This paper presents a new superscalar architecture for fast discrete cosine transform (DCT). Comparing with the general SIMD architecture, it speeds up the DCT computation by a fac...
The problem of evaluating the dominant eigenvalue of real matrices using Monte Carlo numerical methods is considered. Three almost optimal Monte Carlo algorithms are presented:
Ivan Dimov, Vassil N. Alexandrov, Aneta Karaivanov...
Abstract— Most image processing applications are characterized by computation-intensive operations, and high memory and performance requirements. Parallelized implementation on s...
Current microprocessor instruction set architectures are word oriented, with some subword support. Many important applications, however, can realize substantial performance benefi...
The paper presents a concept, implementation and real examples of dynamic parallelization of computations using services derived from MPI applications deployed in the BeesyCluster ...