NVIDIA HGX H100 SXM5 Diagnostics
Classification: Datacenter Accelerators & High Performance Computing Equipment
Hardware operational fault codes, protection alarms, LED blink sequences, and step-by-step diagnostic fixes for the NVIDIA HGX H100 SXM5.
Indexed Fault Codes for HGX H100 SXM5
Step-by-step resolution manuals and root cause matrices
H100 SXM5 XID 31 Fatal Memory Error
An uncorrectable multi-bit ECC error occurred in the High Bandwidth Memory (HBM3) stack, triggering NVIDIA driver event XID 31. The GPU driver attempted dynamic memory page retirement to isolate the failing physical address, but the retirement sequence failed or the bad page table exhausted its capacity, causing the GPU to fall off the bus and trigger a fatal kernel freeze.
GPU Fallen Off The Bus
NVRM Xid 79 indicates an unrecoverable PCIe communication loss between host/PCIe switch and the H100 SXM5 GPU module. Root-cause mechanisms include physical baseboard socket unseating, PCIe Advanced Error Reporting (AER) fatal receiver/replay timeouts, transient 12V/48V rail power sag, or thermal throttle lockout.
NVLink Uncorrectable Error SXid 63
NVIDIA driver SXid 63 reports an uncorrectable fatal error on the NVLink interconnect fabric. A port on the H100 SXM5 GPU or interconnected NVSwitch encountered physical layer packet degradation, link integrity breakdown, or bad cyclic redundancy checks (CRC) exceeding recovery thresholds.