External Memory Controller Node

• US 20090276584A1
• Filed: 05/07/2009
• Published: 11/05/2009
• Est. Priority Date: 11/22/2002
• Status: Active Grant

• Current Assignee: Cornami, Inc.
• Original Assignee: QST Holdings LLC, QuickSilver Controls, Inc.
• Inventors: Master, Paul L., Furtek, Frederick Curtis
• Granted Patent: US 7,937,539 B2
• Time in Patent Office: Days
• US Class Current: 711/149
• CPC Class Codes: G06F 13/1657 Access to multiple memories
• CPC Class Codes: G06F 15/167 using a common memory, e.g. mailbox
• CPC Class Codes: G06F 3/0626 Reducing size or complexity of storage systems
• CPC Class Codes: G06F 3/0661 Format or protocol conversion arrangements
• CPC Class Codes: G06F 3/0679 Non-volatile semiconductor memory device, e.g. flash memory, one time programmable memory [OTP]
• CPC Class Codes: G11C 7/1072 for memories with random access ports synchronised on clock signal pulse trains, e.g. synchronous memories, self timed memories
• CPC Class Codes: H04L 67/60 Scheduling or organising the servicing of application requests, e.g. requests for application data transmissions using the analysis and optimisation of the required network resources admission control or resource allocation H04L47/70

Abstract

A memory controller to provide memory access services in an adaptive computing engine is provided. The controller comprises: a network interface configured to receive a memory request from a programmable network; and a memory interface configured to access a memory to fulfill the memory request from the programmable network, wherein the memory interface receives and provides data for the memory request to the network interface, the network interface configured to send data to and receive data from the programmable network.

Claims

1-32. -32. (canceled)

33. A computing machine embodied in an integrated circuit comprising:

a memory;

a plurality of heterogeneous computational nodes configured to make memory requests for accesses to the memory; and

a memory controller to manage al sequence to allow accesses by the heterogeneous computational nodes to the memory in response to the memory requests.

34. The computing machine of claim 33, wherein the sequence includes sending acknowledgements from the memory controller to the sending computational node indicating that space has become available in an input buffer for receiving additional memory requests.

35. The computing machine of claim 33, wherein the memory controller includes ports that have parameters, the memory controller configured to generate memory locations for the memory requests based on the parameters.

36. The computing machine of claim 33, wherein the memory controller allows multiple independent simultaneous accesses by the heterogeneous computational nodes to the memory in response to the memory requests.

37. The computing machine of claim 33, wherein the memory controller is configured to place the memory requests in a queue and allow accesses by the heterogeneous computational nodes to the memory in an order established by the queue.

38. The computing machine of claim 33, wherein the memory controller includes a predefined number of memory channels and is configured to receive memory requests assigned to corresponding memory channels of the predefined number of memory channels.

39. The computing machine of claim 38, wherein the memory controller is configured to allow accesses by the heterogeneous computational nodes to the memory over the assigned memory channels.

40. The computing machine of claim 38, wherein the memory controller is configured to allow requests sent over different channels of the plurality of memory channels to be processed in an order other than the order in which the requests are received by the memory controller.

41. The computing machine of claim 33, further comprising a programmable interconnection network providing interconnections among the heterogeneous computational nodes and the memory controller, the interconnection network to route the memory requests from the heterogeneous computational nodes to the memory controller, route data for the memory requests between the heterogeneous computational nodes and the memory via the memory controller, and route data between the heterogeneous computational nodes.

42. The computing machine circuit of claim 33, wherein the parameters are configured by the memory controller in response to a peek or a poke.

43. The computing machine of claim 33, wherein the parameters are configured by the memory controller in response to the memory requests.

44. The computing machine of claim 33, wherein the adaptive computing device is in communication with an external memory device, and wherein the memory controller is configured to allow accesses by the heterogeneous computational nodes to the external memory device in response to the memory requests.

45. A computing machine embodied in an integrated circuit, the computing machine in communication with an external memory device, the integrated circuit comprising:

a plurality of heterogeneous computational nodes configured to make memory requests for accesses to the external memory device;

a controller to manage a sequence to allow accesses by the heterogeneous computing nodes to the external memory device in response to the memory requests.

46. The computing machine of claim 45, wherein the sequence includes sending acknowledgements from the controller to the sending computational node indicating that space has become available in an input buffer for receiving additional memory requests.

47. The computing machine of claim 45, wherein the controller includes ports that have parameters, wherein the controller is configured to generate memory locations for the data transfer requests based on the parameters.

48. The computing machine of claim 45, wherein the controller allows multiple independent simultaneous accesses by the heterogeneous computational nodes to the external memory device in response to the requests for data transfer.

49. The computing machine of claim 45, wherein the controller is configured to place the requests for data transfer in a queue and allow accesses by the heterogeneous computational nodes to the external memory device in an order established by the queue.

50. The computing machine of claim 45, wherein the controller includes a predefined number of channels and is configured to receive requests for data-transfer, the requests assigned to corresponding channels of the predefined number of channels.

51. The computing machine of claim 50, wherein the controller is configured to allow accesses by the heterogeneous computational nodes to the external memory device over the assigned channels.

52. The computing machine of claim 50, wherein the controller is configured to allow requests sent over different channels of the plurality of channels to be processed in an order other than the order in which the requests are received by the controller.

53. The computing machine of claim 45, further comprising a programmable interconnection network providing interconnections among the heterogeneous computational nodes and the controller, the interconnection network to route the memory requests from the heterogeneous computational nodes to the controller, route data for the memory requests between the heterogeneous computational nodes and the external memory device via the controller, and route data between the heterogeneous computational nodes.

54. The computing machine of claim 45, wherein the parameters are configured by the controller in response to a peek or a poke.

55. The computing machine of claim 45, wherein the parameters are configured by the controller in response to the requests for data transfer.

56. The computing machine of claim 45, further comprising a memory, and wherein the controller allows multiple independent simultaneous accesses by the heterogeneous computational nodes to the memory in response to the memory requests.

57. An adaptive computing machine embodied in an integrated circuit, the adaptive computing machine comprising:

a memory;

a plurality of heterogeneous computational nodes configured to make memory requests for accesses to the memory;

a memory controller to manage a sequence to allow accesses by the heterogeneous computational nodes to the memory in response to the memory requests; and

a programmable interconnection network providing programmable interconnections among the heterogeneous computational nodes and the memory controller.

58. The computing machine of claim 57, wherein the sequence includes sending acknowledgements from the memory controller to the sending computational node indicating that space has become available in an input buffer for receiving additional memory requests.

59. The adaptive computing machine of claim 57, wherein the memory controller allows multiple independent simultaneous accesses by the heterogeneous computational nodes to the memory in response to the memory requests.

60. The adaptive computing machine of claim 57, wherein the memory controller includes ports that have parameters, the memory controller configured to generate memory locations for the memory requests based on the parameters.

61. The adaptive computing machine of claim 57, wherein the memory controller is configured to place the memory requests in a queue and allow accesses by the heterogeneous computational nodes to the memory in an order established by the queue.

62. The adaptive computing machine of claim 57, wherein the memory controller includes a predefined number of memory channels and is configured to receive memory requests assigned to corresponding memory channels of the predefined number of memory channels.

63. The adaptive computing machine of claim 62, wherein the memory controller is configured to allow accesses by the heterogeneous computational nodes to the memory over the assigned memory channels.

64. The adaptive computing machine of claim 62, wherein the memory controller is configured to allow requests sent over different channels of the plurality of memory channels to be processed in an order other than the order in which the requests are received by the memory controller.

65. The adaptive computing machine of claim 57, wherein the interconnection network routes the memory requests from the heterogeneous computational nodes to the memory controller, routes data for the memory requests between the heterogeneous computational nodes and the memory via the memory controller, and routes data between the heterogeneous computational nodes.

66. The adaptive computing machine of claim 57, wherein the parameters are configured by the memory controller in response to a peek or a poke.

67. The adaptive computing machine of claim 57, wherein the parameters are configured by the memory controller in response to the memory requests.

68. The adaptive computing machine of claim 57, wherein the adaptive computing device is in communication with an external memory device, and wherein the memory controller is configured to allow accesses by the heterogeneous computational nodes to the external memory device in response to the memory requests.

69. An adaptive computing machine embodied in an integrated circuit and in communication with an external memory device, the adaptive computing machine comprising:

a plurality of heterogeneous computational nodes configured to make memory requests for data transfer to the external memory device;

a controller to manage a sequence to allow accesses by the heterogeneous computing nodes to the external memory device in response to the memory requests; and

a programmable interconnection network to provide programmable interconnections among the heterogeneous computational nodes and the controller.

70. The adaptive computing machine of claim 69, wherein the sequence includes sending acknowledgements from the controller to the sending computational node indicating that space has become available in an input buffer for receiving additional memory requests.

71. The adaptable computing machine of claim 69, wherein the controller allows multiple independent simultaneous accesses by the heterogeneous computational nodes to the external memory device in response to the requests for data transfer.

72. The adaptive computing machine of claim 69, further comprising a memory, and wherein the controller allows multiple independent simultaneous accesses by the heterogeneous computational nodes to the memory in response to the memory requests.

73. The adaptive computing machine of claim 69, wherein the controller includes ports that have parameters, and wherein the controller is configured to generate memory locations for the data transfer requests based on the parameters and to allow accesses by the heterogeneous computing nodes to the external memory device at the memory locations in response to the data transfer requests.

74. The adaptive computing machine of claim 69, wherein the controller is configured to place the requests for data transfer in a queue and allow accesses by the heterogeneous computational nodes to the external memory device in an order established by the queue.

75. The adaptive computing machine of claim 69, wherein the controller includes a predefined number of channels and is configured to receive requests for data-transfer, the requests assigned to corresponding channels of the predefined number of channels.

76. The adaptive computing machine of claim 75, wherein the controller is configured to allow accesses by the heterogeneous computational nodes to the external memory device over the assigned channels.

77. The adaptive computing machine of claim 75, wherein the controller is configured to allow requests sent over different channels of the plurality of channels to be processed in an order other than the order in which the requests are received by the controller.

78. The adaptive computing machine of claim 69, wherein the interconnection network routes the memory requests from the heterogeneous computational nodes to the controller, routes data for the memory requests between the heterogeneous computational nodes and the external memory device via the controller, and routes data between the heterogeneous computational nodes.

79. The adaptive computing machine of claim 69, wherein the parameters are configured by the controller in response to a peek or a poke.

80. The adaptive computing machine of claim 69, wherein the parameters are configured by the controller in response to the requests for data transfer.