[SWDEV-513855] Add power cap to power monitor (#193)

Added power cap to display on amd-smi monitor -p.
Updated help and Changelog as well.

Signed-off-by: Kanangot Balakrishnan, Bindhiya <Bindhiya.KanangotBalakrishnan@amd.com>

CHANGELOG.md

@@ -20,6 +20,17 @@ Full documentation for amd_smi_lib is available at [https://rocm.docs.amd.com/pr
 
 ### Changed
 
+- **Added Power Cap to amd-smi monitor**.  
+  - 'amd-smi monitor -p' will display the power cap along with power.
+    ```shell
+    $ amd-smi monitor -p
+    GPU  POWER  PWR_CAP
+      0  148 W    750 W
+      1  156 W    750 W
+      2  153 W    750 W
+      ...
+    ```
+
 - **Modified VRAM display for `amd-smi monitor -v`**.  
   - Added free VRAM and VRAM percentage.
 

amdsmi_cli/amdsmi_commands.py

@@ -5104,6 +5104,24 @@ class AMDSMICommands():
 
             self.logger.table_header += 'POWER'.rjust(7)
 
+        if args.power_usage and not args.default_output:
+            # Get Max Power Cap
+            try:
+                power_cap_info = amdsmi_interface.amdsmi_get_power_cap_info(args.gpu)
+                monitor_values['max_power'] = power_cap_info['max_power_cap']
+                monitor_values['max_power'] = self.helpers.convert_SI_unit(monitor_values['max_power'], AMDSMIHelpers.SI_Unit.MICRO)
+
+                if self.logger.is_human_readable_format() and monitor_values['max_power'] != "N/A":
+                    monitor_values['max_power'] = f"{monitor_values['max_power']} {power_unit}"
+                if self.logger.is_json_format() and monitor_values['max_power'] != "N/A":
+                    monitor_values['max_power'] = {"value" : monitor_values['max_power'],
+                                                     "unit" : power_unit}
+            except amdsmi_exception.AmdSmiLibraryException as e:
+                monitor_values['max_power'] = "N/A"
+                logging.debug("Failed to get power cap info for gpu %s | %s", gpu_id, e.get_error_info())
+
+            self.logger.table_header += 'PWR_CAP'.rjust(9)
+
         if args.temperature:
             try:
                 temperature = amdsmi_interface.amdsmi_get_gpu_metrics_info(args.gpu)['temperature_hotspot']

amdsmi_cli/amdsmi_logger.py

@@ -128,6 +128,8 @@ class AMDSMILogger():
                 table_values += string_value.rjust(10) + '  '
             elif key == 'power_usage':
                 table_values += string_value.rjust(7)
+            elif key == 'max_power':
+                table_values += string_value.rjust(9)
             elif key in ('hotspot_temperature', 'memory_temperature'):
                 table_values += string_value.rjust(8)
             elif key in ('gfx', 'mem'):

amdsmi_cli/amdsmi_parser.py

@@ -1252,7 +1252,7 @@ class AMDSMIParser(argparse.ArgumentParser):
         monitor_optionals_title = "Monitor Arguments"
 
         # Help text for Arguments only on Guest and BM platforms
-        power_usage_help = "Monitor power usage in Watts"
+        power_usage_help = "Monitor power usage and power cap in Watts"
         temperature_help = "Monitor temperature in Celsius"
         gfx_util_help = "Monitor graphics utilization (%%) and clock (MHz)"
         mem_util_help = "Monitor memory utilization (%%) and clock (MHz)"