Extended Fast Memory Access in a Multiprocessor Computer System

• US 20150378961A1
• Filed: 05/27/2015
• Published: 12/31/2015
• Est. Priority Date: 06/12/2009
• Status: Active Grant

• Current Assignee: Intel Corporation
• Original Assignee: Intel Corporation
• Inventors: Abts, Dennis C., Alverson, Robert, Froese, Edwin, Pritchard, Howard, Scott, Steven L.
• Granted Patent: US 10,860,524 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06F 12/0813 with a network or matrix configuration
• CPC Class Codes: G06F 12/1009 using page tables, e.g. page table structures
• CPC Class Codes: G06F 12/109 for multiple virtual address spaces, e.g. segmentation G06F12/1036 takes precedence
• CPC Class Codes: G06F 13/4009 with data restructuring
• CPC Class Codes: G06F 15/167 using a common memory, e.g. mailbox
• CPC Class Codes: G06F 2212/163 Server or database system
• CPC Class Codes: G06F 9/3834 Maintaining memory consistency
• CPC Class Codes: H04L 67/00 Network arrangements or protocols for supporting network services or applications user-to-user messaging H04L51/00; network arrangements, protocols or services for supporting real-time applications in data packet communications networks H04L65/00

Abstract

A multiprocessor computer system comprises a first node operable to access memory local to a remote node by receiving a virtual memory address from a requesting entity in node logic in the first node. The first node creates a network address from the virtual address received in the node logic, where the network address is in a larger address space than the virtual memory address, and sends a fast memory access request from the first node to a network node identified in the network address.

Claims

1-21. -21. (canceled)

22. A method comprising:

receiving a memory request from a processor at a first node having a first address space to access memory at a second node having a second address space;

translating the memory request into a network request to enable to access of the memory according to the second address space; and

transmitting the network request from the first node to the second node to access the memory at the first node.

23. The method of claim 22, further comprising creating a network address from a virtual address received in the first node, where the network address is in a larger address space than the virtual address, and the network address includes a processing element field, a memory domain handle, and an offset

24. The method of claim 23, further comprising sending a fast memory access request from the first node to the second node identified in the network address, wherein the fast memory access request includes the network address.

25. The method of claim 23, wherein the virtual address comprises:

a fast memory access (FMA) descriptor; and

an offset window used to generate network endpoint and offset components of the network address.

26. The method of claim 22, wherein the network address comprises a protection tag.

27. The method of claim 25, wherein fast memory access is used to provide load/store access to remote memory, and a block transfer engine is used to copy remote memory.

28. The method of claim 23, wherein creating a network address from the virtual address comprises looking up at least a portion of the virtual address in a fast memory access table.

29. A multiprocessor computer system, comprising a first node, including one or more processing elements, operable to access memory local to a second node by:

receiving a memory request from a first processing element having a first address space to access memory at the second node having a second address space;

translating the memory request into a network request to enable to access of the memory according to the second address space; and

transmitting the network request from the first node to the second node to access the memory at the first node.

30. The multiprocessor computer system of claim 29, wherein the first node creates a network address from a received virtual address, where the network address is in a larger address space than the virtual address, and the network address includes a processing element field, a memory domain handle, and an offset

31. The multiprocessor computer system of claim 29, wherein the first node sends a fast memory access request from the first node to the second node identified in the network address, wherein the fast memory access request includes the network address.

32. The multiprocessor computer system of claim 30, wherein the virtual address comprises:

a fast memory access (FMA) descriptor; and

an offset window used to generate network endpoint and offset components of the network address.

33. The multiprocessor computer system of claim 30, wherein the network address comprises a protection tag.

34. The multiprocessor computer system of claim 31, wherein fast memory access is used to provide load/store access to remote memory, and a block transfer engine is used to copy remote memory.

35. The multiprocessor computer system of claim 30, wherein creating a network address from the virtual address comprises looking up at least a portion of the virtual address in a fast memory access table.

36. A multiprocessor computer node operable to access memory local to a remote node by:

receiving a memory request from a processing element in the computer node having a first address space to access memory at the remote node having a second address space;

translating the memory request into a network request to enable to access of the memory according to the second address space; and

transmitting the network request from the computer node to the remote node to access the memory at the first node.

37. The multiprocessor computer node of claim 36, wherein the computer node creates a network address from a received virtual address, where the network address is in a larger address space than the virtual address, and the network address includes a processing element field, a memory domain handle, and an offset

38. The multiprocessor computer node of claim 36, wherein the computer node sends a fast memory access to the remote node identified in the network address, wherein the fast memory access request includes the network address.

39. The multiprocessor computer node of claim 37, wherein the virtual address comprises:

a fast memory access (FMA) descriptor; and

an offset window used to generate network endpoint and offset components of the network address.

40. The multiprocessor computer node of claim 37, wherein the network address comprises a protection tag.

41. The multiprocessor computer node of claim 38, wherein fast memory access is used to provide load/store access to remote memory, and a block transfer engine is used to copy remote memory.

42. The multiprocessor computer node of claim 37, wherein creating a network address from the virtual address comprises looking up at least a portion of the virtual address in a fast memory access table.