SWDEV-445664 - Aligned metric --ecc & --ecc-blocks with Host

Signed-off-by: Maisam Arif <maisarif@amd.com>
Change-Id: I93cf2bdab8c4c066bacf0e910e5620d37b362b07
This commit is contained in:
Maisam Arif
2024-03-26 03:33:19 -05:00
committed by Maisam Arif
parent 93b81e5012
commit e2e4349bd2
4 changed files with 56 additions and 24 deletions
+2
View File
@@ -967,6 +967,7 @@ Field | Description
---|---
`correctable_count` | Correctable ECC error count
`uncorrectable_count` | Uncorrectable ECC error count
`deferred_count` | Deferred ECC error count
Exceptions that can be thrown by `amdsmi_get_gpu_total_ecc_count` function:
@@ -2747,6 +2748,7 @@ Field | Description
---|---
`correctable_count` | Count of correctable errors
`uncorrectable_count` | Count of uncorrectable errors
`deferred_count` | Count of deferred errors
Exceptions that can be thrown by `amdsmi_get_gpu_ecc_count` function:
+6 -4
View File
@@ -1821,16 +1821,17 @@ def amdsmi_get_gpu_total_ecc_count(
processor_handle, amdsmi_wrapper.amdsmi_processor_handle
)
error_count = amdsmi_wrapper.amdsmi_error_count_t()
ec = amdsmi_wrapper.amdsmi_error_count_t()
_check_res(
amdsmi_wrapper.amdsmi_get_gpu_total_ecc_count(
processor_handle, ctypes.byref(error_count)
processor_handle, ctypes.byref(ec)
)
)
return {
"correctable_count": error_count.correctable_count,
"uncorrectable_count": error_count.uncorrectable_count,
"correctable_count": ec.correctable_count,
"uncorrectable_count": ec.uncorrectable_count,
"deferred_count": ec.deferred_count,
}
@@ -3655,6 +3656,7 @@ def amdsmi_get_gpu_ecc_count(
return {
"correctable_count": ec.correctable_count,
"uncorrectable_count": ec.uncorrectable_count,
"deferred_count": ec.deferred_count,
}