Systems and methods for determining a configuration for a microarchitecture

At least one non-transitory computer-readable medium comprising instructions that, when executed, cause at least one processor to at least:

• generate a candidate configuration of parameters for a microarchitecture;
• execute a machine learning model with the candidate configuration of parameters to generate estimated performance indicators;
• determine whether the estimated performance indicators are reliable;
• determine if the estimated performance indicators correspond to an improvement toward a target relative to prior performance indicators from a prior candidate configuration;
• when the estimated performance indicators have not improved toward the target, accept the candidate configuration of parameters;
• and
• create a hardware description language (HDL) file based on the candidate configuration of parameters to be used to fabricate the microarchitecture.

A system for optimizing a configuration for a microarchitecture, the system comprising:

• means for generating a candidate configuration of parameters;
• means for applying machine learning to the candidate configuration of parameters to output estimated performance indicators;
• first means for determining whether the estimated performance indicators are reliable;
• second means for determining if the estimated performance indicators correspond to an improvement toward a target relative to prior performance indicators from a prior candidate configuration;
• means for accepting configuration of parameters when performance indicators have worsened with respect to the target;
• and
• means for accepting or rejecting the candidate configuration of parameters, wherein, if the estimated performance indicators have not improved, the accepting or rejecting means is to randomly reject or accept the candidate configuration of parameters.

A method for optimizing a configuration for a microarchitecture, the method comprising:

• generating, by executing an instruction with a processor, a candidate configuration of parameters;
• executing, by executing an instruction with the processor, a machine learning model with the candidate configuration of parameters to generate estimated performance indicators;
• determining, by executing an instruction with the processor, whether the estimated performance indicators are reliable;
• determining, by executing an instruction with the processor, if the estimated performance indicators correspond to an improvement toward a target relative to prior performance indicators from a prior candidate configuration;
• when the estimated performance indicators have worsened with respect to the target, accepting, by executing an instruction with the processor, the candidate configuration of parameters;
• and
• creating, by executing an instruction with the processor, a hardware description language (HDL) file based on the candidate configuration of parameters to be used to fabricate the microarchitecture.

A apparatus to determine a configuration for a microarchitecture, the apparatus comprising:

• memory;
• instructions included in the apparatus;
• and
• processor circuitry to execute the instructions to:
• generate a candidate configuration of parameters for the microarchitecture;
• process the candidate configuration of parameters to output estimated performance indicators for the microarchitecture;
• determine whether the estimated performance indicators are reliable;
• determine if the estimated performance indicators correspond to an improvement toward a target relative to prior performance indicators from a prior candidate configuration;
• in response to determining the estimated performance indicators have worsened with respect to the target, accept the candidate configuration of parameters;
• and
• create a hardware description language (HDL) file based on the candidate configuration of parameters to be used to fabricate the microarchitecture.