Uh-oh - the dreaded WHEA 124 STOP error:
Code:
Proc. Info 0 @ fffffa8008a3b240
===============================================================================
Section 2 : x86/x64 MCA
-------------------------------------------------------------------------------
Descriptor @ fffffa8008a3b138
Section @ fffffa8008a3b2c0
Offset : 664
Length : 264
Flags : 0x00000000
Severity : Fatal
Error : DCACHEL1_WR_ERR (Proc 3 Bank 1)
Status : 0xb200000000000125
3: kd> !cpuinfo
CP F/M/S Manufacturer MHz PRCB Signature MSR 8B Signature Features
3 6,23,6 GenuineIntel 4025 0000060b00000000 011b3ffe
Cached Update Signature 0000060c00000000
Initial Update Signature 0000060b00000000
3: kd> !sysinfo cpuinfo
[CPU Information]
~MHz = REG_DWORD 4025
Component Information = REG_BINARY 0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0
Configuration Data = REG_FULL_RESOURCE_DESCRIPTOR ff,ff,ff,ff,ff,ff,ff,ff,0,0,0,0,0,0,0,0
Identifier = REG_SZ Intel64 Family 6 Model 23 Stepping 6
ProcessorNameString = REG_SZ Intel(R) Core(TM)2 Extreme CPU X9650 @ 3.00GHz
Update Signature = REG_BINARY 0,0,0,0,c,6,0,0
Update Status = REG_DWORD 0
VendorIdentifier = REG_SZ GenuineIntel
MSR8B = REG_QWORD 60c00000000
Processor may be overclocked!
Expected Frequency: 3000
Actual Frequency: 4025
Overclock Ratio: 1.34
There was one NTFS error, but it was inconclusive (could have been a hardware error as well), but the rest are all STOP 0x124 WHEA hardware errors. Specifically, all of them point to either L1 cache write or evict errors on CPU core 3, or bus errors on CPU core 2. Given your CPU is overclocked, the overclock itself could be causing this (that's a pretty large overclock), the CPU could really actually be damaged, or you're having cache miss events where the write back to main memory is failing (although this is the least likely of the 3 options). Since testing RAM is easy, I'd still start with that (to rule that out if possible), and after that you're looking at putting your CPU back to it's stock or underclocking it to see if it still fails, and if so, replacing it.
As I mentioned previously, I'm not as worried as the others about the HDD because the call to NtfsCommonCleanupOnNewStack would cause a filter driver lookup, which would cause an IRP, which would cause a DPC, which would hit the CPU - given there's only one (and all the rest are basically the same CPU failure), I'm fairly convinced the oddball NTFS failure dump is actually a CPU issue as well. I can't prove it without at least a kernel dump, of course, but empirical evidence is overwhelmingly bad for your CPU.
Quote