Consider a typical Linux mcelog entry for exception type 0x12:
References: Intel SDM Vol. 3 (Chapter 15 – Machine-Check Architecture), AMD APM Vol. 2 (Section 8.2 – Machine Check Exception), Linux kernel documentation on MCA (Documentation/x86/x86_64/machinecheck.rst). x64 exception type 0x12 machinecheck exception link
Older CPUs (pre-Nehalem) or ARM64 systems do not expose link details. Ensure you are using mcelog --ascii or rasdaemon on Linux and that your kernel has CONFIG_X86_MCE enabled. Consider a typical Linux mcelog entry for exception
The triggers for a Machine Check Exception are distinct from software errors. While a typical "Blue Screen of Death" (BSOD) might be caused by a corrupt driver or a memory leak, an MCE is almost exclusively rooted in physics and electronics. Common causes include thermal stress, where the CPU overheats and fails to execute instructions correctly; voltage irregularities from the power supply unit (PSU); or physical degradation of the silicon. It can also be triggered by errors in the cache memory (L1, L2, or L3) integrated into the processor. For instance, if the CPU performs an internal parity check on its cache and finds a discrepancy that it cannot correct via Error Correcting Code (ECC), it will assert the MCE to prevent data corruption from propagating to the software layer. Older CPUs (pre-Nehalem) or ARM64 systems do not