithmetic-Based Sparse Linear Solver Using a GMRES Method and Iterative Refinement
Event Type
Workshop
Tags
Algorithms
Extreme Scale Computing
Performance/Productivity Measurement and Evaluation
Scalable Computing
Scientific Computing
Registration Categories
W
TimeThursday, 12 November 202011am - 11:25am EDT
LocationTrack 8
DescriptionIn this paper, we develop a (preconditioned) GMRES solver based on integer arithmetic, and introduce an iterative refinement framework for the solver. We describe the data format for the coefficient matrix and vectors for the solver that is based on integer or fixed-point numbers.
To avoid overflow in calculations, we introduce initial scaling and logical shifts (adjustments) of operands in arithmetic operations. We present the approach operand shifts, considering the characteristics of the GMRES algorithm. Numerical tests demonstrate that the integer arithmetic-based solver with iterative refinement has comparable solver performance in terms of convergence to the standard solver based on floating-point arithmetic. Moreover, we show that preconditioning is important, not only for improving convergence but also reducing the risk of overflow.
Back To Top Button