专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2009037684A3 SPARSE MATRIX BY VECTOR MULTIPLICATION 审中-公开
标题翻译：矢量矩阵的散列矩阵
公开(公告)号：WO2009037684A3
公开(公告)日：2010-05-06
申请号：PCT/IE2008000089
申请日：2008-09-19
申请人： TRINITY COLLEGE DUBLIN , GERAGHTY THOMAS DERMOT , GREGG DAVID , MCELROY BARTLEY , CONNOR FERGAL , MCELROY CIARAN
发明人： GERAGHTY THOMAS DERMOT , GREGG DAVID , MCELROY BARTLEY , CONNOR FERGAL , MCELROY CIARAN
IPC分类号： G06F17/16
CPC分类号： G06F17/16
摘要： The invention involves pre-processing the matrix according to an encoding scheme whereby the non-zero data (in any numerical format), blocking information, the row an column offset indices within a block are represented by state machine control words which are combined in a single data stream. Thus, a single vector may be used to store all of the matrix information required to compute a sparse matrix by vector multiplication. Therefore, the system can be used effectively with a single memory channel. Also, it can be used in parallel with multiple independent memory channels. This method of matrix-by-vector multiplication achieves allows very high FPU utilization to be achieved for low bandwidth matrices such as those from finite element calculations. Also, it allows local memory buffers to be simple, and so there is no need for a complex cache architecture.
摘要翻译：本发明涉及根据编码方案对矩阵进行预处理，由此非零数据（以任何数字格式）阻塞信息，行中的列偏移索引由状态机控制字表示，所述状态机控制字被组合在一个单数据流。因此，可以使用单个向量来存储通过向量乘法计算稀疏矩阵所需的所有矩阵信息。因此，可以使用单个存储器通道有效地使用该系统。此外，它可以与多个独立的存储器通道并行使用。这种逐向矢量乘法的方法实现了对于诸如来自有限元计算的低带宽矩阵来实现非常高的FPU利用率。此外，它允许本地内存缓冲区简单，因此不需要复杂的缓存架构。

2. 发明申请

WO2009037684A2 SPARSE MATRIX BY VECTOR MULTIPLICATION 审中-公开
标题翻译：矢量矩阵的散列矩阵
公开(公告)号：WO2009037684A2
公开(公告)日：2009-03-26
申请号：PCT/IE2008/000089
申请日：2008-09-19
申请人： PROVOST FELLOWS AND SCHOLARS OF THE COLLEGE OF THE HOLY AND UNDIVIDED TRINITY OF QUEEN ELIZABETH NEAR DUBLIN , GERAGHTY, Thomas, Dermot , GREGG, David , McELROY, Bartley , CONNOR, Fergal , McELROY, Ciarán
发明人： GERAGHTY, Thomas, Dermot , GREGG, David , McELROY, Bartley , CONNOR, Fergal , McELROY, Ciarán
IPC分类号： G06F17/16
CPC分类号： G06F17/16
摘要： The invention involves pre-processing the matrix according to an encoding scheme whereby the non-zero data (in any numerical format), blocking information, the row an column offset indices within a block are represented by state machine control words which are combined in a single data stream. Thus, a single vector may be used to store all of the matrix information required to compute a sparse matrix by vector multiplication. Therefore, the system can be used effectively with a single memory channel. Also, it can be used in parallel with multiple independent memory channels. This method of matrix-by-vector multiplication achieves allows very high FPU utilization to be achieved for low bandwidth matrices such as those from finite element calculations. Also, it allows local memory buffers to be simple, and so there is no need for a complex cache architecture.
摘要翻译：本发明涉及根据编码方案对矩阵进行预处理，由此非零数据（以任何数字格式）阻塞信息，行中的列偏移索引由状态机控制字表示，所述状态机控制字被组合在一个单数据流。因此，可以使用单个向量来存储通过向量乘法计算稀疏矩阵所需的所有矩阵信息。因此，可以使用单个存储器通道有效地使用该系统。此外，它可以与多个独立的存储器通道并行使用。这种逐向矢量乘法的方法实现了对于诸如来自有限元计算的低带宽矩阵来实现非常高的FPU利用率。此外，它允许本地内存缓冲区简单，因此不需要复杂的缓存架构。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式