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

[SWDEV-490187 / SWDEV-491215] Remove reset gpu partition + NPS test disabled

Browse Source 
The reset gpu partition support for both compute and memory were removed

Code changes related to the following:
  * rsmi_dev_compute_partition_reset()
  * rsmi_dev_memory_partition_reset()
  * CLI
  * Unit tests
  * Documentation

Change-Id: I3fb8570dbf9e755ae70369587ef44bbf64e17fe8
Signed-off-by: Oliveira, Daniel <daniel.oliveira@amd.com>
This commit is contained in:
Oliveira, Daniel
2024-10-08 20:23:09 -05:00
committed by Charis Poag
parent 0609cbf1d0
commit a1295714f2
8 changed files with 44 additions and 237 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/rocm_smi_test/functional/computepartition_read_write.cc
+18 -18
View File
@@ -428,7 +428,7 @@ void TestComputePartitionReadWrite::Run(void) {
* [0:SPX, 1:CPX, 2:CPX, 3:CPX, 4:CPX, 5:CPX, 6:SPX, 7:SPX] <- set 1 to CPX
* [0:SPX, 1:SPX, 2:SPX, 3:SPX] <- reset(1)
* ...
*
*
*/
std::string final_partition_state = "UNKNOWN";
@@ -564,29 +564,29 @@ void TestComputePartitionReadWrite::Run(void) {
<< "========" << std::endl;
}
std::string oldPartition = current_char_computePartition;
bool wasResetSuccess = false;
ret = rsmi_dev_compute_partition_reset(dv_ind);
IF_VERB(STANDARD) {
std::cout << "\t**"
<< "rsmi_dev_compute_partition_reset(" << dv_ind << "): "
<< amd::smi::getRSMIStatusString(ret, false) << "\n";
rsmi_compute_partition_type_t updatePartition =
static_cast<rsmi_compute_partition_type_t>(
mapStringToRSMIComputePartitionTypes.at(
std::string(orig_char_computePartition)));
ret = rsmi_dev_compute_partition_set(dv_ind, updatePartition);
ret = rsmi_dev_compute_partition_get(dv_ind, current_char_computePartition, 255);
if (strcmp(oldPartition.c_str(), current_char_computePartition) !=
0) {
devicePartitionUpdated = true;
final_partition_state = current_char_computePartition;
} else {
devicePartitionUpdated = false;
}
ASSERT_TRUE((ret == RSMI_STATUS_SUCCESS) ||
(ret == RSMI_STATUS_NOT_SUPPORTED) ||
(ret == RSMI_STATUS_BUSY));
if (ret == RSMI_STATUS_SUCCESS) {
wasResetSuccess = true;
}
ret = rsmi_dev_compute_partition_get(dv_ind, current_char_computePartition,
255);
CHK_ERR_ASRT(ret)
IF_VERB(STANDARD) {
std::cout << "\t**" << "Current compute partition: "
<< current_char_computePartition << "\n"
<< "\t**" << "Old Partition partition (before setting to original): "
<< oldPartition << "\n"
<< "\t**" << "Original compute partition: "
<< orig_char_computePartition << "\n"
<< "\t**" << "Reset Successful: "
<< (wasResetSuccess ? "TRUE" : "FALSE") << "\n"
<< "\t**" << "Partitions Updated: "
<< (devicePartitionUpdated ? "TRUE" : "FALSE") << "\n";
}
@@ -598,7 +598,7 @@ void TestComputePartitionReadWrite::Run(void) {
checkPartitionIdChanges(dv_ind, std::string(current_char_computePartition),
isVerbose, false);
}
if (wasResetSuccess && devicePartitionUpdated) {
if (devicePartitionUpdated) {
ASSERT_STRNE(oldPartition.c_str(), current_char_computePartition);
IF_VERB(STANDARD) {
std::cout << "\t**"
tests/rocm_smi_test/functional/memorypartition_read_write.cc
+4 -8
View File
@@ -111,6 +111,8 @@ mapStringToRSMIMemoryPartitionTypes {
};
void TestMemoryPartitionReadWrite::Run(void) {
GTEST_SKIP_("Temporarily disabled"); // Skipped due to SWDEV-491215 -
// will be re-enabled in rocm 6.4
rsmi_status_t ret, err;
char orig_memory_partition[255];
char current_memory_partition[255];
@@ -302,13 +304,7 @@ void TestMemoryPartitionReadWrite::Run(void) {
<< "SETTING ========" << std::endl;
}
std::string oldMode = current_memory_partition;
bool wasResetSuccess = false;
ret = rsmi_dev_memory_partition_reset(dv_ind);
ASSERT_TRUE((ret == RSMI_STATUS_SUCCESS) ||
(ret == RSMI_STATUS_NOT_SUPPORTED));
if (ret == RSMI_STATUS_SUCCESS) {
wasResetSuccess = true;
}
ret = rsmi_dev_memory_partition_get(dv_ind, current_memory_partition, 255);
CHK_ERR_ASRT(ret)
IF_VERB(STANDARD) {
@@ -316,7 +312,7 @@ void TestMemoryPartitionReadWrite::Run(void) {
<< "Current memory partition: " << current_memory_partition
<< std::endl;
}
if (wasResetSuccess && wasSetSuccess) {
if (wasSetSuccess) {
ASSERT_STRNE(oldMode.c_str(), current_memory_partition);
IF_VERB(STANDARD) {
std::cout << "\t**"