[SWDEV-422195/SWDEV-440985] GPU metrics 1.6

Changes:
    - Added new GPU metrics:
      1) Violation status' (ex. PVIOL/TVIOL) accumulators
      2) XCP (Graphics Compute Partitions) statistics
      3) pcie other end recovery counter
    - CLI/API/tests changes were made accordingly

Change-Id: I589b9b1f570f25dda12d95bb501feca85da8b3bb
Signed-off-by: Charis Poag <Charis.Poag@amd.com>
This commit is contained in:
Charis Poag
2024-05-21 20:30:16 -05:00
szülő 7a557b1c50
commit 3a4abbd8c0
23 fájl változott, egészen pontosan 3260 új sor hozzáadva és 942 régi sor törölve
+4 -2
Fájl megtekintése
@@ -61,7 +61,7 @@
const char *err_str; \
std::cout << "AMDSMI call returned " << RET << " at line " \
<< __LINE__ << std::endl; \
amdsmi_status_code_to_string(RET, &err_str); \
amdsmi_status_code_to_string(RET, &err_str); \
std::cout << err_str << std::endl; \
return RET; \
} \
@@ -262,8 +262,10 @@ int main() {
char bad_page_status_names[3][15] = {"RESERVED", "PENDING",
"UNRESERVABLE"};
uint32_t num_pages = 0;
std::vector<amdsmi_retired_page_record_t> bad_page_info(num_pages);
ret = amdsmi_get_gpu_bad_page_info(processor_handles[j], &num_pages,
nullptr);
bad_page_info.data());
std::cout << "num_pages = " << num_pages << "\n";
CHK_AMDSMI_RET(ret)
printf(" Output of amdsmi_get_gpu_bad_page_info:\n");
if (!num_pages) {