Arbitrary accuracy with variable precision arithmetic
Proceedings of the International Symposium on interval mathematics on Interval mathematics 1985
Implementation and test of the ACRITH facility in a system/370
IEEE Transactions on Computers
Programming parallel processors
Programming parallel processors
Hardware speedups in long integer multiplication
ACM SIGARCH Computer Architecture News - Symposium on parallel algorithms and architectures
A Fortran Multiple-Precision Arithmetic Package
ACM Transactions on Mathematical Software (TOMS)
Pascal-XSC: Language Reference with Examples
Pascal-XSC: Language Reference with Examples
Efficient High-Accuracy Computations in Massively Parallel Systems
PARA '94 Proceedings of the First International Workshop on Parallel Scientific Computing
Towards a High Precision Massively Parallel Computer
PARLE '94 Proceedings of the 6th International PARLE Conference on Parallel Architectures and Languages Europe
CADAC: A Controlled-Precision Decimal Arithmetic Unit
IEEE Transactions on Computers
| Hi-index | 0.00 |
The multiprecision arithmetic allows to reduce significantly the influence of rounding errors in cases when the standard data representation does not support the required accuracy. In this paper we discuss the technology of effective programming supporting the given accuracy of calculations in the suitable time by complex using the multiprecision arithmetic, dynamically changed length of operands, and parallel data processing. The distinguishing feature of proposed approach is that the initial high parallel algorithm can be adapted to the computations with the variable capacity of data. The library is described supporting this technology on parallel computers with message passing interface for communications. Some examples are presented of solution of typical problems.