Other

So Yamada

Nobuaki Miyakawa

Hajime Takashima

Kunihiro Kitamura

Shinjiro Inabata

Shigeru Obara

Takashi Amisaki

Matrix element calculation carried out efficiently without the overhead of communication between a host computer and processor elements even in parallel calculation utilizing a low-cost communication device and multiple processor elements having memories of a small capacity. In a method for calculating molecular orbitals, for example, all elements F(I, J) of a Fock matrix are calculated where an outermost loop is a loop associated with combinations (RT) of contracted shell R and contracted shell T which satisfy relationships R&lE;Nshell and T&lE;R. A second loop is a loop associated with contracted shell S, and a third loop is a loop associated with contracted shell U. Alternatively, the second loop is a loop associated with the contracted shell U, and the third loop is a loop associated with the contracted shell S. The value of S ranges from 1 to R, and the value of U ranges from 1 to R. Calculation of predetermined electron repulsion integrals and calculation of a predetermined part of Fock matrix elements utilizing the result of the calculation is carried out inside the third loop.

Method and apparatus for parallel processing

There is provided a parallel computer and a parallel computing method which allows high precision parallel calculation to be executed without requiring a hardware scale while maintaining high calculation speed. A system is constructed by connecting a host processor with a plurality of special purpose processors via buses. The host processor carries out the operation in a format of double-precision floating-point and the special purpose processor carries out the operation in an internal format of floating-point. The special purpose processor comprises an input data converting section for converting from the double-precision to the internal format and an output data converting section for converting from the internal format to the double-precision. Because the sign part and the exponent part can use data in common in the data before and after the conversion, only the mantissa part is converted by a specific procedure.

Parallel computer system and parallel computing method

Growing community of inventors

Nakai-machi, Japan

So Yamada