System and method of computation in a programmable logic device using virtual instructions

• US 6,421,817 B1
• Filed: 04/03/2000
• Issued: 07/16/2002
• Est. Priority Date: 05/29/1997
• Status: Expired due to Term

• Current Assignee: Xilinx, Inc. (Advanced Micro Devices, Inc.)
• Original Assignee: Xilinx, Inc. (Advanced Micro Devices, Inc.)
• Inventors: Trimberger, Stephen M., Mohan, Sundararajarao
• Primary Examiner(s): Siek, Vuthe
• Application Number:
  US09/541,530
• Time in Patent Office: 834 Days
• Field of Search: 716/16, 716/17
• US Class Current: 716/117
• CPC Class Codes: G06F 15/7867 with reconfigurable architecture

Abstract

An FPGA configuration provides a virtual instruction. In a generic computation, the output pattern of a first instruction is compared to the input pattern of a second instruction. If the input and output patterns of the first and second instructions do not match, then a pattern manipulation instruction is inserted between the first and second instructions. At this point, the input and output patterns of the first and second instructions should match and the computation task can be completed. The method of providing virtual instructions is applicable to any FPGA. In a standard FPGA, the data stored in the storage elements of the FPGA, such as flip-flops, is retained for the next configuration of the FPGA. In this manner, successive configurations can communicate data using the patterns of the storage elements, thereby allowing standard FPGAs to implement virtual instructions. Alternatively, a standard FPGA could write out data to an external memory using a predetermined pattern of addresses. In a subsequent configuration of the FPGA, the device could read data back from this pattern of addresses in the external memory. This embodiment allows various patterns of addresses, corresponding to data, to be used in any appropriate subsequent configuration of the FPGA. In this manner, the plurality of memory planes, previously provided on the dynamically reconfigurable FPGA, can be implemented off-chip.

Claims

1. A method for computation in a programmable logic device (PLD), the PLD including a logic plane and a plurality of memory planes, the method comprising:

determining a first instruction of a computation task, wherein the first instruction has a first input pattern and a first output pattern;

determining a second instruction of the computation, wherein the second instruction has a second input pattern and a second output pattern, further wherein the second instruction receives data from the first instruction; and

comparing the first output pattern to the second input pattern,

wherein if the first output pattern fails to match the second input pattern, then inserting a pattern manipulation instruction, and

wherein if the first output pattern matches the second input pattern, then completing the computation task.

2. The method of claim 1, wherein the first input pattern and the first output pattern are the same.

3. The method of claim 1, wherein the second input pattern and the second output pattern are the same.

4. The method of claim 1, wherein the step of inserting includes choosing the pattern manipulation instruction from a library.

5. The method of claim 1, wherein the step of inserting includes creating the pattern manipulation instruction by generating a new PLD configuration.

6. A method for computation in a programmable logic device (PLD), the PLD including a logic plane and at least one memory plane, the method comprising:

providing a first virtual instruction corresponding to a first configuration of the logic plane;

providing a second virtual instruction corresponding to a second configuration of the logic plane;

wherein the first virtual instruction provides a predetermined data pattern on the memory plane to the second virtual instruction.

7. The method of claim 6, wherein the predetermined data pattern is provided by a plurality of storage elements.

8. The method of claim 7, wherein at least one of the storage elements is a flip-flop.

9. The method of claim 6, wherein the first configuration directs the PLD to write out data to a predetermined pattern of addresses in an external memory and the second configuration directs the PLD to read data back from the predetermined pattern of addresses.

10. The method of claim 9, wherein the first and second configurations are successive.

11. The method of claim 9, wherein at least one other configuration is performed between the first and second configurations.

12. The method of claim 6, wherein the first configuration is a partial configuration occupying a first physical area of the PLD and the second configuration is another partial configuration occupying a second physical area of the PLD.

13. The method of claim 12, wherein the second physical area overlaps the first physical area.

14. The method of claim 13, wherein the predetermined data pattern is stored only in the second physical area.

15. The method of claim 14, wherein the second configuration, when activated, retrieves the predetermined data pattern from the second physical area.

16. The method of claim 12, wherein the second physical area does not overlap the first physical area.

17. The method of claim 16, further including creating a pattern manipulation instruction to include both the first and second physical areas.

18. A computation system for a programmable logic device, the system comprising:

a virtual instruction library, wherein each virtual instruction operates on user data in the programmable logic device, wherein the virtual instruction library includes a plurality of templates.

19. The system of claim 18, wherein at least one template can be customized with additional functionality.

20. The system of claim 18, wherein the virtual instruction library further includes a plurality of parameters for customizing the plurality of templates.

21. The system of claim 19, further includes a user interface to allow customizing the plurality of templates.

22. The system of claim 18, wherein the virtual instruction library further includes a plurality of input/output patterns.

23. The system of claim 18, further including a user interface to allow creating virtual instructions.