Machine perception and dense algorithm integrated circuit

• US 10,474,398 B2
• Filed: 06/13/2019
• Issued: 11/12/2019
• Est. Priority Date: 03/08/2018
• Status: Active Grant

• Current Assignee: quadric.io, Inc.
• Original Assignee: quadric.io, Inc.
• Inventors: Drego, Nigel, Sikka, Aman, Ravichandran, Mrinalini, Durbha, Ananth, Firu, Robert Daniel, Kheterpal, Veerbhan
• Primary Examiner(s): Coleman, Eric
• Application Number:
  US16/439,988
• Publication Number:
  US 20190310801A1
• Time in Patent Office: 152 Days
• Field of Search: None
• CPC Class Codes: G06F 15/80 comprising an array of processing units with common control, e.g. single instruction multiple data processors G06F15/82 takes precedence ; for correlation function computation G06F17/15
• CPC Class Codes: G06F 15/8023 Two dimensional arrays, e.g. mesh, torus
• CPC Class Codes: G06F 3/0655 Vertical data movement, i.e. input-output transfer; data movement between one or more hosts and one or more storage devices
• CPC Class Codes: G06F 3/0685 Hybrid storage combining heterogeneous device types, e.g. hierarchical storage, hybrid arrays
• CPC Class Codes: G06F 3/0688 Non-volatile semiconductor memory arrays
• CPC Class Codes: G06F 30/30 Circuit design
• CPC Class Codes: G06F 30/32 Circuit design at the digital level reconfigurable circuits G06F30/34
• CPC Class Codes: G06F 30/36 Circuit design at the analogue level

Abstract

A circuit that includes a plurality of array cores, each array core of the plurality of array cores comprising: a plurality of distinct data processing circuits; and a data queue register file; a plurality of border cores, each border core of the plurality of border cores comprising: at least a register file, wherein: [i] at least a subset of the plurality of border cores encompasses a periphery of a first subset of the plurality of array cores; and [ii] a combination of the plurality of array cores and the plurality of border cores define an integrated circuit array.

Claims

1. An integrated circuit comprising:

a plurality of processing cores, each processing core of the plurality of processing cores comprising;

at least one processing circuit; and

at least one memory circuit;

a plurality of peripheral cores, each peripheral core of the plurality of peripheral cores comprising;

at least one memory circuit,

wherein;

[i] at least a subset of the plurality of peripheral cores is arranged along a periphery of a first subset of the plurality of processing cores; and

[ii] a combination of the plurality of processing cores and the plurality of peripheral cores define an integrated circuit array;

a dispatch controller that provides data movement instructions, wherein the data movement instructions comprise a data flow schedule that;

defines an automatic movement of data within the integrated circuit array; and

sets one or more peripheral cores of the plurality of peripheral cores to a predetermined constant value if no data is provided to the one or more peripheral cores according to the predetermined data flow schedule.

2. The integrated circuit according to claim 1, wherein

the first subset of the plurality of processing cores encompasses a periphery of a second subset of the plurality of processing cores.

3. The integrated circuit according to claim 1, wherein

the at least one processing circuit of each of the plurality of processing cores comprises:

at least one multiply accumulator is arranged adjacent a data input/output port of a respective processing core of the plurality of processing cores.

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

a first plurality of dual FIFOs that loads data into the integrated circuit array on a first-in, first-out basis, such that an oldest dataset entering a respective dual FIFO of the first plurality of dual FIFOs is first disposed by the respective dual FIFO,

wherein the first plurality of dual FIFOs are arranged along a first peripheral side of the integrated circuit array;

a second plurality of dual FIFOs that loads data into the integrated circuit array on a first-in, first-out basis, such that an oldest dataset entering a respective dual FIFO of the second plurality of dual FIFOs is first disposed by the respective dual FIFO,

wherein the second plurality of dual FIFOs are arranged along a second peripheral side of the integrated circuit array that is distinct from the first peripheral side of the integrated circuit array.

5. The integrated circuit according to claim 4, wherein:

each of the first and the second plurality of dual FIFOs comprise at least two memory elements;

a first of the at least two memory elements pushes data into one of a peripheral core of the plurality of peripheral cores and an processing core of the plurality of processing cores of the integrated circuit array;

a second of the at least two memory elements collects data from the one of a peripheral core of the plurality of peripheral cores and an processing core of the plurality of processing cores of the integrated circuit array.

6. The integrated circuit according to claim 3, wherein:

each of the plurality of processing cores having a rectangular shape; and

the at least one multiply accumulator being arranged within the rectangular shape of each of the plurality of processing cores.

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

a first periphery memory and a second periphery memory that interface with unified memory, wherein;

the first periphery memory is arranged along a first peripheral side of the integrated circuit array and interfaces with a first periphery load store; and

the second periphery memory is arranged along a second peripheral side of the integrated circuit array and interfaces with a second periphery load store.

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

a hierarchical memory structure that enables direct memory access between a main memory and the integrated circuit array, the hierarchical memory structure includes;

a plurality of dual FIFOs that interfaces with the integrated circuit array and transmits and accepts 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 and/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.

9. The integrated circuit according to claim 8, further comprising:

a plurality of periphery controllers that, when executing data movement instructions, control a movement of data between the hierarchical memory structure and the integrated circuit array.

10. The integrated circuit according to claim 8, wherein

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

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

a dispatch controller that provides;

(i) data movement instructions that causes an automatic movement of data;

(a) between a hierarchical memory structure of the integrated circuit and the integrated circuit array;

(b) within each respective processing core of the plurality of processing cores;

(c) between respective processing cores and between processing cores and peripheral cores of the integrated circuit array; and

(ii) computation instructions that defines a plurality of computations to be executed by the plurality of processing cores of the integrated circuit array.

12. The integrated circuit according to claim 1, wherein

the data flow schedule comprises a schedule of memory address executable by one or more of a plurality of periphery load stores.

13. 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 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.

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

a broadcast bus arranged in electrical communication with one or more periphery controllers at a first input terminal of the broadcast bus and in electrical communication with a subset of the plurality of processing cores at a plurality of output terminals of the broadcast bus.

15. The integrated circuit according to claim 1, wherein

each of the plurality of processing cores is arranged in bi-directional communication with a neighboring core that includes one or more of the plurality processing cores and the plurality of peripheral cores.

16. The integrated circuit according to claim 1, wherein

each of the plurality of processing cores further comprises at least one arithmetic logic unit.

17. An integrated circuit comprising:

a plurality of processing cores, each processing core of the plurality of processing cores comprising;

at least one multiply accumulator; and

at least one memory circuit;

a plurality of peripheral cores, each peripheral core of the plurality of peripheral cores comprising;

at least one memory circuit,

wherein;

[i] at least a subset of the plurality of peripheral cores is arranged along a periphery of a first subset of the plurality of processing cores; and

[ii] a combination of the plurality of processing cores and the plurality of peripheral cores define an integrated circuit array;

a dispatch controller that provides data movement instructions, wherein the data movement instructions comprise a data flow schedule that;

defines an automatic movement of data within the integrated circuit array; and

sets one or more peripheral cores of the plurality of peripheral cores to a predetermined constant value if no data is provided to the one or more peripheral cores according to the predetermined data flow schedule.