Shared resource analysis for embedded multi-core systems
Various embodiments discussed herein systems and methods that facilitate analysis of shared resources for a multi-core system. One example embodiment comprise a method involving identifying, via static data based on analysis of the multi-core system, shared resource(s) of the multi-core system that are subject to potential resource violation(s), wherein the static data identifies each read and write access of those shared resource(s) in a software of the multi-core system; receiving hardware trace data for the multi-core system comprising each read and write access of those shared resource(s) in the software as executed by the multi-core system; and making a determination, for each shared resource of the one or more shared resources, based on a comparison between the static data and the hardware trace data, whether at least one of the one or more associated potential resource violations of that shared resource is an associated resource violation of that shared resource.
1. A computer-readable medium comprising instructions that, when executed, cause a computer to:
identify, via static data, one or more shared resources of a multi-core system, wherein each of the one or more shared resources is subject to one or more associated potential resource violations, wherein the static data is based on an analysis of the multi-core system, wherein the static data comprises semi-formal notation that indicates, for each shared resource of the one or more shared resources, each read access of that shared resource in a software of the multi-core system and each write access of that shared resource in the software of the multi-core system, and wherein each of the shared resources has two or more write accesses in the software;
receive hardware trace data for the multi-core system that comprises, for each shared resource of the one or more shared resources, each read access of that shared resource in the software as executed by the multi-core system and each write access of that shared resource in the software as executed by the multi-core system; and
make a determination, for each shared resource of the one or more shared resources, based on a comparison between the static data and the hardware trace data, whether at least one of the one or more associated potential resource violations of that shared resource is an associated resource violation of that shared resource.
2. The computer-readable medium of claim 1 , wherein, for each shared resource of the one or more shared resources, the static data comprises one or more proposed mitigation measures for the one or more associated potential resource violations of that shared resource.
3. The computer-readable medium of claim 1 , wherein the instructions, when executed, further cause the computer to, for each shared resource of the one or more shared resources, generate a user notification in response to a determination that at least one of the one or more associated potential resource violations of that shared resource is the associated resource violation of that shared resource.
4. The computer-readable medium of claim 3 , wherein the user notification is generated via one of a safety management unit (SMU) alarm, an interrupt, or a trap.
5. The computer-readable medium of claim 1 , wherein the instructions, when executed, cause the computer to perform the comparison in response to one or more on-demand checks.
6. The computer-readable medium of claim 1 , wherein the instructions, when executed, cause the computer to continuously perform the comparison via continuous monitoring of the static data and hardware trace data.
7. The computer-readable medium of claim 1 , wherein the instructions, when executed, cause the computer to perform the comparison via periodic monitoring of the static data and hardware trace data according to a monitoring frequency.
8. A system, comprising:
processing circuitry comprising a resource violation checker configured to identify, via static data, one or more shared resources of a multi-core system, wherein each of the one or more shared resources is subject to one or more associated potential resource violations, wherein the static data is based on an analysis of the multi-core system, wherein the static data comprises semi-formal notation that indicates, for each shared resource of the one or more shared resources, each read access of that shared resource in a software of the multi-core system and each write access of that shared resource in the software of the multi-core system, and wherein each of the shared resources has two or more write accesses in the software; and
a user buffer circuit configured to receive hardware trace data for the multi-core system and to send the hardware trace data to the resource violation checker, wherein the hardware trace data comprises, for each shared resource of the one or more shared resources, each read access of that shared resource in the software as executed by the multi-core system and each write access of that shared resource in the software as executed by the multi-core system,
wherein the processing circuitry comprising the resource violation checker is further configured to make a determination, for each shared resource of the one or more shared resources, based on a comparison between the static data and the hardware trace data, whether at least one of the one or more associated potential resource violations of that shared resource is an associated resource violation of that shared resource.
9. The system of claim 8 , wherein, for each shared resource of the one or more shared resources, the static data comprises one or more proposed mitigation measures for the one or more associated potential resource violations of that shared resource.
10. The system of claim 8 , wherein the processing circuitry comprising the resource violation checker is further configured to, for each shared resource of the one or more shared resources, generate a user notification in response to a determination that at least one of the one or more associated potential resource violations of that shared resource is the associated resource violation of that shared resource.
11. The system of claim 10 , wherein the user notification is generated via one of a safety management unit (SMU) alarm, an interrupt, or a trap.
12. The system of claim 8 , wherein the processing circuitry comprising the resource violation checker is configured to perform the comparison in response to one or more on-demand checks.
13. The system of claim 8 , wherein the processing circuitry comprising the resource violation checker is configured to continuously perform the comparison via continuous monitoring of the static data and hardware trace data.
14. The system of claim 8 , wherein the processing circuitry comprising the resource violation checker is configured to perform the comparison via periodic monitoring of the static data and hardware trace data according to a monitoring frequency.
15. A method, comprising:
identifying, via static data, one or more shared resources of a multi-core system, wherein each of the one or more shared resources is subject to one or more associated potential resource violations, wherein the static data is based on an analysis of the multi-core system, wherein the static data comprises semi-formal notation that indicates, for each shared resource of the one or more shared resources, each read access of that shared resource in a software of the multi-core system and each write access of that shared resource in the software of the multi-core system, and wherein each of the shared resources has two or more write accesses in the software;
receiving hardware trace data for the multi-core system that comprises, for each shared resource of the one or more shared resources, each read access of that shared resource in the software as executed by the multi-core system and each write access of that shared resource in the software as executed by the multi-core system; and
making a determination, for each shared resource of the one or more shared resources, based on a comparison between the static data and the hardware trace data, whether at least one of the one or more associated potential resource violations of that shared resource is an associated resource violation of that shared resource.
16. The method of claim 15 , further comprising generating a user notification in response to a determination that at least one of the one or more associated potential resource violations of that shared resource is the associated resource violation of that shared resource.