-
公开(公告)号：US20170206183A1
公开(公告)日：2017-07-20
申请号：US15476598
申请日：2017-03-31
申请人： CORNAMI, INC.
发明人： Solomon Harsha , Paul Master
CPC分类号： G06F15/8046 , G06F8/45 , G06Q40/00
摘要： An apparatus, computer-readable medium, and computer-implemented method for parallelization of a computer program on a plurality of computing cores includes receiving a computer program comprising a plurality of commands, decomposing the plurality of commands into a plurality of node networks, each node network corresponding to a command in the plurality of commands and including one or more nodes corresponding to execution dependencies of the command, mapping the plurality of node networks to a plurality of systolic arrays, each systolic array comprising a plurality of cells and each non-data node in each node network being mapped to a cell in the plurality of cells, and mapping each cell in each systolic array to a computing core in the plurality of computing cores.
-
公开(公告)号：US11853256B2
公开(公告)日：2023-12-26
申请号：US16004799
申请日：2018-06-11
申请人： CORNAMI, INC.
发明人： Solomon Harsha , Paul Master
CPC分类号： G06F15/8046 , G06F8/45 , G06Q40/00
摘要： An apparatus, computer-readable medium, and computer-implemented method for parallelization of a computer program on a plurality of computing cores includes receiving a computer program comprising a plurality of commands, decomposing the plurality of commands into a plurality of node networks, each node network corresponding to a command in the plurality of commands and including one or more nodes corresponding to execution dependencies of the command, mapping the plurality of node networks to a plurality of systolic arrays, each systolic array comprising a plurality of cells and each non-data node in each node network being mapped to a cell in the plurality of cells, and mapping each cell in each systolic array to a computing core in the plurality of computing cores.
-
公开(公告)号：US10019410B2
公开(公告)日：2018-07-10
申请号：US15480411
申请日：2017-04-06
申请人： CORNAMI, INC.
发明人： Solomon Harsha , Paul Master
CPC分类号： G06F15/8046 , G06F8/45 , G06Q40/00
摘要： An apparatus, computer-readable medium, and computer-implemented method for parallelization of a computer program on a plurality of computing cores includes receiving a computer program comprising a plurality of commands, decomposing the plurality of commands into a plurality of node networks, each node network corresponding to a command in the plurality of commands and including one or more nodes corresponding to execution dependencies of the command, mapping the plurality of node networks to a plurality of systolic arrays, each systolic array comprising a plurality of cells and each non-data node in each node network being mapped to a cell in the plurality of cells, and mapping each cell in each systolic array to a computing core in the plurality of computing cores.
-
公开(公告)号：US09760530B2
公开(公告)日：2017-09-12
申请号：US15476598
申请日：2017-03-31
申请人： CORNAMI, INC.
发明人： Solomon Harsha , Paul Master
CPC分类号： G06F15/8046 , G06F8/45 , G06Q40/00
摘要： An apparatus, computer-readable medium, and computer-implemented method for parallelization of a computer program on a plurality of computing cores includes receiving a computer program comprising a plurality of commands, decomposing the plurality of commands into a plurality of node networks, each node network corresponding to a command in the plurality of commands and including one or more nodes corresponding to execution dependencies of the command, mapping the plurality of node networks to a plurality of systolic arrays, each systolic array comprising a plurality of cells and each non-data node in each node network being mapped to a cell in the plurality of cells, and mapping each cell in each systolic array to a computing core in the plurality of computing cores.
-
公开(公告)号：US20180095931A1
公开(公告)日：2018-04-05
申请号：US15480411
申请日：2017-04-06
申请人： CORNAMI, INC.
发明人： Solomon Harsha , Paul Master
CPC分类号： G06F15/8046 , G06F8/45 , G06Q40/00
摘要： An apparatus, computer-readable medium, and computer-implemented method for parallelization of a computer program on a plurality of computing cores includes receiving a computer program comprising a plurality of commands, decomposing the plurality of commands into a plurality of node networks, each node network corresponding to a command in the plurality of commands and including one or more nodes corresponding to execution dependencies of the command, mapping the plurality of node networks to a plurality of systolic arrays, each systolic array comprising a plurality of cells and each non-data node in each node network being mapped to a cell in the plurality of cells, and mapping each cell in each systolic array to a computing core in the plurality of computing cores.
-
公开(公告)号：US09760531B2
公开(公告)日：2017-09-12
申请号：US15480412
申请日：2017-04-06
申请人： CORNAMI, INC.
发明人： Solomon Harsha , Paul Master
CPC分类号： G06F15/8046 , G06F8/45 , G06Q40/00
摘要： An apparatus, computer-readable medium, and computer-implemented method for parallelization of a computer program on a plurality of computing cores includes receiving a computer program comprising a plurality of commands, decomposing the plurality of commands into a plurality of node networks, each node network corresponding to a command in the plurality of commands and including one or more nodes corresponding to execution dependencies of the command, mapping the plurality of node networks to a plurality of systolic arrays, each systolic array comprising a plurality of cells and each non-data node in each node network being mapped to a cell in the plurality of cells, and mapping each cell in each systolic array to a computing core in the plurality of computing cores.
-
7.发明公开公开(公告)号：US20240070114A1
公开(公告)日：2024-02-29
申请号：US18388463
申请日：2023-11-09
申请人： CORNAMI, INC.
发明人： Solomon Harsha , Paul Master
CPC分类号： G06F15/8046 , G06F8/45 , G06Q40/00
摘要： An apparatus, computer-readable medium, and computer-implemented method for parallelization of a computer program on a plurality of computing cores includes receiving a computer program comprising a plurality of commands, decomposing the plurality of commands into a plurality of node networks, each node network corresponding to a command in the plurality of commands and including one or more nodes corresponding to execution dependencies of the command, mapping the plurality of node networks to a plurality of systolic arrays, each systolic array comprising a plurality of cells and each non-data node in each node network being mapped to a cell in the plurality of cells, and mapping each cell in each systolic array to a computing core in the plurality of computing cores.
-
8.发明申请公开(公告)号：US20180293206A1
公开(公告)日：2018-10-11
申请号：US16004799
申请日：2018-06-11
申请人： CORNAMI, INC.
发明人： Solomon Harsha , Paul Master
摘要： An apparatus, computer-readable medium, and computer-implemented method for parallelization of a computer program on a plurality of computing cores includes receiving a computer program comprising a plurality of commands, decomposing the plurality of commands into a plurality of node networks, each node network corresponding to a command in the plurality of commands and including one or more nodes corresponding to execution dependencies of the command, mapping the plurality of node networks to a plurality of systolic arrays, each systolic array comprising a plurality of cells and each non-data node in each node network being mapped to a cell in the plurality of cells, and mapping each cell in each systolic array to a computing core in the plurality of computing cores.
-
公开(公告)号：US20170212866A1
公开(公告)日：2017-07-27
申请号：US15480412
申请日：2017-04-06
申请人： CORNAMI, INC.
发明人： Solomon Harsha , Paul Master
CPC分类号： G06F15/8046 , G06F8/45 , G06Q40/00
摘要： An apparatus, computer-readable medium, and computer-implemented method for parallelization of a computer program on a plurality of computing cores includes receiving a computer program comprising a plurality of commands, decomposing the plurality of commands into a plurality of node networks, each node network corresponding to a command in the plurality of commands and including one or more nodes corresponding to execution dependencies of the command, mapping the plurality of node networks to a plurality of systolic arrays, each systolic array comprising a plurality of cells and each non-data node in each node network being mapped to a cell in the plurality of cells, and mapping each cell in each systolic array to a computing core in the plurality of computing cores.
-
-
-
-
-
-
-
-
搜索结果
9 条记录 (耗时 0.01 秒)
