Added amd-smi partition as preliminary command.
new command includes following arguments:
- current - display the current partition information for the selected
gpu(s)
- memory - display memory partition information for the selected
gpu(s)
- accelerator - display accelerator partition information for the
selected gpu(s)
additional functionality will be added as more partition APIs are added.
Signed-off-by: gabrpham <Gabriel.Pham@amd.com>
Change-Id: Ica86160139002ef5213d6d4b0e390670aeef01c8
Šī revīzija ir iekļauta:
gabrpham
@@ -94,7 +94,8 @@ if __name__ == "__main__":
|
||||
amd_smi_commands.reset,
|
||||
amd_smi_commands.monitor,
|
||||
amd_smi_commands.rocm_smi,
|
||||
amd_smi_commands.xgmi)
|
||||
amd_smi_commands.xgmi,
|
||||
amd_smi_commands.partition)
|
||||
try:
|
||||
try:
|
||||
argcomplete.autocomplete(amd_smi_parser)
|
||||
@@ -128,7 +129,6 @@ if __name__ == "__main__":
|
||||
sys.tracebacklimit = 10
|
||||
else:
|
||||
sys.tracebacklimit = -1
|
||||
|
||||
# Execute subcommands
|
||||
args.func(args)
|
||||
except amdsmi_cli_exceptions.AmdSmiException as e:
|
||||
|
||||
@@ -5043,6 +5043,8 @@ class AMDSMICommands():
|
||||
bitrate = pcie_speed_GTs_value
|
||||
max_bandwidth = bitrate * pcie_static['max_pcie_width']
|
||||
except amdsmi_exception.AmdSmiLibraryException as e:
|
||||
bitrate = "N/A"
|
||||
max_bandwidth = "N/A"
|
||||
logging.debug("Failed to get bitrate and bandwidth for GPU %s | %s", src_gpu_id,
|
||||
e.get_error_info())
|
||||
|
||||
@@ -5084,6 +5086,8 @@ class AMDSMICommands():
|
||||
read = metrics_info['xgmi_read_data_acc'][dest_gpu_id]
|
||||
write = metrics_info['xgmi_write_data_acc'][dest_gpu_id]
|
||||
except amdsmi_exception.AmdSmiLibraryException as e:
|
||||
read = "N/A"
|
||||
write = "N/A"
|
||||
logging.debug("Failed to get read data for %s to %s | %s",
|
||||
self.helpers.get_gpu_id_from_device_handle(src_gpu),
|
||||
self.helpers.get_gpu_id_from_device_handle(dest_gpu),
|
||||
@@ -5172,6 +5176,207 @@ class AMDSMICommands():
|
||||
self.logger.print_output(multiple_device_enabled=True)
|
||||
|
||||
|
||||
def partition(self, args, multiple_devices=False, gpu=None, current=None, memory=None, accelerator=None):
|
||||
""" Display parition information for the target GPU
|
||||
param:
|
||||
args - argparser args to pass to subcommand
|
||||
multiple_devices (bool) - True if checking for multiple devices
|
||||
gpu (device_handle) - device_handle for target device
|
||||
current - boolean which dictates whether the current partition information is shown
|
||||
memory - boolean which dictates whether the memory partition information is shown
|
||||
accelerator - boolean which dictates whether the accelerator partition information is shown
|
||||
returns:
|
||||
nothing
|
||||
"""
|
||||
|
||||
if gpu:
|
||||
args.gpu = gpu
|
||||
if args.gpu == None:
|
||||
args.gpu = self.device_handles
|
||||
if not isinstance(args.gpu, list):
|
||||
args.gpu = [args.gpu]
|
||||
if current:
|
||||
args.current = current
|
||||
if memory:
|
||||
args.memory = memory
|
||||
if accelerator:
|
||||
args.accelerator = accelerator
|
||||
|
||||
# if no args are present, then everything should be displayed
|
||||
if not args.current and not args.memory and not args.accelerator:
|
||||
args.current = True
|
||||
args.memory = True
|
||||
args.accelerator = True
|
||||
|
||||
if args.current:
|
||||
self.logger.table_header = ''.rjust(7)
|
||||
current_header = "GPU_ID".ljust(13) + \
|
||||
"MEMORY".ljust(8) + \
|
||||
"ACCELERATOR_TYPE".ljust(18) + \
|
||||
"ACCELERATOR_PROFILE_INDEX".ljust(27) + \
|
||||
"PARTITION_ID".ljust(14)
|
||||
self.logger.table_header = current_header + self.logger.table_header.strip()
|
||||
|
||||
tabular_output = []
|
||||
for gpu in args.gpu:
|
||||
gpu_id = self.helpers.get_gpu_id_from_device_handle(gpu)
|
||||
try:
|
||||
partition_dict = amdsmi_interface.amdsmi_get_gpu_accelerator_partition_profile(gpu)
|
||||
profile_type = partition_dict['partition_profile']['profile_type']
|
||||
profile_index = partition_dict['partition_profile']['profile_index']
|
||||
partition_id = partition_dict['partition_id']
|
||||
except amdsmi_exception.AmdSmiLibraryException as e:
|
||||
profile_type = "N/A"
|
||||
profile_index = "N/A"
|
||||
partition_id = "N/A"
|
||||
logging.debug("Failed to get accelerator partition profile for GPU %s | %s", gpu_id, e.get_error_info())
|
||||
try:
|
||||
current_mem_cap = amdsmi_interface.amdsmi_get_gpu_memory_partition(gpu)
|
||||
except amdsmi_exception.AmdSmiLibraryException as e:
|
||||
current_mem_cap = "N/A"
|
||||
logging.debug("Failed to get current memory partition capabilties for GPU %s | %s", gpu_id, e.get_error_info())
|
||||
|
||||
tabular_output_dict = {"gpu_id": gpu_id,
|
||||
"memory": current_mem_cap,
|
||||
"accelerator_type": profile_type,
|
||||
"accelerator_profile_index": profile_index,
|
||||
"partition_id": partition_id}
|
||||
tabular_output.append(tabular_output_dict)
|
||||
|
||||
self.logger.multiple_device_output = tabular_output
|
||||
self.logger.table_title = "CURRENT_PARTITION"
|
||||
self.logger.print_output(multiple_device_enabled=True, tabular=True)
|
||||
self.logger.clear_multiple_devices_ouput()
|
||||
|
||||
if args.memory:
|
||||
for gpu in args.gpu:
|
||||
gpu_id = self.helpers.get_gpu_id_from_device_handle(gpu)
|
||||
try:
|
||||
memory_partition = amdsmi_interface.amdsmi_get_gpu_memory_partition(gpu) # this info likely actually comes from different apis than used here
|
||||
except amdsmi_exception.AmdSmiLibraryException as e:
|
||||
memory_partition = "N/A"
|
||||
logging.debug("Failed to get current memory partition for GPU %s | %s", gpu_id, e.get_error_info())
|
||||
try:
|
||||
partition_dict = amdsmi_interface.amdsmi_get_gpu_accelerator_partition_profile(gpu)
|
||||
temp_mem_caps = partition_dict['partition_profile']['memory_caps']
|
||||
|
||||
if temp_mem_caps.amdsmi_nps_flags_t == None:
|
||||
mem_caps = temp_mem_caps.nps_cap_mask
|
||||
mem_caps_list = []
|
||||
if mem_caps & 1 == 1:
|
||||
mem_caps_list.append("NPS1")
|
||||
if mem_caps & 2 == 2:
|
||||
mem_caps_list.append("NPS2")
|
||||
if mem_caps & 4 == 4:
|
||||
mem_caps_list.append("NPS4")
|
||||
if mem_caps & 8 == 8:
|
||||
mem_caps_list.append("NPS8")
|
||||
mem_caps_str = str(mem_caps_list).replace("]", "").replace("[", "")
|
||||
else:
|
||||
mem_caps = temp_mem_caps.amdsmi_nps_flags_t
|
||||
mem_caps_list = []
|
||||
if mem_caps.nps1_cap == 1:
|
||||
mem_caps_list.append("NPS1")
|
||||
if mem_caps.nps2_cap == 1:
|
||||
mem_caps_list.append("NPS2")
|
||||
if mem_caps.nps4_cap == 1:
|
||||
mem_caps_list.append("NPS4")
|
||||
if mem_caps.nps8_cap == 1:
|
||||
mem_caps_list.append("NPS8")
|
||||
mem_caps_str = str(mem_caps_list).replace("]", "").replace("[", "")
|
||||
if mem_caps_str == "":
|
||||
mem_caps_str = "N/A"
|
||||
except amdsmi_exception.AmdSmiLibraryException as e:
|
||||
mem_caps_str = "N/A"
|
||||
logging.debug("Failed to get accelerator partition profile for GPU %s | %s", gpu_id, e.get_error_info())
|
||||
|
||||
memory_dict = {'caps': mem_caps_str, 'current': memory_partition}
|
||||
self.logger.store_output(gpu, 'memory_partition', memory_dict)
|
||||
self.logger.store_multiple_device_output()
|
||||
self.logger.print_output(multiple_device_enabled=True)
|
||||
self.logger.clear_multiple_devices_ouput()
|
||||
if args.accelerator:
|
||||
self.logger.table_header = ''.rjust(7)
|
||||
current_header = "GPU_ID".ljust(13) + \
|
||||
"PROFILE_INDEX".ljust(15) + \
|
||||
"MEMORY_PARTITION_CAPS".ljust(23) + \
|
||||
"ACCELERATOR_TYPE".ljust(18) + \
|
||||
"PARTITION_ID".ljust(14) + \
|
||||
"NUM_PARTITIONS".ljust(16) + \
|
||||
"NUM_RESOURCES".ljust(15) + \
|
||||
"RESOURCE_INDEX".ljust(16) + \
|
||||
"RESOURCE_TYPE".ljust(15) + \
|
||||
"RESOURCE_INSTANCES".ljust(20) + \
|
||||
"RESOURCES_SHARED".ljust(18)
|
||||
self.logger.table_header = current_header + self.logger.table_header.strip()
|
||||
|
||||
tabular_output = []
|
||||
for gpu in args.gpu:
|
||||
gpu_id = self.helpers.get_gpu_id_from_device_handle(gpu)
|
||||
try:
|
||||
partition_dict = amdsmi_interface.amdsmi_get_gpu_accelerator_partition_profile(gpu)
|
||||
profile_type = partition_dict['partition_profile']['profile_type']
|
||||
profile_index = partition_dict['partition_profile']['profile_index']
|
||||
temp_mem_caps = partition_dict['partition_profile']['memory_caps']
|
||||
parition_id = partition_dict['partition_id']
|
||||
num_resources = partition_dict['partition_profile']['num_resources']
|
||||
resources = partition_dict['partition_profile']['resources']
|
||||
|
||||
if temp_mem_caps.amdsmi_nps_flags_t == None:
|
||||
mem_caps = temp_mem_caps.nps_cap_mask
|
||||
mem_caps_list = []
|
||||
if mem_caps & 1 == 1:
|
||||
mem_caps_list.append("NPS1")
|
||||
if mem_caps & 2 == 2:
|
||||
mem_caps_list.append("NPS2")
|
||||
if mem_caps & 4 == 4:
|
||||
mem_caps_list.append("NPS4")
|
||||
if mem_caps & 8 == 8:
|
||||
mem_caps_list.append("NPS8")
|
||||
mem_caps_str = str(mem_caps_list).replace("]", "").replace("[", "")
|
||||
else:
|
||||
mem_caps = temp_mem_caps.amdsmi_nps_flags_t
|
||||
mem_caps_list = []
|
||||
if mem_caps.nps1_cap == 1:
|
||||
mem_caps_list.append("NPS1")
|
||||
if mem_caps.nps2_cap == 1:
|
||||
mem_caps_list.append("NPS2")
|
||||
if mem_caps.nps4_cap == 1:
|
||||
mem_caps_list.append("NPS4")
|
||||
if mem_caps.nps8_cap == 1:
|
||||
mem_caps_list.append("NPS8")
|
||||
mem_caps_str = str(mem_caps_list).replace("]", "").replace("[", "")
|
||||
if mem_caps_str == "":
|
||||
mem_caps_str = "N/A"
|
||||
except amdsmi_exception.AmdSmiLibraryException as e:
|
||||
profile_type = "N/A"
|
||||
profile_index = "N/A"
|
||||
temp_mem_caps = "N/A"
|
||||
parition_id = "N/A"
|
||||
num_resources = "N/A"
|
||||
resources = "N/A"
|
||||
mem_caps_str = "N/A"
|
||||
logging.debug("Failed to get accelerator partition profile for GPU %s | %s", gpu_id, e.get_error_info())
|
||||
|
||||
tabular_output_dict = {"gpu_id": gpu_id,
|
||||
"profile_index": profile_index,
|
||||
"memory_partition_caps": mem_caps_str,
|
||||
"accelerator_type": profile_type,
|
||||
"partition_id": parition_id,
|
||||
"num_partitions": 0,
|
||||
"num_resources": num_resources,
|
||||
"resource_index": resources,
|
||||
"resource_type": resources,
|
||||
"resource_instances": resources,
|
||||
"resources_shared": resources}
|
||||
tabular_output.append(tabular_output_dict)
|
||||
|
||||
self.logger.multiple_device_output = tabular_output
|
||||
self.logger.table_title = "ACCELERATOR_PARTITION_PROFILES"
|
||||
self.logger.print_output(multiple_device_enabled=True, tabular=True)
|
||||
self.logger.clear_multiple_devices_ouput()
|
||||
|
||||
|
||||
def _event_thread(self, commands, i):
|
||||
devices = commands.device_handles
|
||||
if len(devices) == 0:
|
||||
|
||||
@@ -150,8 +150,32 @@ class AMDSMILogger():
|
||||
table_values += string_value.ljust(14)
|
||||
elif key == "link_type":
|
||||
table_values += string_value.ljust(10)
|
||||
elif key == "memory":
|
||||
table_values += string_value.ljust(8)
|
||||
elif key == "accelerator_type":
|
||||
table_values += string_value.ljust(18)
|
||||
elif key == "partition_id":
|
||||
table_values += string_value.ljust(14)
|
||||
elif key == "accelerator_profile_index":
|
||||
table_values += string_value.ljust(27)
|
||||
elif key == "profile_index":
|
||||
table_values += string_value.ljust(15)
|
||||
elif key == "memory_partition_caps":
|
||||
table_values += string_value.ljust(23)
|
||||
elif key == "num_partitions":
|
||||
table_values += string_value.ljust(16)
|
||||
elif key == "num_resources":
|
||||
table_values += string_value.ljust(15)
|
||||
elif key == "resource_index":
|
||||
table_values += string_value.ljust(16)
|
||||
elif key == "resource_type":
|
||||
table_values += string_value.ljust(15)
|
||||
elif key == "resource_instances":
|
||||
table_values += string_value.ljust(20)
|
||||
elif key == "resources_shared":
|
||||
table_values += string_value.ljust(18)
|
||||
elif key == "RW":
|
||||
table_values += " " + string_value.ljust(52)
|
||||
table_values += string_value.ljust(52)
|
||||
elif key == "process_list":
|
||||
#Add an additional padding between the first instance of GPU and NAME
|
||||
table_values += ' '
|
||||
|
||||
@@ -71,7 +71,7 @@ class AMDSMIParser(argparse.ArgumentParser):
|
||||
"""
|
||||
def __init__(self, version, list, static, firmware, bad_pages, metric,
|
||||
process, profile, event, topology, set_value, reset, monitor,
|
||||
rocmsmi, xgmi):
|
||||
rocmsmi, xgmi, partition):
|
||||
|
||||
# Helper variables
|
||||
self.helpers = AMDSMIHelpers()
|
||||
@@ -117,7 +117,7 @@ class AMDSMIParser(argparse.ArgumentParser):
|
||||
# Store possible subcommands & aliases for later errors
|
||||
self.possible_commands = ['version', 'list', 'static', 'firmware', 'ucode', 'bad-pages',
|
||||
'metric', 'process', 'profile', 'event', 'topology', 'set',
|
||||
'reset', 'monitor', 'dmon', 'xgmi']
|
||||
'reset', 'monitor', 'dmon', 'xgmi', 'partition']
|
||||
|
||||
# Add all subparsers
|
||||
self._add_version_parser(self.subparsers, version)
|
||||
@@ -135,6 +135,7 @@ class AMDSMIParser(argparse.ArgumentParser):
|
||||
self._add_monitor_parser(self.subparsers, monitor)
|
||||
self._add_rocm_smi_parser(self.subparsers, rocmsmi)
|
||||
self._add_xgmi_parser(self.subparsers, xgmi)
|
||||
self._add_partition_parser(self.subparsers, partition)
|
||||
|
||||
|
||||
def _not_negative_int(self, int_value):
|
||||
@@ -1286,6 +1287,40 @@ class AMDSMIParser(argparse.ArgumentParser):
|
||||
xgmi_parser.add_argument('-m', '--metric', action='store_true', required=False, help=metrics_help)
|
||||
|
||||
|
||||
def _add_partition_parser(self, subparsers, func):
|
||||
if not self.helpers.is_amdgpu_initialized():
|
||||
# The partition subcommand is only applicable to systems with amdgpu initialized
|
||||
return
|
||||
|
||||
# Subparser help text
|
||||
partition_help = "Displays partition information of the devices"
|
||||
partition_subcommand_help = "If no GPU is specified, returns information for all GPUs on the system.\
|
||||
\nIf no partition argument is provided all partition information will be displayed."
|
||||
partition_optionals_title = "partition arguments"
|
||||
|
||||
# Options help text
|
||||
current_help = "display the current partition information"
|
||||
memory_help = "display the current memory partition mode and capabilities"
|
||||
accelerator_help = "display accelerator partition information"
|
||||
|
||||
# Create partition subparser
|
||||
partition_parser = subparsers.add_parser('partition', help=partition_help, description=partition_subcommand_help)
|
||||
partition_parser._optionals.title = partition_optionals_title
|
||||
partition_parser.formatter_class=lambda prog: AMDSMISubparserHelpFormatter(prog)
|
||||
partition_parser.set_defaults(func=func)
|
||||
|
||||
# Add Universal Arguments
|
||||
self._add_device_arguments(partition_parser, required=False)
|
||||
|
||||
# Handle GPU Options
|
||||
partition_parser.add_argument('-c', '--current', action='store_true', required=False, help=current_help)
|
||||
partition_parser.add_argument('-m', '--memory', action='store_true', required=False, help=memory_help)
|
||||
partition_parser.add_argument('-a', '--accelerator', action='store_true', required=False, help=accelerator_help)
|
||||
|
||||
# Add command modifiers to the bottom
|
||||
self._add_command_modifiers(partition_parser)
|
||||
|
||||
|
||||
def error(self, message):
|
||||
outputformat = self.helpers.get_output_format()
|
||||
|
||||
|
||||
Atsaukties uz šo jaunā problēmā
Block a user