Machine perception and dense algorithm integrated circuit

1. An integrated circuit comprising:

a first plurality of processing cores and a second plurality of processing cores that define an array of cores within the integrated circuit;

data handling circuitry that interface with one or more memory circuits; and

a subset of the first plurality of processing cores being arranged between the data handling circuitry and the second plurality of processing cores, wherein a circuitry of each of the second plurality of processing cores includes:

a register file; and

a plurality of distinct data processing circuits comprising a plurality of multiply accumulators, each of the plurality of multiply accumulators being arranged adjacent a data input/output port of a respective processing core of the second plurality of processing cores.

2. The integrated circuit according to claim 1 , wherein

the first plurality of processing cores:

(a) accepts data into the array of cores and

(b) transmits data out of the array of cores.

3. The integrated circuit according to claim 1 , wherein

the data handling circuitry:

(a) are arranged outside of the array of cores;

(b) transmits input data from the one or more memory circuits into the first plurality of processing cores; and

(c) accepts output data from the first plurality of processing cores.

4. The integrated circuit according to claim 1 , wherein

each processing core of the second plurality of processing cores interfaces with one or more processing cores of the first plurality of processing cores and one or more neighboring processing cores of the second plurality of cores.

5. The integrated circuit according to claim 1 , wherein

the second plurality of processing cores:

(a) accepts input data from the first plurality of processing cores;

(b) processes the input data;

(c) transmits the processed input data as output data to the first plurality of processing cores.

6. The integrated circuit according to claim 1 , wherein

a subset of the second plurality of processing cores is encompassed entirely by neighboring cores of the second plurality of processing cores.

7. The integrated circuit according to claim 6 , wherein

a distinct subset of the second plurality of processing cores is encompassed by one or more of the second plurality of processing cores and one or more of the first plurality of processing cores.

8. The integrated circuit according to claim 1 , wherein

a circuitry architecture of the first plurality of processing cores is distinct from a circuitry architecture of the second plurality of processing cores.

9. The integrated circuit according to claim 1 , wherein

each processing core of the second plurality of processing cores includes:

a plurality of data input/output ports, wherein a data input/output port of the plurality of data input/output ports is arranged at each side of each processing core of the second plurality of processing cores,

wherein each of the data input/output ports of a given processing core of the second plurality of processing cores interfaces with one or more of the register file and another data input/output port of the given processing core.

10. The integrated circuit according to claim 1 ,

a circuitry of the first plurality of processing cores include:

a register file; and

a plurality of data input/output ports, wherein a data input/output port of the plurality of data input/output ports is arranged at each side of each processing core of the second plurality of processing cores,

wherein each of the data input/output ports of a given processing core of the first plurality of processing cores interfaces with one or more of the register file and another data input/output port of the given processing core.

11. The integrated circuit according to claim 1 , wherein

a propagation of input data within the integrated circuit includes passing the input data from the data handling circuitry into one or more of the plurality of first processing cores and passing the input data from the one or more of the plurality of first processing cores into one or more of the second plurality of processing cores that performs one or more computations against the input data.

12. The integrated circuit according to claim 1 , wherein

a propagation of output data within the integrated circuit includes after a processing of input data by the second plurality of processing cores, passing the output data from one or more of the second plurality of processing cores into one or more of the first plurality of processing cores, and passing the output data from the first plurality of processing cores into the data handling circuitry arranged outside of the array of cores.

13. The integrated circuit according to claim 1 , wherein

the data handling circuitry controls a movement of data between the array of cores and a hierarchical memory structure of the integrated circuit.

14. The integrated circuit according to claim 13 , wherein

the hierarchical memory structure enables direct memory access between a main memory and array of cores, the hierarchical memory structure includes:

a plurality of dual FIFOs that transmit and accept data on a first-in, first-out basis,

a plurality of periphery load stores that each interface with a respective dual FIFO of the plurality of dual FIFOs and store one or more loads of data that is either received from the respective dual FIFO or that is pending a loading into the respective dual FIFO, and

a plurality of periphery memory that each interface with a respective periphery load store of the plurality of periphery load stores and interfaces with the main memory.

15. The integrated circuit according to claim 1 , wherein

the hierarchical memory structure being implemented as a two-dimensional direct memory access enabling data access and data reshaping during data transfers.

16. The integrated circuit according to claim 1 , further comprising:

a dispatch controller comprising:

a compute instructions generator circuit that provides computation instructions for each of the second plurality of processing cores; and

a data movement generator circuit that provides a data flow schedule that defines predetermined movements of data within the integrated circuit.

17. The integrated circuit according to claim 1 , further comprising:

a broadcast bus arranged in electrical communication with the data handling circuits at a first input terminal of the broadcast bus and in electrical communication with a subset of the array of cores at a plurality of output terminals of the broadcast bus.

18. An integrated circuit comprising:

a first plurality of processing cores and a second plurality of processing cores that define an array of cores within the integrated circuit;

data handling circuitry that interface with one or more memory circuits, wherein the data handling circuitry controls a movement of data between the array of cores and a hierarchical memory structure of the integrated circuit;

a subset of the first plurality of processing cores being arranged between the data handling circuitry and the second plurality of processing cores; and

a hierarchical memory structure that enables direct memory access between a main memory and array of cores, the hierarchical memory structure includes:

a plurality of dual FIFOs that transmit and accept data on a first-in, first-out basis,

a plurality of periphery load stores that each interface with a respective dual FIFO of the plurality of dual FIFOs and store one or more loads of data that is either received from the respective dual FIFO or that is pending a loading into the respective dual FIFO, and

a plurality of periphery memory that each interface with a respective periphery load store of the plurality of periphery load stores and interfaces with the main memory.

19. An integrated circuit comprising:

a first plurality of processing cores and a second plurality of processing cores that define an array of cores within the integrated circuit;

data handling circuitry that interface with one or more memory circuits; and

a subset of the first plurality of processing cores being arranged between the data handling circuitry and the second plurality of processing cores;

a dispatch controller comprising:

a compute instructions generator circuit that provides computation instructions for each of the second plurality of processing cores; and

a data movement generator circuit that provides a data flow schedule that defines predetermined movements of data within the integrated circuit.