Allocating machine check architecture banks
In accordance with embodiments disclosed herein, there is provided systems and methods for allocating machine check architecture banks. The processing device includes a plurality of machine check architecture banks to communicate a machine check error. The processing also includes an allocator to allocate during runtime of the processor a target machine check architecture bank of the plurality of machine check architecture banks. The runtime of the processor is during an occurrence of the machine check error.
1. A processor comprising:
a plurality of machine check architecture banks to communicate a machine check error; and
an allocator to select, based on availability of the plurality of machine check architecture banks, during runtime of the processor, a target machine check architecture bank of the plurality of machine check architecture banks to allocate to the machine check error.
2. The processor of claim 1 wherein the runtime of the processor is during an occurrence of the machine check error.
3. The processor of claim 1 wherein the target machine check architecture bank is not statically allocated to the machine check error.
4. The processor of claim 1 wherein the allocator to select, based on a type of the machine check error, the target machine check architecture bank among the plurality of machine check architecture banks to allocate to the machine check error.
5. The processor of claim 1 wherein the plurality of machine check architecture banks comprise multiple registers to detect, process and report the machine check error.
6. The processor of claim 1 wherein the machine check error comprises an uncorrectable error (UE).
7. The processor of claim 1 wherein the machine check error comprises a correctable error (CE) without an associated threshold.
8. A system comprising:
a memory; and
a processing device communicably coupled to the memory, wherein the processing device comprises:
a plurality of machine check architecture banks to communicate a machine check error; and
an allocator to select, based on availability of the plurality of machine check architecture banks, during runtime of the processing device, a target machine check architecture bank of the plurality of machine check architecture banks to allocate to the machine check error.
9. The system of claim 8 wherein the runtime of the processor is during an occurrence of the machine check error.
10. A method comprising:
receiving a machine check error communicated by a plurality of machine check architecture banks; and
selecting, based on availability of the plurality of machine check architecture banks, during runtime of a processor, a target machine check architecture bank of the plurality of machine check architecture banks to allocate to the machine check error.
11. The method of claim 10 wherein the runtime of the processor is during an occurrence of the machine check error.
12. The method of claim 10 wherein the target machine check architecture bank is not statically allocated to the machine check error.
13. The method of claim 10 further comprising selecting, based on a type of the machine check error, the target machine check architecture bank among the plurality of machine check architecture banks to allocate to the machine check error.
14. The method of claim 10 wherein the plurality of machine check architecture banks comprises multiple registers to communicate to system software for detection, processing and reporting the machine check error.
15. The method of claim 10 wherein the machine check error comprise an uncorrectable error (UE).
16. The method of claim 10 wherein the machine check error comprise a correctable error (CE) without an associated threshold.
17. A non-transitory machine-readable storage medium including data that, when accessed by a processing device, cause the processing device to perform operations comprising:
receiving a machine check error communicated by a plurality of machine check architecture banks; and
selecting, based on availability of the plurality of machine check architecture banks, during runtime of the processing device, a target machine check architecture bank of the plurality of machine check architecture banks to allocate to the machine check error.
18. The non-transitory machine-readable storage medium of claim 17 wherein the runtime of the processor is during an occurrence of the machine check error.
19. The non-transitory machine-readable storage medium of claim 17 , wherein the target machine check architecture bank is not statically allocated to the machine check error.
20. The non-transitory machine-readable storage medium of claim 17 , wherein the operations further comprising selecting, based on a type of the machine check error, the target machine check architecture bank among the plurality of machine check architecture banks to allocate to the machine check error.