Method and apparatus for managing orders in financial markets

• US 10,037,568 B2
• Filed: 12/09/2011
• Issued: 07/31/2018
• Est. Priority Date: 12/09/2010
• Status: Active Grant

• Current Assignee: Exegy Incorporated
• Original Assignee: Ip Reservoir, LLC
• Inventors: Taylor, David, Parsons, Scott
• Primary Examiner(s): BORLINGHAUS, JASON M
• Application Number:
  US13/316,332
• Publication Number:
  US 20120246052A1
• Time in Patent Office: 2,426 Days
• Field of Search: None
• CPC Class Codes: G06Q 40/04 Trading; Exchange, e.g. stocks, commodities, derivatives or currency exchange
• CPC Class Codes: G06Q 40/06 Asset management; Financial planning or analysis

Abstract

An integrated order management engine is disclosed that reduces the latency associated with managing multiple orders to buy or sell a plurality of financial instruments. Also disclosed is an integrated trading platform that provides low latency communications between various platform components. Such an integrated trading platform may include a trading strategy offload engine.

Claims

1. An apparatus comprising:

a trading platform, the trading platform configured to receive and process streaming financial market data, the trading platform comprising;

a host system, the host system comprising a host processor and host memory ;

a ticker plant engine, the ticker plant engine configured to receive and normalize a stream of financial market data, wherein the ticker plant engine is deployed on a member of the group consisting of (1) a reconfigurable logic device, (2) a graphics processor unit (GPU), and (3) a chip multi-processor (CMP) ;

an order management engine, the order management engine configured to manage a plurality of financial instrument orders based on the normalized financial market data, wherein the order management engine is deployed on a member of the group consisting of (1) a reconfigurable logic device, (2) a GPU, and (3) a CMP ;

a shared memory, wherein the shared memory includes memory space that is read/write addressable by the ticker plant engine and the order management engine; and

a peer-to-peer hardware interconnect configured to interconnect the ticker plant engine and the order management engine via the shared memory; and

wherein the host processor and the host memory are configured to (1) process data in support of financial instrument trading based on normalized financial market data received from the ticker plant engine and (2) communicate with the order management engine regarding a plurality of the financial instrument orders; and

wherein the ticker plant engine is configured to write the normalized financial market data to the shared addressable memory space to thereby communicate the normalized financial market data to the order management engine via the peer-to-peer hardware interconnect without using the host processor and without using the host memory.

2. The apparatus of claim 1 wherein the trading platform further comprises:

a trading strategy offload engine, the trading strategy offload engine configured to implement at least a portion of a trading strategy based on the normalized financial market data, wherein the trading strategy offload engine is deployed on a member of the group consisting of (1) a reconfigurable logic device, (2) a GPU, and (3) a CMP;

wherein the shared memory further includes memory space that is read/write addressable by the ticker plant engine and the trading strategy offload engine;

wherein the peer-to-peer hardware interconnect is further configured to interconnect the ticker plant engine and the trading strategy offload engine via the shared memory; and

wherein the ticker plant engine is further configured to write the normalized financial market data to the addressable memory space shared by the ticker plant engine and the trading strategy offload engine to thereby communicate the normalized financial market data to the trading strategy offload engine via the peer-to-peer hardware interconnect without using the host processor and without using the host memory.

3. The apparatus of claim 2 wherein the trading strategy offload engine comprises a basket calculation engine.

4. The apparatus of claim 2 wherein the trading strategy offload engine comprises an options pricing engine.

5. The apparatus of claim 2 wherein the trading strategy offload engine comprises a rules engine.

6. The apparatus of claim 2 wherein the trading strategy offload engine configured to implement a first portion of the trading strategy based on the normalized financial market data, wherein the host processor and host memory are configured to execute a second portion of the trading strategy via a software application, wherein the trading platform further comprises:

a memory shared by the ticker plant engine and the host system, wherein the ticker plant engine is further configured to write normalized financial market data to the shared memory; and

a hardware-software interconnect channel configured to interconnect the trading strategy software application and the trading strategy offload engine; and

wherein the trading strategy software application is configured to (1) read the normalized financial market data from the memory shared by the ticker plant engine and the host system, (2) offload the first portion of the trading strategy to the trading strategy offload engine via the hardware-software interconnect channel, and (3) execute the second portion of the trading strategy based on the read normalized financial market data and an interaction with the trading strategy offload engine via the hardware-software interconnect channel.

7. The apparatus of claim 6 wherein the hardware-software interconnect channel is further configured to interconnect the trading strategy software application and the order management engine, and wherein the trading strategy software application is further configured to (1) generate a plurality of orders based on the execution of the trading strategy, and (2) communicate the generated orders to the order management engine via the hardware-software interconnect channel.

8. The apparatus of claim 6 wherein the host processor and the host memory are configured to execute a plurality of the trading strategy software applications.

10. The apparatus of claim 1 wherein the host processor and the host memory are configured to execute a trading strategy via a software application, wherein the trading platform further comprises:

a memory shared by the ticker plant engine and the host system, wherein the ticker plant engine is further configured to write normalized financial market data to the memory shared by the ticker plant engine and the host system; and

wherein the trading strategy software application is configured to (1) read the normalized financial market data from the memory shared by the ticker plant engine and the host system, and (2) execute the trading strategy based on the read normalized financial market data.

11. The apparatus of claim 2 wherein the ticker plant engine, the order management engine, and the trading strategy offload engine are configured for parallel operation such that each of the ticker plant, order management, and trading strategy offload engines are configured to operate simultaneously.

12. The apparatus of claim 1 wherein the ticker plant engine and the order management engine are deployed on different reconfigurable logic devices.

37. The apparatus of claim 1 wherein the ticker plant engine is deployed on a first device, wherein the first device is a member of the group consisting of the reconfigurable logic device, the GPU, and the CMP;

wherein the order management engine is deployed on a second device, wherein the second device is a member of the group consisting of the reconfigurable logic device, the GPU, and the CMP; and

wherein the ticker plant engine is assigned a first portion of the shared addressable memory space and the order management engine is assigned a second portion of the shared addressable memory space.

38. The apparatus of claim 37 wherein the peer-to-peer hardware interconnect comprises a PCI Express bus.

39. The apparatus of claim 37 wherein the trading platform further comprises:

a base address register (BAR), the BAR configured to define the first and second portions of the shared addressable memory space for the ticker plant engine and the order management engine.

40. The apparatus of claim 1 wherein the ticker plant engine is deployed on a first field programmable gate array (FPGA), and wherein the order management engine is deployed on a second FPGA.

41. The apparatus of claim 1 wherein the ticker plant engine is deployed on a first GPU, and wherein the order management engine is deployed on a second GPU.

42. The apparatus of claim 1 wherein the ticker plant engine is deployed on a first CMP, and wherein the order management engine is deployed on a second CMP.

43. The apparatus of claim 1 wherein the ticker plant engine is deployed on a field programmable gate array (FPGA), and wherein the order management engine is deployed on a GPU.

44. The apparatus of claim 1 wherein the ticker plant engine is deployed on a field programmable gate array (FPGA), and wherein the order management engine is deployed on a CMP.

45. The apparatus of claim 1 wherein the ticker plant engine and the order management engine are configured for parallel operation such that the ticker plant engine and the order management engine are configured to operate simultaneously.

46. The apparatus of claim 2 wherein the ticker plant engine is deployed on a first device, wherein the first device is a member of the group consisting of the reconfigurable logic device, the GPU, and the CMP;

wherein the order management engine is deployed on a second device, wherein the second device is a member of the group consisting of the reconfigurable logic device, the GPU, and the CMP;

wherein the trading strategy offload engine is deployed on a third device, wherein the third device is a member of the group consisting of the reconfigurable logic device, the GPU, and the CMP; and

wherein the ticker plant engine, the order management engine, and the trading strategy offload engine share the same shared addressable memory space, the ticker plant engine being assigned a first portion of the shared addressable memory space, the order management engine being assigned a second portion of the shared addressable memory space, and the trading strategy offload engine being assigned a third portion of the shared addressable memory space.

47. The apparatus of claim 46 wherein the peer-to-peer hardware interconnect comprises a PCI Express bus.

48. The apparatus of claim 46 wherein the trading platform further comprises:

a base address register (BAR), the BAR configured to define the first, second, and third portions of the shared addressable memory space for the ticker plant engine, the order management engine, and the trading strategy offload engine.

49. The apparatus of claim 6 wherein the ticker plant engine, the order management engine, the trading strategy offload engine, and the trading strategy software application are configured for parallel operation such that each of the ticker plant engine, the order management engine, the trading strategy offload engine, and the trading strategy software application are configured to operate simultaneously.

93. The apparatus of claim 1 wherein the trading platform further comprises a software subsystem and a hardware subsystem, wherein the host processor and the host memory are part of the software subsystem, and wherein the ticker plant engine, the order management engine, and the peer-to-peer hardware interconnect are part of the hardware subsystem.

94. The apparatus of claim 93 wherein the trading platform is resident in a single appliance.

95. The apparatus of claim 1 wherein the shared memory is resident in the order management engine.

96. The apparatus of claim 6 wherein the trading strategy software application is configured to read the normalized financial market data from the memory shared by the ticker plant engine and the host system without receiving and parsing messages to extract data fields.

9. An apparatus comprising:

a trading platform, the trading platform configured to receive and process streaming financial market data, wherein the trading platform comprises;

a host system, the host system comprising a host processor and host memory;

a ticker plant engine, the ticker plant engine configured to receive and normalize a stream of financial market data, wherein the ticker plant engine is deployed on a member of the group consisting of (1) a reconfigurable logic device, (2) a graphics processor unit (GPU), and (3) a chip multi-processor (CMP);

a trading strategy offload engine, the trading strategy offload engine configured to implement at least a portion of a trading strategy based on the normalized financial market data, wherein the trading strategy offload engine is deployed on a member of the group consisting of (1) a reconfigurable logic device,

     2) a GPU, and (3) a CMP;

a shared memory, wherein the shared memory includes memory space that is read/write addressable by the ticker plant engine and the trading strategy offload engine; and

a peer-to-peer hardware interconnect configured to interconnect the trading strategy offload engine and the ticker plant engine via the shared memory; and

wherein the host processor and the host memory are configured to (1) process data in support of financial instrument trading based on normalized financial market data received from the ticker plant engine and (2) communicate with the trading strategy offload engine regarding the trading strategy; and

wherein the ticker plant engine is configured to write the normalized financial market data to the shared addressable memory space to thereby communicate the normalized financial market data to the trading strategy offload engine via the peer-to-peer hardware interconnect without using the host processor and without using the host memory.

50. The apparatus of claim 9 wherein the trading strategy offload engine is configured to implement a first portion of the trading strategy based on the normalized financial market data, wherein the host processor and host memory are configured to execute a second portion of the trading strategy via a software application, wherein the trading platform further comprises:

a memory shared by the ticker plant engine and the host system, wherein the ticker plant engine is further configured to write normalized financial market data to the memory shared by the ticker plant engine and the host system; and

a hardware-software interconnect channel configured to interconnect the trading strategy software application and the trading strategy offload engine; and

wherein the trading strategy software application is configured to (1) read the normalized financial market data from the memory shared by the ticker plant engine and the host system, (2) offload the first portion of the trading strategy to the trading strategy offload engine via the hardware-software interconnect channel, and (3) execute the second portion of the trading strategy based on the read normalized financial market data and an interaction with the trading strategy offload engine via the hardware-software interconnect channel.

51. The apparatus of claim 9 wherein the ticker plant engine is deployed on a first device, wherein the first device is a member of the group consisting of the reconfigurable logic device, the GPU, and the CMP;

wherein the trading strategy offload engine is deployed on a second device, wherein the second device is a member of the group consisting of the reconfigurable logic device, the GPU, and the CMP; and

wherein the ticker plant engine is assigned a first portion of the shared addressable memory space and the trading strategy offload engine is assigned a second portion of the shared addressable memory space.

52. The apparatus of claim 51 wherein the peer-to-peer hardware interconnect comprises a PCI Express bus.

53. The apparatus of claim 51 wherein the trading platform further comprises:

a base address register (BAR), the BAR configured to define the first and second portions of the shared addressable memory space for the ticker plant engine and the trading strategy offload engine.

54. The apparatus of claim 9 wherein the ticker plant engine is deployed on a first field programmable gate array (FPGA), and wherein the trading strategy offload engine is deployed on a second FPGA.

55. The apparatus of claim 9 wherein the ticker plant engine is deployed on a first GPU, and wherein the trading strategy offload engine is deployed on a second GPU.

56. The apparatus of claim 9 wherein the ticker plant engine is deployed on a first CMP, and wherein the order management engine is deployed on a second CMP.

57. The apparatus of claim 9 wherein the ticker plant engine is deployed on a field programmable gate array (FPGA), and wherein the trading strategy offload engine is deployed on a GPU.

58. The apparatus of claim 9 wherein the ticker plant engine is deployed on a field programmable gate array (FPGA), and wherein the trading strategy offload engine is deployed on a CMP.

97. The apparatus of claim 9 wherein the shared memory is resident in the trading strategy offload engine.

13. A method comprising:

receiving and processing, by a trading platform, streaming financial market data, the trading platform comprising;

a host system, the host system comprising a host processor and host memory;

a ticker plant engine, wherein the ticker plant engine is deployed on a member of the group consisting of (1) a reconfigurable logic device, (2) a graphics processor unit (GPU), and (3) a chip multi-processor (CMP);

an order management engine, wherein the order management engine is deployed on a member of the group consisting of (1) a reconfigurable logic device, (2) a GPU, and (3) a CMP;

a shared memory, wherein the shared memory includes memory space that is read/write addressable by the ticker plant engine and the order management engine; and

a peer-to-peer hardware interconnect configured to interconnect the ticker plant engine and the order management engine via the shared memory; and

wherein the host processor and the host memory are configured to (1) process data in support of financial instrument trading based on normalized financial market data received from the ticker plant engine and (2) communicate with the order management engine regarding a plurality of the financial instrument orders; and

wherein the receiving and processing step comprises;

the ticker plant engine receiving and normalizing a stream of financial market data;

the order management engine managing a plurality of financial instrument orders based on the normalized financial market data; and

the ticker plant engine writing the normalized financial market data to the shared addressable memory space and thereby communicating the normalized financial market data to the order management engine via the peer-to-peer hardware interconnect without using the host processor and without using the host memory.

14. The method of claim 13 wherein the trading platform further comprises:

a trading strategy offload engine, wherein the trading strategy offload engine is deployed on a member of the group consisting of (1) a reconfigurable logic device, (2) a GPU, and (3) a CMP; and

wherein the shared memory further includes memory space that is read/write addressable by the ticker plant engine and the trading strategy offload engine;

wherein the peer-to-peer hardware interconnect is further configured to interconnect the ticker plant engine and the trading strategy offload engine via the shared memory;

wherein the method further comprises;

the trading strategy offload engine implementing at least a portion of a trading strategy based on the normalized financial market data; and

the ticker plant engine writing the normalized financial market data to the addressable memory space shared by the ticker plant engine and the trading strategy offload engine and thereby communicating the normalized financial market data to the trading strategy offload engine via the peer-to-peer hardware interconnect without using the host processor and without using the host memory.

15. The method of claim 14 wherein the trading strategy offload engine comprises a basket calculation engine.

16. The method of claim 14 wherein the trading strategy offload engine comprises an options pricing engine.

17. The method of claim 14 wherein the trading strategy offload engine comprises a rules engine.

18. The method of claim 14 further comprising:

the host processor and host memory executing the trading strategy via a software application, wherein the trading platform further comprises (1) a memory shared by the ticker plant engine and the host system, and (2) a hardware-software interconnect channel configured to interconnect the trading strategy software application and the trading strategy offload engine; and

the ticker plant engine writing normalized financial market data to the memory shared by the ticker plant engine and the host system; and

wherein the executing step further comprises the trading strategy software application (1) reading the normalized financial market data from the memory shared by the ticker plant engine and the host system, (2) offloading a portion of the trading strategy to the trading strategy offload engine via the hardware-software interconnect channel, and (3) executing the trading strategy based on the read normalized financial market data and an interaction with the trading strategy offload engine via the hardware-software interconnect channel.

19. The method of claim 18 wherein the hardware-software interconnect channel is further configured to interconnect the trading strategy software application and the order management engine, and wherein the executing step further comprises:

the trading strategy software application (1) generating a plurality of orders based on the execution of the trading strategy, and (2) communicating the generated orders to the order management engine via the hardware-software interconnect channel.

20. The method of claim 18 wherein the executing step further comprises the host processor and host memory executing a plurality of the trading strategy software applications.

22. The method of claim 13 further comprising the host processor interacting with the host memory and executing a trading strategy via a software application, wherein the trading platform further comprises:

a memory shared by the ticker plant engine and the host system; and

wherein the method further comprises;

the ticker plant engine writing normalized financial market data to the memory shared by the ticker plant engine and the host system; and

wherein the executing step further comprises the trading strategy software application (1) reading the normalized financial market data from the memory shared by the ticker plant engine and the host system, and (2) executing the trading strategy based on the read normalized financial market data.

23. The method of claim 14 further comprising the ticker plant engine, the order management engine, and the trading strategy offload engine operating simultaneously in parallel.

24. The method of claim 13 wherein the ticker plant engine and the order management engine are deployed on different reconfigurable logic devices.

59. The method of claim 13 wherein the ticker plant engine is deployed on a first device, wherein the first device is a member of the group consisting of the reconfigurable logic device, the GPU, and the CMP;

wherein the order management engine is deployed on a second device, wherein the second device is a member of the group consisting of the reconfigurable logic device, the GPU, and the CMP; and

wherein the ticker plant engine is assigned a first portion of the shared addressable memory space and the order management engine is assigned a second portion of the shared addressable memory space.

60. The method of claim 59 wherein the peer-to-peer hardware interconnect comprises a PCI Express bus.

61. The method of claim 59 wherein the trading platform further comprises:

a base address register (BAR), the BAR defining the first and second portions of the shared addressable memory space for the ticker plant engine and the order management engine.

62. The method of claim 13 wherein the ticker plant engine is deployed on a first field programmable gate array (FPGA), and wherein the order management engine is deployed on a second FPGA.

63. The method of claim 13 wherein the ticker plant engine is deployed on a first GPU, and wherein the order management engine is deployed on a second GPU.

64. The method of claim 13 wherein the ticker plant engine is deployed on a first CMP, and wherein the order management engine is deployed on a second CMP.

65. The method of claim 13 wherein the ticker plant engine is deployed on a field programmable gate array (FPGA), and wherein the order management engine is deployed on a GPU.

66. The method of claim 13 wherein the ticker plant engine is deployed on a field programmable gate array (FPGA), and wherein the order management engine is deployed on a CMP.

67. The method of claim 13 further comprising the ticker plant engine and the order management engine operating simultaneously in parallel.

68. The method of claim 14 wherein the ticker plant engine is deployed on a first device, wherein the first device is a member of the group consisting of the reconfigurable logic device, the GPU, and the CMP;

wherein the order management engine is deployed on a second device, wherein the second device is a member of the group consisting of the reconfigurable logic device, the GPU, and the CMP;

wherein the trading strategy offload engine is deployed on a third device, wherein the third device is a member of the group consisting of the reconfigurable logic device, the GPU, and the CMP; and

wherein the ticker plant engine, the order management engine, and the trading strategy offload engine share the same shared addressable memory space, the ticker plant engine being assigned a first portion of the shared addressable memory space, the order management engine being assigned a second portion of the shared addressable memory space, and the trading strategy offload engine being assigned a third portion of the shared addressable memory space.

69. The method of claim 68 wherein the peer-to-peer hardware interconnect comprises a PCI Express bus.

70. The method of claim 68 wherein the trading platform further comprises:

a base address register (BAR), the BAR defining the first, second, and third portions of the shared addressable memory space for the ticker plant engine, the order management engine, and the trading strategy offload engine.

71. The method of claim 18 further comprising the ticker plant engine, the order management engine, the trading strategy offload engine, and the trading strategy software application operating simultaneously in parallel.

98. The method of claim 13 wherein the shared memory is resident in the order management engine.

21. A method comprising:

receiving and processing, by a trading platform, streaming financial market data, wherein the trading platform comprises;

a host system, the host system comprising a host processor and host memory;

a trading strategy offload engine, wherein the trading strategy offload engine is deployed on a member of the group consisting of (1) a reconfigurable logic device, (2) a graphics processor unit (GPU), and (3) a chip multi-processor (CMP);

a ticker plant engine, wherein the ticker plant engine is deployed on a member of the group consisting of (1) a reconfigurable logic device, (2) a GPU, and (3) a CMP;

a shared memory, wherein the shared memory includes memory space that is read/write addressable by the ticker plant engine and the trading strategy offload engine; and

a peer-to-peer hardware interconnect configured to interconnect the trading strategy offload engine and the ticker plant engine via the shared memory; and

wherein the host processor and the host memory are configured to (1) process data in support of financial instrument trading based on normalized financial market data received from the ticker plant engine and (2) communicate with the order management engine regarding a plurality of the financial instrument orders; and

wherein the receiving and processing step comprises;

the ticker plant engine receiving and normalizing a stream of financial market data;

the trading strategy offload engine implementing at least a portion of a trading strategy based on the normalized financial market data; and

the ticker plant engine writing the normalized financial market data to the shared addressable memory space and thereby communicating the normalized financial market data to the trading strategy offload engine via the peer-to-peer hardware interconnect without using the host processor and without using the host memory.

72. The method of claim 21 further comprising:

the host processor and host memory executing a trading strategy via a software application, wherein the trading platform further comprises (1) a memory shared by the ticker plant engine and the host system, and (2) a hardware-software interconnect channel configured to interconnect the trading strategy software application and the trading strategy offload engine; and

the ticker plant engine writing normalized financial market data to the memory shared by the ticker plant engine and the host system; and

wherein the executing step comprises the trading strategy software application (1) reading the normalized financial market data from the memory shared by the ticker plant engine and the host system, (2) offloading a portion of the trading strategy to the trading strategy offload engine via the hardware-software interconnect channel, and (3) executing the trading strategy based on the read normalized financial market data and an interaction with the trading strategy offload engine via the hardware-software interconnect channel.

73. The method of claim 21 wherein the ticker plant engine is deployed on a first device, wherein the first device is a member of the group consisting of the reconfigurable logic device, the GPU, and the CMP;

wherein the trading strategy offload engine is deployed on a second device, wherein the second device is a member of the group consisting of the reconfigurable logic device, the GPU, and the CMP; and

wherein the ticker plant engine is assigned a first portion of the shared addressable memory space and the trading strategy offload engine is assigned a second portion of the shared addressable memory space.

74. The method of claim 73 wherein the peer-to-peer hardware interconnect comprises a PCI Express bus.

75. The method of claim 73 wherein the trading platform further comprises:

a base address register (BAR), the BAR defining the first and second portions of the shared addressable memory space for the ticker plant engine and the trading strategy offload engine.

76. The method of claim 21 wherein the ticker plant engine is deployed on a first field programmable gate array (FPGA), and wherein the trading strategy offload engine is deployed on a second FPGA.

77. The method of claim 21 wherein the ticker plant engine is deployed on a first GPU, and wherein the trading strategy offload engine is deployed on a second GPU.

78. The method of claim 21 wherein the ticker plant engine is deployed on a first CMP, and wherein the order management engine is deployed on a second CMP.

79. The method of claim 21 wherein the ticker plant engine is deployed on a field programmable gate array (FPGA), and wherein the trading strategy offload engine is deployed on a GPU.

80. The method of claim 21 wherein the ticker plant engine is deployed on a field programmable gate array (FPGA), and wherein the trading strategy offload engine is deployed on a CMP.

99. The method of claim 21 wherein the shared memory is resident in the trading strategy offload engine.

25. An apparatus comprising:

a trading platform, the trading platform configured to receive and process streaming financial market data, the trading platform comprising;

a host computer system, the host computer system comprising a host processor and a host memory, the host processor configured to execute a trading strategy via a software application; and

a trading strategy offload engine configured to offload from the host computer system a portion of the trading strategy with respect to one or more financial instruments and one or more financial markets, wherein the trading strategy offload engine is deployed on a member of the group consisting of (1) a reconfigurable logic device, (2) a graphics processor unit (GPU), and (3) a chip multi-processor (CMP);

a hardware-software interconnect channel configured to interconnect the trading strategy software application and the trading strategy offload engine;

an order management engine, the order management engine configured to manage a plurality of financial instrument orders generated as a result of the trading strategy, wherein the order management engine is deployed on a member of the group consisting of (1) a reconfigurable logic device, (2) a GPU, and (3) a CMP;

a shared memory, wherein the shared memory includes memory space that is read/write addressable by the trading strategy offload engine and the order management engine; and

a peer-to-peer hardware interconnect configured to interconnect the trading strategy offload engine and the order management engine; and

wherein the trading strategy software application and the trading strategy offload engine are configured to communicate with each other via the hardware-software interconnect channel to implement the trading strategy; and

wherein the trading strategy offload engine and the order management engine are configured to communicate with each other over the peer-to-peer hardware interconnect via the shared memory without using the host processor and without using the host memory.

26. The apparatus of claim 25 wherein the trading strategy offload engine comprises a basket calculation engine.

27. The apparatus of claim 25 wherein the trading strategy offload engine comprises an options pricing engine.

28. The apparatus of claim 25 wherein the trading strategy offload engine comprises a rules engine.

29. The apparatus of claim 25 wherein the trading strategy offload engine is deployed on a reconfigurable logic device.

30. The apparatus of claim 29 wherein the reconfigurable logic device comprises a field programmable gate array (FPGA).

81. The apparatus of claim 25 wherein the trading strategy offload engine is deployed on a GPU.

82. The apparatus of claim 25 wherein the trading strategy offload engine is deployed on a CMP.

83. The apparatus of claim 25 wherein the trading strategy offload engine is deployed on a first device, wherein the first device is a member of the group consisting of the reconfigurable logic device, the GPU, and the CMP;

wherein the order management engine is deployed on a second device, wherein the second device is a member of the group consisting of the reconfigurable logic device, the GPU, and the CMP; and

wherein the peer-to-peer hardware interconnect has an addressable memory space, the trading strategy offload engine being assigned a first portion of the addressable memory space and the order management engine being assigned a second portion of the addressable memory space.

84. The apparatus of claim 83 wherein the peer-to-peer hardware interconnect comprises a PCI Express bus.

85. The apparatus of claim 83 wherein the trading platform further comprises:

a base address register (BAR), the BAR configured to define the first and second portions of the addressable memory space for the trading strategy offload engine and the order management engine.

86. The apparatus of claim 25 wherein the trading strategy offload engine is deployed on a first field programmable gate array (FPGA), and wherein the order management engine is deployed on a second FPGA.

31. A method comprising:

receiving and processing, by a trading platform, streaming financial market data, the trading platform comprising;

a host computer system, wherein the host computer system comprises a host processor and a host memory;

a trading strategy offload engine, wherein the trading strategy offload engine is deployed on a member of the group consisting of (1) a reconfigurable logic device, (2) a graphics processor unit (GPU), and (3) a chip multi-processor (CMP); and

a hardware-software interconnect channel configured to interconnect the trading strategy software application and the trading strategy offload engine;

an order management engine, wherein the order management engine is deployed on a member of the group consisting of (1) a reconfigurable logic device, (2) a GPU, and (3) a CMP;

a shared memory, wherein the shared memory includes memory space that is read/write addressable by the trading strategy offload engine and the order management engine; and

a peer-to-peer hardware interconnect configured to interconnect the trading strategy offload engine and the order management engine; and

wherein the receiving and processing step comprises (1) the trading strategy software application and the trading strategy offload engine communicating with each other via the hardware-software interconnect channel to implement the trading strategy, (2) the trading strategy offload engine offloading from the host computer system a portion of the trading strategy with respect to one or more financial instruments and one or more financial markets, (3) the order management engine managing a plurality of financial instrument orders generated as a result of the trading strategy, and (4) the trading strategy offload engine and the order management engine communicating with each other over the peer-to-peer hardware interconnect via the shared memory without using the host processor and without using the host memory.

32. The method of claim 31 wherein the trading strategy offload engine comprises a basket calculation engine.

33. The method of claim 31 wherein the trading strategy offload engine comprises an options pricing engine.

34. The method of claim 31 wherein the trading strategy offload engine comprises a rules engine.

35. The method of claim 31 wherein the trading strategy offload engine is deployed on a reconfigurable logic device.

36. The method of claim 35 wherein the reconfigurable logic device comprises a field programmable gate array (FPGA).

87. The method of claim 31 wherein the trading strategy offload engine is deployed on a GPU.

88. The method of claim 31 wherein the trading strategy offload engine is deployed on a CMP.

89. The method of claim 31 wherein the trading strategy offload engine is deployed on a first device, wherein the first device is a member of the group consisting of the reconfigurable logic device, the GPU, and the CMP;

wherein the order management engine is deployed on a second device, wherein the second device is a member of the group consisting of the reconfigurable logic device, the GPU, and the CMP; and

wherein the peer-to-peer hardware interconnect has an addressable memory space, the trading strategy offload engine being assigned a first portion of the addressable memory space and the order management engine being assigned a second portion of the addressable memory space.

90. The method of claim 89 wherein the peer-to-peer hardware interconnect comprises a PCI Express bus.

91. The method of claim 89 wherein the trading platform further comprises:

a base address register (BAR), the BAR configured to define the first and second portions of the addressable memory space for the trading strategy offload engine and the order management engine.

92. The method of claim 31 wherein the trading strategy offload engine is deployed on a first field programmable gate array (FPGA), and wherein the order management engine is deployed on a second FPGA.