Algorithmic foundation for benchmarking of computational platforms running asymmetric cipher systems

Abstract

The 0–1 Knapsack Problem is a well known NP-complete problem. It is used as the core primitive in several asymmetric cipher systems. Designing such systems requires a reliable method of computational platform benchmarking. But the existing general-purpose benchmarks are not accurate enough, as they are mostly based on floating-point arith-metics, while the Knapsack Problem relies on large amount of calculations with very long integers. Therefore, a new specialized benchmark is required to get accurate performance estimates. In this paper we study some features of exact parallel algorithms for the Knapsack Problem, as well as load balancing techniques for them. We then choose several algorithms based on their scalability and applicability to the asymmetric cipher system analysis and suggest a new algorithmic foundation for computational platform benchmarking comprised of these algorithms.