The hardware-oriented algorithms for the fast Hauscholder transformation have been developed, and the methods for comparison of the basic characteristics in the hardware-oriented algorithms have been proposed. The use of the developed algorithms permits to decrease significantly (several times) the solution time of the linear algebra problems and to increase significantly the high-action of the computer systems. According to the order of the Open Type Joint-Stock Company "Volgogradneftegeofizika" the board-accelerator of the personal computer IBM PC/AT has been developed and manufactured. The board-accelerator permits to decrease 1,5 time the solution time of the linear algebra problems on the personal computerAvailable from VNTIC...
The work covers the algorithms and hardware for realization of the arrangement procedure. The aim is...
The object of investigation: the problem of mapping of the computing algorithms on the structure of ...
A branch of computer science dealing with algorithmic efficiency has developedfaster ways to execute...
The hardware-oriented algorithms for solution of the linear algebraic equation systems with real and...
The work is concerned with the power increase methods of the microprocessors. The aim of the work is...
In this paper we consider the data distribution and data movement issues related to the solution of ...
Colour correction algorithm plays an essential part in processing the colour information. Researches...
The paper presents the novel principle on constructing a new class of highly parallel fast stable nu...
Communicated by Yasuaki Ito Solution of large-scale dense nonsymmetric eigenvalue problem is require...
The work covers the algorithms of large mathematical operations for the spectral methods of solving ...
This thesis describes the design and implementation of high speed hardware chess modules which can b...
The work covers the dicrete linear transformations. The aim is to develop and investigate the class ...
The work covers the software for the image processing systems on base of support software system wit...
The objective of high performance computing (HPC) is to ensure that the computational power of hardw...
. Some details of arithmetic of two representatives of computers (a superscalar workstation and a ve...
The work covers the algorithms and hardware for realization of the arrangement procedure. The aim is...
The object of investigation: the problem of mapping of the computing algorithms on the structure of ...
A branch of computer science dealing with algorithmic efficiency has developedfaster ways to execute...
The hardware-oriented algorithms for solution of the linear algebraic equation systems with real and...
The work is concerned with the power increase methods of the microprocessors. The aim of the work is...
In this paper we consider the data distribution and data movement issues related to the solution of ...
Colour correction algorithm plays an essential part in processing the colour information. Researches...
The paper presents the novel principle on constructing a new class of highly parallel fast stable nu...
Communicated by Yasuaki Ito Solution of large-scale dense nonsymmetric eigenvalue problem is require...
The work covers the algorithms of large mathematical operations for the spectral methods of solving ...
This thesis describes the design and implementation of high speed hardware chess modules which can b...
The work covers the dicrete linear transformations. The aim is to develop and investigate the class ...
The work covers the software for the image processing systems on base of support software system wit...
The objective of high performance computing (HPC) is to ensure that the computational power of hardw...
. Some details of arithmetic of two representatives of computers (a superscalar workstation and a ve...
The work covers the algorithms and hardware for realization of the arrangement procedure. The aim is...
The object of investigation: the problem of mapping of the computing algorithms on the structure of ...
A branch of computer science dealing with algorithmic efficiency has developedfaster ways to execute...