Instruction paging in reconfigurable fabric
View Patent ↗Circular buffers containing instructions that enable the execution of operations on logical elements are described where data in the circular buffers is swapped to storage. Data stored in circular buffers is paged in and out to a second level memory. State information for each logical element is also saved and restored using paging memory. Logical elements such as processing elements are provided instructions via circular buffers. The instructions enable a group of processing elements to perform operations implementing a desired functionality. That functionality is changed by updating the circular buffers with new instructions that are transferred from paging memory. The previous instructions can be saved off in paging memory before the new instructions are copied over to the circular buffers. This enables the hardware to be rapidly reconfigured amongst multiple functions.
1. A processor-implemented method for computation comprising:
paging data stored in a plurality of circular buffers where the paging comprises:
copying data from a first storage memory into the plurality of circular buffers where:
the plurality of circular buffers is coupled to logical elements where the plurality of circular buffers controls the logical elements, wherein the plurality of circular buffers have differing lengths, and wherein the plurality of circular buffers that have differing lengths resynchronize with a zeroth pipeline stage for each of the plurality of circular buffers;
the data provides instructions for the logical elements; and
as the circular buffers rotate, instructions change that are delivered to the logical elements.
2. The method of claim 1 wherein the paging further comprises copying the data stored in the plurality of circular buffers into a second storage memory.
3. The method of claim 2 further comprising storing state information in the second storage memory.
4. The method of claim 1 wherein the instructions that change, that are delivered to the logical elements, provide a first sequence of operations by the logical elements.
5. The method of claim 4 wherein the data from the first storage memory provides a second set of instructions to the logical elements.
6. The method of claim 1 wherein the plurality of circular buffers have differing lengths.
7. The method of claim 6 wherein the plurality of circular buffers include a first circular buffer repeating at one frequency and a second circular buffer repeating at a second frequency.
8. An apparatus for computation comprising:
a plurality of circular buffers where the plurality of circular buffers contains instructions for logical elements, coupled to the plurality of circular buffers, where the plurality of circular buffers contains a first copy of instructions, wherein the plurality of circular buffers have differing lengths, and wherein the plurality of circular buffers that have differing lengths resynchronize with a zeroth pipeline stage for each of the plurality of circular buffers;
a storage memory containing a second copy of instructions for the plurality of circular buffers where the storage memory is coupled to the plurality of circular buffers; and
a set of switches and connections, coupled to the plurality of circular buffers, for transferring contents of the storage memory to the plurality of circular buffers, wherein the contents comprise instructions for the logical elements, and wherein as the plurality of circular buffers rotates, instructions that are delivered to the logical elements change.
9. The apparatus of claim 8 wherein the first copy of instructions is swappable to a swapping memory.
10. The apparatus of claim 9 wherein the swapping memory further contains state information that is copied from circuitry associated with the plurality of circular buffers.
11. The apparatus of claim 8 further comprising a further storage memory for a third copy of instructions for the plurality of circular buffers where the further storage memory is coupled to the plurality of circular buffers; and a further set of switches and connections for transferring contents of the further storage memory to the plurality of circular buffers.
12. The apparatus of claim 11 wherein the first copy of instructions is copied to a swapping memory before the third copy of instructions is moved into the plurality of circular buffers.
13. The apparatus of claim 8 wherein other circular buffers, than the plurality of circular buffers, continue to rotate while the set of switches and connections transfers contents of the storage memory to the plurality of circular buffers.
14. The apparatus of claim 8 wherein other circular buffers, than the plurality of circular buffers, continue to rotate while a third copy of instructions are transferred to the plurality of circular buffers.
15. The apparatus of claim 14 further comprising stable configuration logic to maintain a stable configuration while rotation occurs.
16. The apparatus of claim 8 wherein, as the circular buffers rotate, instructions change that are delivered to the logical elements.
17. The apparatus of claim 16 wherein the instructions that change, that are delivered to the logical elements, provide a first sequence of operations by the logical elements.
18. The apparatus of claim 17 wherein the data from the storage memory provides a second set of instructions to the logical elements.
19. The apparatus of claim 18 wherein the second set of instructions provide a second sequence of operations by the logical elements.
20. The apparatus of claim 19 wherein the first sequence of operations and the second sequence of operations differ.
21. The apparatus of claim 8 wherein the plurality of circular buffers dynamically change operations of the logical elements based on circular buffer rotation.
22. A computer program product embodied in a non-transitory computer readable medium for implementation of a logical calculation apparatus comprising:
code for designing a processing architecture including:
a plurality of circular buffers where the plurality of circular buffers contains instructions for logical elements, coupled to the plurality of circular buffers, where the plurality of circular buffers contains a first copy of instructions, wherein the plurality of circular buffers have differing lengths, and wherein the plurality of circular buffers that have differing lengths resynchronize with a zeroth pipeline stage for each of the plurality of circular buffers;
a storage memory containing a second copy of instructions for the plurality of circular buffers where the storage memory is coupled to the plurality of circular buffers; and
a set of switches and connections, coupled to the plurality of circular buffers, for transferring contents of the storage memory to the plurality of circular buffers, wherein the contents comprise instructions for the logical elements, and wherein as the plurality of circular buffers rotates, instructions that are delivered to the logical elements change.