发明公开
EP0094177A2 Apparatus for direct memory-to-memory intercomputer communication
失效
Gerätzur direkten Speicher-zu-Speicherübertragungzwischen Rechnern。
- 专利标题: Apparatus for direct memory-to-memory intercomputer communication
- 专利标题(中): Gerätzur direkten Speicher-zu-Speicherübertragungzwischen Rechnern。
-
申请号: EP83302411.0申请日: 1983-04-28
-
公开(公告)号: EP0094177A2公开(公告)日: 1983-11-16
- 发明人: Strecker, William D. , Stewart, Robert E. , Fuller, Samuel
- 申请人: DIGITAL EQUIPMENT CORPORATION
- 申请人地址: 146 Main Street Maynard, MA 01754 US
- 专利权人: DIGITAL EQUIPMENT CORPORATION
- 当前专利权人: DIGITAL EQUIPMENT CORPORATION
- 当前专利权人地址: 146 Main Street Maynard, MA 01754 US
- 代理机构: Goodman, Christopher
- 优先权: US375984 19820507
- 主分类号: G06F15/16
- IPC分类号: G06F15/16
摘要:
Method and apparatus for transfer of packet-type information from the memory (24B) of one node (14) in a computer network to the memory (24C) of another node (16) in the network. The invention is of particular utility in transfers over serial buses (e.g., 18). Packets are sent from a named memory buffer (25A) at a first node (14) to a named memory buffer (25C) at a second node (16), allowing random access by the first node to the memory of the second node without either node having to have knowledge of the memory structure of the other; the source and destination buffer names are contained right in the transmitted packet.
The first node (14) can both write to and read from the second node (16). An opcode (40A) sent in each packet signifies whether a read or write operation is to be performed. For reading from the second node, the opcode actually causes the second node to write back to the first node; in this situation, the second node to write back to the first node; in this situation, che second node, upon detecting the appropriate opcode, places the remainder of the received packet on a command queue (202), to be excuted with the commands locally generated at the second node, without need for host interruption.
The first node (14) can both write to and read from the second node (16). An opcode (40A) sent in each packet signifies whether a read or write operation is to be performed. For reading from the second node, the opcode actually causes the second node to write back to the first node; in this situation, the second node to write back to the first node; in this situation, che second node, upon detecting the appropriate opcode, places the remainder of the received packet on a command queue (202), to be excuted with the commands locally generated at the second node, without need for host interruption.
公开/授权文献
信息查询