Automated microprocessor design
Systems and methods are disclosed for automated generation of integrated circuit designs and associated data. These allow the design of processors and SoCs by a single, non-expert who understands high-level requirements; allow the en masse exploration of the design-space through the generation processors across the design-space via simulation, or emulation; allow the easy integration of IP cores from multiple third parties into an SoC; allow for delivery of a multi-tenant service for producing processors and SoCs that are customized while also being pre-verified and delivered with a complete set of developer tools, documentation and related outputs. Some embodiments, provide direct delivery, or delivery into a cloud hosting environment, of finished integrated circuits embodying the processors and SoCs.
1. A system comprising:
a web application server configured to generate a design parameters data structure based on input received, wherein the design parameters data structure includes values of design parameters of an integrated circuit design, configured to display an auto-updating block diagram of a template design reflecting changes to values of the design parameters of the integrated circuit design, and configured to issue a command to build the integrated circuit design; and
a controller configured to, responsive to the command to build the integrated circuit design, access the design parameters data structure, invoke a register-transfer level service module with the design parameters data structure to obtain a register-transfer level data structure, invoke a software development kit service module with the register-transfer level data structure to obtain a software development kit, invoke a physical design service module with the register-transfer level data structure to obtain a physical design data structure, invoke a verification service module to obtain a test plan, and invoke tests for the integrated circuit design based on the test plan, the register-transfer level data structure, the software development kit, and the physical design data structure to obtain a set of test results; and
a machine learning based design iterator configured to take as input both, values of design parameters of the design parameters data structure, and a feedback signal based on a design criterion of the design parameters data structure and the set of test results, to obtain a modified design parameters data structure, and configured to issue a command to the controller to cause the controller to build a second integrated circuit design based on the modified design parameters data structure.
2. The system of claim 1 , wherein the machine learning based design iterator has been trained using training data that includes prior inputs to the machine learning based design iterator that included a respective feedback signal based on test results obtained by the controller.
3. The system of claim 1 , wherein the feedback signal includes a difference between a test result from the set of test results and a threshold of the design criterion.
4. The system of claim 1 , wherein the feedback signal includes a ratio between a test result from the set of test results and a threshold of the design criterion.
5. The system of claim 1 , wherein a provenance stamp is embedded within the register-transfer level data structure, wherein the provenance stamp includes metadata indicating circumstances of reception of a design data structure used to generate the register-transfer level data structure.
6. The system of claim 5 , wherein the provenance stamp includes at least one of a cryptographic signature, a hash, and a notarization.
7. The system of claim 1 , wherein a provenance stamp is embedded within the physical design data structure, wherein the provenance stamp includes metadata indicating circumstances of reception of a design data structure used to generate the physical design data structure.