IPC분류정보
국가/구분 |
United States(US) Patent
등록
|
국제특허분류(IPC7판) |
|
출원번호 |
UP-0843083
(2007-08-22)
|
등록번호 |
US-7840779
(2011-01-22)
|
발명자
/ 주소 |
- Archer, Charles J.
- Berg, Jeremy E.
- Blocksome, Michael A.
- Smith, Brian E.
|
출원인 / 주소 |
- International Business Machines Corporation
|
대리인 / 주소 |
|
인용정보 |
피인용 횟수 :
1 인용 특허 :
32 |
초록
▼
Methods, apparatus, and products are disclosed for line-plane broadcasting in a data communications network of a parallel computer, the parallel computer comprising a plurality of compute nodes connected together through the network, the network optimized for point to point data communications and c
Methods, apparatus, and products are disclosed for line-plane broadcasting in a data communications network of a parallel computer, the parallel computer comprising a plurality of compute nodes connected together through the network, the network optimized for point to point data communications and characterized by at least a first dimension, a second dimension, and a third dimension, that include: initiating, by a broadcasting compute node, a broadcast operation, including sending a message to all of the compute nodes along an axis of the first dimension for the network; sending, by each compute node along the axis of the first dimension, the message to all of the compute nodes along an axis of the second dimension for the network; and sending, by each compute node along the axis of the second dimension, the message to all of the compute nodes along an axis of the third dimension for the network.
대표청구항
▼
What is claimed is: 1. A parallel computer for line-plane broadcasting in a data communications network, the parallel computer comprising a plurality of compute nodes connected together through the data communications network, the data communications network optimized for point to point data commun
What is claimed is: 1. A parallel computer for line-plane broadcasting in a data communications network, the parallel computer comprising a plurality of compute nodes connected together through the data communications network, the data communications network optimized for point to point data communications and characterized by at least a first dimension, a second dimension, and a third dimension, the plurality of compute nodes further comprising a plurality of computer processors and computer memory operatively coupled to the plurality of computer processors, the computer memory having disposed within it computer program instructions capable of: partitioning, by a broadcasting compute node, a message into a plurality of portions, each portion corresponding to one of the dimensions; initiating, by the broadcasting compute node, a broadcast operation, including sending the portion of the message that corresponds to the first dimension to all of the compute nodes along an axis of the first dimension for the data communications network; sending, by each compute node along the axis of the first dimension, the portion of the message that corresponds to the first dimension to all of the compute nodes along an axis of the second dimension for the data communications network; and sending, by each compute node along the axis of the second dimension, the portion of the message that corresponds to the first dimension to all of the compute nodes along an axis of the third dimension for the data communications network, wherein the plurality of compute nodes are organized into at least one operational group and wherein line plane broadcasting in the data communications network is carried out using only the compute nodes in the operational group. 2. The parallel computer of claim 1 wherein: the data communications network is organized in a rectangular mesh topology and is characterized by the first dimension, the second dimension, and the third dimension; and the axis of each dimension is perpendicular to the axis of the other dimensions. 3. The parallel computer of claim 1 wherein the plurality of compute nodes are also connected together for data communications through another data communications network optimized for collective operations. 4. A computer program product for line-plane broadcasting in a data communications network of a parallel computer, the parallel computer comprising a plurality of compute nodes connected together through the data communications network, the data communications network optimized for point to point data communications and characterized by at least a first dimension, a second dimension, and a third dimension, the computer program product disposed upon a recordable computer readable medium, the computer program product comprising computer program instructions capable of: partitioning, by a broadcasting compute node, a message into a plurality of portions, each portion corresponding to one of the dimensions; initiating, by the broadcasting compute node, a broadcast operation, including sending the portion of the message that corresponds to the first dimension to all of the compute nodes along an axis of the first dimension for the data communications network; sending, by each compute node along the axis of the first dimension, the portion of the message that corresponds to the first dimension to all of the compute nodes along an axis of the second dimension for the data communications network; and sending, by each compute node along the axis of the second dimension, the portion of the message that corresponds to the first dimension to all of the compute nodes along an axis of the third dimension for the data communications network, wherein the plurality of compute nodes are organized into at least one operational group and wherein line plane broadcasting in the data communications network is carried out using only the compute nodes in the operational group. 5. The computer program product of claim 4 wherein: the data communications network is organized in a rectangular mesh topology and is characterized by the first dimension, the second dimension, and the third dimension; and the axis of each dimension is perpendicular to the axis of the other dimensions. 6. The computer program product of claim 4 wherein the plurality of compute nodes are also connected together for data communications through another data communications network optimized for collective operations. 7. A parallel computer for line-plane broadcasting in a data communications network, the parallel computer comprising a plurality of compute nodes connected together through the data communications network and through another data communications network, the data communications network optimized for point to point data communications, the another data communications network optimized for collective operations, the data communications network organized in a rectangular mesh topology and characterized by a first dimension, a second dimension, and a third dimension, the plurality of compute nodes further comprising a plurality of computer processors and computer memory operatively coupled to the plurality of computer processors, the computer memory having disposed within it computer program instructions capable of: partitioning, by a broadcasting compute node, a message into a plurality of portions, each portion corresponding to one of the dimensions; initiating, by the broadcasting compute node, a broadcast operation, including sending the portion of the message that corresponds to the first dimension to all of the compute nodes along an axis of the first dimension for the data communications network; sending, by each compute node along the axis of the first dimension, the portion of the message that corresponds to the first dimension to all of the compute nodes along an axis of the second dimension for the data communications network; and sending, by each compute node along the axis of the second dimension, the portion of the message that corresponds to the first dimension to all of the compute nodes along an axis of the third dimension for the data communications network, wherein the plurality of compute nodes are organized into at least one operational group and wherein line plane broadcasting in the data communications network is carried out using only the compute nodes in the operational group.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.