Systems and methods for NoC construction

1. A method for generating a Network on Chip (NoC), comprising:

determining a plurality of traffic flows from a NoC specification;

grouping the plurality of traffic flows into a plurality of groups based on characteristics of the NoC;

utilizing a first machine learning algorithm to determine a sorting order on each of the plurality of groups of traffic flows, the first machine learning algorithm configured to determine the sorting order according to one or more first cost functions;

generating a list of traffic flows for NoC construction from the plurality of groups of traffic flows based on the sorting order;

utilizing a second machine learning algorithm to select one or more mapping algorithms for each group of the plurality of groups of traffic flows for NoC construction; and

generating the NoC based on a mapping from the selection of the one or more mapping algorithms,

wherein the second machine learning algorithm is configured to select the one or more mapping algorithms by:

selecting a first mapping algorithm from the one or more mapping algorithms based on the second machine learning algorithm for one or more second cost functions;

executing the first mapping algorithm to map a first flow from the list of traffic flow groups;

for subsequent mapping of traffic flow groups from the list of traffic flow groups by the first mapping algorithm not meeting the one or more second cost functions, selecting a second mapping algorithm from the one or more mapping algorithms based on the second machine learning algorithm, the one or more second cost functions, and a current mapping status of the NoC.

2. The method of claim 1 , wherein the one or more mapping algorithms are configured to map each group of traffic flows of the plurality of groups of traffic flows individually.

3. The method of claim 1 , wherein the second machine learning algorithm is configured to select the one or more mapping algorithms for each group of traffic flows of the plurality of groups of traffic flows based on one or more second cost functions.

4. The method of claim 1 , further comprising:

selecting one or more traffic flow groups from the generated NoC for remapping based on a third cost function.

5. A non-transitory computer readable medium, storing instructions for generating a Network on Chip (NoC), the instructions comprising:

determining a plurality of traffic flows from a NoC specification;

grouping the plurality of traffic flows into a plurality of groups based on characteristics of the NoC;

utilizing a first machine learning algorithm to determine a sorting order on each of the plurality of groups of traffic flows, the first machine learning algorithm configured to determine the sorting order according to one or more first cost functions;

generating a list of traffic flows for NoC construction from the plurality of groups of traffic flows based on the sorting order;

utilizing a second machine learning algorithm to select one or more mapping algorithms for each group of the plurality of groups of traffic flows for NoC construction; and

generating the NoC based on a mapping from the selection of the one or more mapping algorithms,

wherein the second machine learning algorithm is configured to select the one or more mapping algorithms by:

selecting a first mapping algorithm from the one or more mapping algorithms based on the second machine learning algorithm for one or more second cost functions;

executing the first mapping algorithm to map a first flow from the list of traffic flow groups;

for subsequent mapping of traffic flow groups from the list of traffic flow groups by the first mapping algorithm not meeting the one or more second cost functions, selecting a second mapping algorithm from the one or more mapping algorithms based on the second machine learning algorithm, the one or more second cost functions, and a current mapping status of the NoC.

6. The non-transitory computer readable medium of claim 5 , wherein the one or more mapping algorithms are configured to map each group of traffic flows of the plurality of groups of traffic flows individually.

7. The non-transitory computer readable medium of claim 5 , wherein the second machine learning algorithm is configured to select the one or more mapping algorithms for each group of traffic flows of the plurality of groups of traffic flows based on one or more second cost functions.

8. The non-transitory computer readable medium of claim 5 , further comprising:

selecting one or more traffic flow groups from the generated NoC for remapping based on a third cost function.

9. An apparatus configured to generate a Network on Chip (NoC), the apparatus comprising:

a processor, configured to:

determine a plurality of traffic flows from a NoC specification;

group the plurality of traffic flows into a plurality of groups based on characteristics of the NoC;

utilize a first machine learning algorithm to determine a sorting order on each of the plurality of groups of traffic flows, the first machine learning algorithm configured to determine the sorting order according to a first cost function;

generate a list of traffic flows for NoC construction from the plurality of groups of traffic flows based on the sorting order;

utilize a second machine learning algorithm to select one or more mapping algorithms for each group of the plurality of groups of traffic flows for NoC construction; and

generate the NoC based on a mapping from the selection of the one or more mapping algorithms,

wherein the second machine learning algorithm is configured to select the one or more mapping algorithms by:

selecting a first mapping algorithm from the one or more mapping algorithms based on the second machine learning algorithm for one or more second cost functions;

executing the first mapping algorithm to map a first flow from the list of traffic flow groups;

for subsequent mapping of traffic flow groups from the list of traffic flow groups by the first mapping algorithm not meeting the one or more second cost functions, selecting a second mapping algorithm from the one or more mapping algorithms based on the second machine learning algorithm, the one or more second cost functions, and a current mapping status of the NoC.

10. The apparatus of claim 9 , wherein the one or more mapping algorithms are configured to map each group of traffic flows of the plurality of groups of traffic flows individually.

11. The apparatus of claim 9 , wherein the second machine learning algorithm is configured to select the one or more mapping algorithms for each group of traffic flows of the plurality of groups of traffic flows based on one or more second cost functions.

12. The apparatus of claim 9 , wherein the processor is further configured to:

select one or more traffic flow groups from the generated NoC for remapping based on a third cost function.