Multi-processor with selectively interconnected memory units

1. A method of optimizing use of a multi-core processor in executing a data processing program, wherein the multi-core processor comprises (a) a plurality of data processor cores, each comprising an arithmetic logic unit, (b) a plurality of memories, and (c) a bus system selectively interconnecting the plurality of data processor cores and the plurality of memories, and wherein the multi-core processor is adapted for executing at least parts of the data processing program in a data-flow manner on parts of the multi-core processor and for executing at least parts of the data processing program in a sequential manner on parts of the multi-core processor that are specifically adapted for executing in a sequential manner, the method comprising:

carrying out a first partitioning of the data processing program into parts to be processed in the data flow manner and into parts having a local sequentiality;

rolling the parts having the local sequentiality together for execution on the parts of the multi-core processor that are specifically adapted for executing in the sequential manner;

judging whether sufficient resources are implemented for sequential processing or other processing; and

responsive to a result of the judging being that insufficient resources are implemented, carrying out a re-partitioning.

2. The method according to claim 1 , wherein the plurality of data processor cores comprise an instruction decoder.

3. The method according to claim 1 , wherein the multi-core processor further comprises at least one input-output (I/O) processor, and the bus system selectively interconnects at least one of said plurality of data processor cores, at least one of said plurality of memories, and at least one of said at least one I/O processor.

4. The method according to claim 1 , wherein at least two of said data processor cores are operable at at least two different clock frequencies.

5. The method according to claim 1 , wherein the multi-core processor further includes an instruction loader to transmit a program part, comprising one or more ALU instructions, to one or more of the plurality of memories.

6. The method according to claim 1 , wherein the multi-core processor further includes at least one Memory Management Unit (MMU).

7. The method according to claim 1 , wherein the bus system further selectively interconnects two or more of the data processor cores with each other.

8. The method according to claim 1 , wherein:

the multi-core processor comprises at least one instruction decoder and at least one input-output (I/O) processor; and

the bus system selectively interconnects at least one of said plurality of data processor cores, at least one of said plurality of memories, and at least one of said at least one I/O processor.

9. The method according to claim 1 , wherein:

the bus system selectively interconnects two or more of the data processor cores with each other;

the multi-core processor comprises an instruction loader to transmit a program part, comprising one or more ALU instructions, to one or more of the plurality of memories; and

at least two of said data processor cores are operable at at least two different clock frequencies.

10. The method according to claim 9 , wherein:

the multi-core processor comprises at least one instruction decoder and at least one input-output (I/O) processor; and

the bus system selectively interconnects at least one of said plurality of data processor cores, at least one of said plurality of memories, and at least one of said at least one I/O processor.