AI/rocm-systems
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

[RDC] [SWDEV-551280] RDC to include Error Counters (#1087)

Browse Source 
* rdc error counter

* RDC error counters

* fix

* Updates

* updated field names

Signed-off-by: yalmusaf_amdeng <yalmusaf@amd.com>

---------

Signed-off-by: yalmusaf_amdeng <yalmusaf@amd.com>
Co-authored-by: yalmusaf_amdeng <yalmusaf@amd.com>
This commit is contained in:
Yazen AL Musaffar
2025-12-03 15:22:18 -06:00
committed by GitHub
parent c9d6a8720c
commit 16b9160034
8 changed files with 95 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
projects/rdc/include/rdc_lib/impl/RdcCacheManagerImpl.h
+3
View File
@@ -71,6 +71,9 @@ struct GpuSummaryStats {
uint64_t energy_last_time;
uint64_t ecc_correct_init; // Init counter when job starts
uint64_t ecc_uncorrect_init; // Init counter when job starts
uint32_t pcie_lc_perf_other_end_recovery_count_init; // Init counter when job starts
uint32_t pcie_nak_sent_count_acc_init; // Init counter when job starts
uint32_t pcie_nak_rcvd_count_acc_init; // Init counter when job starts
std::map<uint32_t, FieldSummaryStats> field_summaries;
};