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

[SWDEV-538786] Fix ecc counts returning file error (#494)

Browse Source 
Change-Id: I5cea584289df95e89b6151d549bf69e4c3e50d22

Signed-off-by: Maisam Arif <Maisam.Arif@amd.com>
This commit is contained in:
Arif, Maisam
2025-06-19 15:24:03 -05:00
committed by GitHub
parent 470c62f887
commit 967e879861
2 changed files with 9 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
rocm_smi/src/rocm_smi.cc
+7
View File
@@ -763,6 +763,13 @@ rsmi_dev_ecc_count_get(uint32_t dv_ind, rsmi_gpu_block_t block,
if (val_vec.size() < 2 ) ret = RSMI_STATUS_FILE_ERROR;
if (ret != RSMI_STATUS_SUCCESS) {
if (ret == RSMI_STATUS_FILE_ERROR) {
ss << __PRETTY_FUNCTION__ << " | ======= end ======="
<< ", GetDevValueVec() ret was RSMI_STATUS_FILE_ERROR "
<< "-> reporting RSMI_STATUS_NOT_SUPPORTED";
LOG_ERROR(ss);
return RSMI_STATUS_NOT_SUPPORTED;
}
ss << __PRETTY_FUNCTION__ << " | ======= end ======="
<< ", GetDevValueVec() ret was not RSMI_STATUS_SUCCESS"
<< " -> reporting " << amd::smi::getRSMIStatusString(ret);
tests/amd_smi_test/functional/err_cnt_read.cc
+2 -3
View File
@@ -120,7 +120,7 @@ void TestErrCntRead::Run(void) {
err = amdsmi_get_gpu_ecc_count(processor_handles_[i], static_cast<amdsmi_gpu_block_t>(b), &ec);
if (err == AMDSMI_STATUS_NOT_SUPPORTED || err == AMDSMI_STATUS_FILE_ERROR) {
if (err == AMDSMI_STATUS_NOT_SUPPORTED) {
IF_VERB(STANDARD) {
std::cout << "\t**Error Count for " <<
GetBlockNameStr(static_cast<amdsmi_gpu_block_t>(b)) <<
@@ -129,8 +129,7 @@ void TestErrCntRead::Run(void) {
// Verify api support checking functionality is working
err = amdsmi_get_gpu_ecc_count(processor_handles_[i], static_cast<amdsmi_gpu_block_t>(b),
nullptr);
ASSERT_TRUE(err == AMDSMI_STATUS_NOT_SUPPORTED
|| err == AMDSMI_STATUS_FILE_ERROR);
ASSERT_TRUE(err == AMDSMI_STATUS_NOT_SUPPORTED);
} else {
CHK_ERR_ASRT(err)