公开(公告)号：US4621324A

公开(公告)日：1986-11-04

申请号：US562224

申请日：1983-12-16

申请人： Yasunori Ushiro ,  Shigeo Nagashima ,  Shun Kawabe

发明人： Yasunori Ushiro ,  Shigeo Nagashima ,  Shun Kawabe

IPC分类号： G06F17/16 ,  G06F15/80 ,  G06F13/00

CPC分类号： G06F15/8092

摘要： A vector processor provided wtih a vector register to set therein vector element data having been stored in a main storage, prior to a vector operation, is disclosed in which control information indicating whether new element data is read out from the main storage to be set in one location of the vector register capable of storing one vector element data and to be latched, or vector element data having been latched is set in the above location, is set in a mask register, for each location of the vector register, and the control information is successively read out from the mask register, to set vector element data in the vector register in accordance with the read-out control information.

摘要翻译： 向量处理器提供矢量寄存器以在其中设置已经存储在主存储器中的向量操作之前的向量元素数据，其中指示是否从主存储器读出新元素数据被设置在 对于矢量寄存器的每个位置，将能够存储一个矢量元素数据并被锁存的向量寄存器的一个位置或被锁存的向量元素数据设置在上述位置中，被设置在屏蔽寄存器中，并且控制 信息从掩模寄存器连续地读出，根据读出的控制信息在向量寄存器中设置矢量元素数据。

公开(公告)号：US5604911A

公开(公告)日：1997-02-18

申请号：US947801

申请日：1992-09-21

申请人： Yasunori Ushiro

发明人： Yasunori Ushiro

IPC分类号： G06F17/12 ,  G06F17/16 ,  G06F15/347

CPC分类号： G06F17/16 ,  G06F17/12

摘要： To analyze a physical phenomenon by a computer having a plurality of vector processors and a parallel computer, there is generated submatrices in a preconditioning for obtaining solutions of simultaneous linear equations. Nonzero elements of the coefficient matrix are stored with column number indices assigned thereto such that the elements of the coefficient matrix and the data of right-side vector are scaled according to a sum of absolute values of nondiagonal elements of the coefficient matrix and a diagonal element related thereto. The nonzero elements are sorted depending on magnitude of their absolute values to subdivide the nondiagonal nonzero elements into m submatrices E1, E2, . . . , Em each having substantially a comparable order. Using products developed between differences between a unit matrix and these submatrices in the iterative calculations for a large-sized numerical simulation, there is obtained quite a satisfactory characteristic of convergence of solutions and hence the processing speed is remarkably increased.

摘要翻译： 为了通过具有多个向量处理器和并行计算机的计算机分析物理现象，在用于获得联立线性方程的解的预处理中存在生成子矩阵。 存储系数矩阵的非零元素，其中分配有列号索引，使得系数矩阵的元素和右侧向量的数据根据​​系数矩阵的非对角元素的绝对值和对角线元素之和来缩放 相关。 非零元素根据其绝对值的大小进行排序，以将非对角非零元素细分为m个子矩阵E1，E2。 。 。 ，Em各自具有基本上相当的顺序。 在大尺寸数值模拟的迭代计算中，使用在单位矩阵和这些子矩阵之间的差异之间开发的产品，获得了令人满意的解决方案收敛的特征，因此处理速度显着增加。