Merge amd-dev into amd-master 20240502

Signed-off-by: Maisam Arif <maisarif@amd.com> Change-Id: I9d8d0cd0f4ffe39605d087dd52a7768fc15db49d
2024-05-02 16:40:26 -05:00
parent 881920c864 bf6fc51f4f
commit f8c19dce67
@@ -4,14 +4,54 @@ Full documentation for amd_smi_lib is available at [https://rocm.docs.amd.com/](
 ***All information listed below is for reference and subject to change.***
-## amd_smi_lib for ROCm 6.1.1
+## amd_smi_lib for ROCm 6.1.2
 ### Added
- N/A
+- **Added process isolation and clean shader APIs and CLI commands**  
 Added APIs CLI and APIs to address LeftoverLocals security issues. Allowing clearing the sram data and setting process isolation on a per GPU basis. New APIs:
  - `amdsmi_get_gpu_process_isolation()`
  - `amdsmi_set_gpu_process_isolation()`
  - `amdsmi_set_gpu_clear_sram_data()`
 - **Added `MIN_POWER` to output of `amd-smi static --limit`**  
 This change was to help users to identify what range they can change the power cap of the GPU to. We added this to simplify why a device supports (or does not support) power capping (also known as overdrive). See `amd-smi set -g all --power-cap <value in W>` or `amd-smi reset -g all --power-cap`.
 ```shell
 $ amd-smi static --limit 
 GPU: 0
    LIMIT:
        MAX_POWER: 203 W
        MIN_POWER: 0 W
        SOCKET_POWER: 203 W
        SLOWDOWN_EDGE_TEMPERATURE: 100 °C
        SLOWDOWN_HOTSPOT_TEMPERATURE: 110 °C
        SLOWDOWN_VRAM_TEMPERATURE: 100 °C
        SHUTDOWN_EDGE_TEMPERATURE: 105 °C
        SHUTDOWN_HOTSPOT_TEMPERATURE: 115 °C
        SHUTDOWN_VRAM_TEMPERATURE: 105 °C
 GPU: 1
    LIMIT:
        MAX_POWER: 213 W
        MIN_POWER: 213 W
        SOCKET_POWER: 213 W
        SLOWDOWN_EDGE_TEMPERATURE: 109 °C
        SLOWDOWN_HOTSPOT_TEMPERATURE: 110 °C
        SLOWDOWN_VRAM_TEMPERATURE: 100 °C
        SHUTDOWN_EDGE_TEMPERATURE: 114 °C
        SHUTDOWN_HOTSPOT_TEMPERATURE: 115 °C
        SHUTDOWN_VRAM_TEMPERATURE: 105 °C
 ```
 ### Changed
 - **`amdsmi_get_power_cap_info` now returns values in uW instead of W**  
 `amdsmi_get_power_cap_info` will return in uW as originally reflected by driver. Previously `amdsmi_get_power_cap_info` returned W values, this conflicts with our sets and modifies values retrieved from driver. We decided to keep the values returned from driver untouched (in original units, uW). Then in CLI we will convert to watts (as previously done - no changes here). Additionally, driver made updates to min power cap displayed for devices when overdrive is disabled which prompted for this change (in this case min_power_cap and max_power_cap are the same).
 - **Updated Python Library return types for amdsmi_get_gpu_memory_reserved_pages & amdsmi_get_gpu_bad_page_info**  
 Previously calls were returning "No bad pages found." if no pages were found, now it only returns the list type and can be empty.
 - **Updated `amd-smi metric --ecc-blocks` output**  
 The ecc blocks arguement was outputing blocks without counters available, updated the filtering show blocks that counters are available for:
@@ -52,6 +92,58 @@ GPU: 0
 - **Removed `amdsmi_get_gpu_process_info` from python library**  
 amdsmi_get_gpu_process_info was removed from the C library in an earlier build, but the API was still in the python interface
 ### Optimizations
 - **Updated `amd-smi monitor --pcie` output**  
 The source for pcie bandwidth monitor output was a legacy file we no longer support and was causing delays within the monitor command. The output is no longer using TX/RX but instantaneous bandwidth from gpu_metrics instead; updated output:
 ```shell
 $ amd-smi monitor --pcie
 GPU   PCIE_BW
  0   26 Mb/s
 ```
 ### Fixed
 - **Fixed `amd-smi metric --power` now provides power output for Navi2x/Navi3x/MI1x**  
 These systems use an older version of gpu_metrics in amdgpu. This fix only updates what CLI outputs.
 No change in any of our APIs.
 ```shell
 $ amd-smi metric --power
 GPU: 0
    POWER:
        SOCKET_POWER: 11 W
        GFX_VOLTAGE: 768 mV
        SOC_VOLTAGE: 925 mV
        MEM_VOLTAGE: 1250 mV
        POWER_MANAGEMENT: ENABLED
        THROTTLE_STATUS: UNTHROTTLED
 GPU: 1
    POWER:
        SOCKET_POWER: 17 W
        GFX_VOLTAGE: 781 mV
        SOC_VOLTAGE: 806 mV
        MEM_VOLTAGE: 1250 mV
        POWER_MANAGEMENT: ENABLED
        THROTTLE_STATUS: UNTHROTTLED
 ```
 - **Fixed `amdsmitstReadWrite.TestPowerCapReadWrite` test for Navi3X, Navi2X, MI100**  
 Updates required `amdsmi_get_power_cap_info` to return in uW as originally reflected by driver. Previously `amdsmi_get_power_cap_info` returned W values, this conflicts with our sets and modifies values retrieved from driver. We decided to keep the values returned from driver untouched (in original units, uW). Then in CLI we will convert to watts (as previously done - no changes here). Additionally, driver made updates to min power cap displayed for devices when overdrive is disabled which prompted for this change (in this case min_power_cap and max_power_cap are the same).
 - **Fixed python interface call amdsmi_get_gpu_memory_reserved_pages & amdsmi_get_gpu_bad_page_info**  
 Previously python interface calls to populated bad pages resulted in a `ValueError: NULL pointer access`. This fixes the bad-pages subcommand CLI  subcommand as well.
 ## amd_smi_lib for ROCm 6.1.1
 ### Added
 - N/A
 ### Changed
 - **Updated metrics --clocks**  
 Output for `amd-smi metric --clock` is updated to reflect each engine and bug fixes for the clock lock status and deep sleep status.
@@ -188,9 +280,10 @@ GPU: 0
 ```
 - **Updated `amd-smi topology --json` to align with host/guest**  
-Topology's `--json` output now is changed to align with output reported bt host/guest systems. Additionally, users can select/filter specific topology details as desired (refer to `amd-smi topology -h` for full list). See examples shown below.
+Topology's `--json` output now is changed to align with output host/guest systems. Additionally, users can select/filter specific topology details as desired (refer to `amd-smi topology -h` for full list). See examples shown below.
 *Previous format:*
 ```shell
 $ amd-smi topology --json
 [
@@ -244,6 +337,7 @@ $ amd-smi topology --json
 ```
 *New format:*
 ```shell
 $ amd-smi topology --json
 [
@@ -275,6 +369,7 @@ $ amd-smi topology --json
    ...
 ]
 ```
 ```shell
 $ /opt/rocm/bin/amd-smi topology -a -t --json
 [
@@ -28,7 +28,7 @@ find_program(GIT NAMES git)
 ## Setup the package version based on git tags.
 set(PKG_VERSION_GIT_TAG_PREFIX "amdsmi_pkg_ver")
-get_package_version_number("24.5.1" ${PKG_VERSION_GIT_TAG_PREFIX} GIT)
+get_package_version_number("24.5.2" ${PKG_VERSION_GIT_TAG_PREFIX} GIT)
 message("Package version: ${PKG_VERSION_STR}")
 set(${AMD_SMI_LIBS_TARGET}_VERSION_MAJOR "${CPACK_PACKAGE_VERSION_MAJOR}")
 set(${AMD_SMI_LIBS_TARGET}_VERSION_MINOR "${CPACK_PACKAGE_VERSION_MINOR}")
@@ -79,7 +79,7 @@ amd-smi will report the version and current platform detected when running the c
 ~$ amd-smi
 usage: amd-smi [-h]  ...
-AMD System Management Interface | Version: 24.5.1.0 | ROCm version: 6.1.1 | Platform: Linux Baremetal
+AMD System Management Interface | Version: 24.5.2.0 | ROCm version: 6.1.2 | Platform: Linux Baremetal
 options:
  -h, --help          show this help message and exit
@@ -148,9 +148,9 @@ Command Modifiers:
 ```bash
 ~$ amd-smi static --help
-usage: amd-smi static [-h] [-g GPU [GPU ...] | -U CPU [CPU ...]] [-a] [-b] [-V] [-d] [-v]
+usage: amd-smi static [-h] [-g GPU [GPU ...]] [-a] [-b] [-V] [-d] [-v] [-c] [-B] [-r] [-p]
-                      [-c] [-B] [-r] [-p] [-l] [-u] [-s] [-i] [--json | --csv]
+                      [-l] [-P] [-x] [-s] [-u] [--json | --csv] [--file FILE]
-                      [--file FILE] [--loglevel LEVEL]
+                      [--loglevel LEVEL]
 If no GPU is specified, returns static information for all GPUs on the system.
 If no static argument is provided, all static information will be displayed.
@@ -179,6 +179,7 @@ Static Arguments:
  -r, --ras                Displays RAS features information
  -p, --partition          Partition information
  -l, --limit              All limit metric values (i.e. power and thermal limits)
  -s, --process-isolation  The process isolation status
  -u, --numa               All numa node information
 CPU Arguments:
@@ -474,13 +475,13 @@ Command Modifiers:
 ```bash
 usage: amd-smi set [-h] (-g GPU [GPU ...] | -U CPU [CPU ...] | -O CORE [CORE ...]) [-f %]
                   [-l LEVEL] [-P SETPROFILE] [-d SCLKMAX] [-C PARTITION] [-M PARTITION]
-                   [-o WATTS] [-p POLICY] [--cpu-pwr-limit PWR_LIMIT]
+                   [-o WATTS] [-p POLICY] [-i STATUS] [--cpu-pwr-limit PWR_LIMIT]
                   [--cpu-xgmi-link-width MIN_WIDTH MAX_WIDTH]
                   [--cpu-lclk-dpm-level NBIOID MIN_DPM MAX_DPM] [--cpu-pwr-eff-mode MODE]
                   [--cpu-gmi3-link-width MIN_LW MAX_LW] [--cpu-pcie-link-rate LINK_RATE]
                   [--cpu-df-pstate-range MAX_PSTATE MIN_PSTATE] [--cpu-enable-apb]
                   [--cpu-disable-apb DF_PSTATE] [--soc-boost-limit BOOST_LIMIT]
-                   [--core-boost-limit BOOST_LIMIT] [--json | --csv] [--file FILE]
+                   [--core-boost-limit BOOST_LIMIT] [-c] [--json | --csv] [--file FILE]
                   [--loglevel LEVEL]
 A GPU must be specified to set a configuration.
@@ -514,6 +515,8 @@ Set Arguments:
  -o, --power-cap WATTS                        Set power capacity limit
  -p, --dpm-policy POLICY_ID                   Set the GPU DPM policy using policy id
  -x, --xgmi-plpd POLICY_ID                    Set the GPU XGMI per-link power down policy using policy id
  -i, --process-isolation STATUS               Enable or disable the GPU process isolation: 0 for disable and 1 for enable.
  -c, --clear-sram-data                        Clear the GPU SRAM data
 CPU Arguments:
  --cpu-pwr-limit PWR_LIMIT                    Set power limit for the given socket. Input parameter is power limit value.
@@ -245,7 +245,7 @@ class AMDSMICommands():
    def static_gpu(self, args, multiple_devices=False, gpu=None, asic=None, bus=None, vbios=None,
                        limit=None, driver=None, ras=None, board=None, numa=None, vram=None,
                        cache=None, partition=None, dfc_ucode=None, fb_info=None, num_vf=None,
-                        policy=None, xgmi_plpd=None):
+                        policy=None, xgmi_plpd=None, process_isolation=None):
        """Get Static information for target gpu
        Args:
@@ -270,6 +270,7 @@ class AMDSMICommands():
            num_vf (bool, optional): Value override for args.num_vf. Defaults to None.
            policy (bool, optional): Value override for args.policy. Defaults to None.
            xgmi_plpd (bool, optional): Value override for args.xgmi_plpd. Defaults to None.
            process_isolation (bool, optional): Value override for args.process_isolation. Defaults to None.
        Returns:
            None: Print output via AMDSMILogger to destination
        """
@@ -306,8 +307,10 @@ class AMDSMICommands():
                args.policy = policy
            if xgmi_plpd:
                args.xgmi_plpd = xgmi_plpd
-            current_platform_args += ["ras", "limit", "partition", "policy", "xgmi_plpd"]
+            if process_isolation:
-            current_platform_values += [args.ras, args.limit, args.partition, args.policy, args.xgmi_plpd]
+                args.process_isolation = process_isolation
            current_platform_args += ["ras", "limit", "partition", "policy", "xgmi_plpd", "process_isolation"]
            current_platform_values += [args.ras, args.limit, args.partition, args.policy, args.xgmi_plpd, args.process_isolation]
        if self.helpers.is_linux() and not self.helpers.is_virtual_os():
            if numa:
@@ -411,7 +414,11 @@ class AMDSMICommands():
                    power_limit_error = False
                    power_cap_info = amdsmi_interface.amdsmi_get_power_cap_info(args.gpu)
                    max_power_limit = power_cap_info['max_power_cap']
                    max_power_limit = AMDSMIHelpers.convert_SI_unit(max_power_limit, AMDSMIHelpers.SI_Unit.MICRO)
                    min_power_limit = power_cap_info['min_power_cap']
                    min_power_limit = AMDSMIHelpers.convert_SI_unit(min_power_limit, AMDSMIHelpers.SI_Unit.MICRO)
                    socket_power_limit = power_cap_info['power_cap']
                    socket_power_limit = AMDSMIHelpers.convert_SI_unit(socket_power_limit, AMDSMIHelpers.SI_Unit.MICRO)
                except amdsmi_exception.AmdSmiLibraryException as e:
                    power_limit_error = True
                    max_power_limit = "N/A"
@@ -489,11 +496,18 @@ class AMDSMICommands():
                power_unit = 'W'
                temp_unit_human_readable = '\N{DEGREE SIGN}C'
                temp_unit_json = 'C'
-                if self.logger.is_human_readable_format():
+                if not power_limit_error:
-                    if not power_limit_error:
+                    max_power_limit = self.helpers.unit_format(self.logger,
-                        max_power_limit = f"{max_power_limit} {power_unit}"
+                                                               max_power_limit,
-                        socket_power_limit = f"{socket_power_limit} {power_unit}"
+                                                               power_unit)
                    min_power_limit = self.helpers.unit_format(self.logger,
                                                               min_power_limit,
                                                               power_unit)
                    socket_power_limit = self.helpers.unit_format(self.logger,
                                                                  socket_power_limit,
                                                                  power_unit)
                if self.logger.is_human_readable_format():
                    if not slowdown_temp_edge_limit_error:
                        slowdown_temp_edge_limit = f"{slowdown_temp_edge_limit} {temp_unit_human_readable}"
                    if not slowdown_temp_hotspot_limit_error:
@@ -506,13 +520,8 @@ class AMDSMICommands():
                        shutdown_temp_hotspot_limit = f"{shutdown_temp_hotspot_limit} {temp_unit_human_readable}"
                    if not shutdown_temp_vram_limit_error:
                        shutdown_temp_vram_limit = f"{shutdown_temp_vram_limit} {temp_unit_human_readable}"
                if self.logger.is_json_format():
                    if not power_limit_error:
                        max_power_limit = {"value" : max_power_limit,
                                           "unit" : power_unit}
                        socket_power_limit = {"value" : socket_power_limit,
                                              "unit" : power_unit}
                if self.logger.is_json_format():
                    if not slowdown_temp_edge_limit_error:
                        slowdown_temp_edge_limit = {"value" : slowdown_temp_edge_limit,
                                                    "unit" : temp_unit_json}
@@ -535,6 +544,7 @@ class AMDSMICommands():
                limit_info = {}
                # Power limits
                limit_info['max_power'] = max_power_limit
                limit_info['min_power'] = min_power_limit
                limit_info['socket_power'] = socket_power_limit
                # Shutdown limits
@@ -643,6 +653,16 @@ class AMDSMICommands():
                    logging.debug("Failed to get xgmi_plpd info for gpu %s | %s", gpu_id, e.get_error_info())
                static_dict['xgmi_plpd'] = policy_info
        if 'process_isolation' in current_platform_args:
            if args.process_isolation:
                try:
                    status = amdsmi_interface.amdsmi_get_gpu_process_isolation(args.gpu)
                    status = "Enabled" if status else "Disabled"
                except amdsmi_exception.AmdSmiLibraryException as e:
                    status = "N/A"
                    logging.debug("Failed to process isolation for gpu %s | %s", gpu_id, e.get_error_info())
                static_dict['process_isolation'] = status
        if 'numa' in current_platform_args:
            if args.numa:
                try:
@@ -779,7 +799,7 @@ class AMDSMICommands():
                bus=None, vbios=None, limit=None, driver=None, ras=None,
                board=None, numa=None, vram=None, cache=None, partition=None,
                dfc_ucode=None, fb_info=None, num_vf=None, cpu=None,
-                interface_ver=None, policy=None, xgmi_plpd = None):
+                interface_ver=None, policy=None, xgmi_plpd = None, process_isolation=None):
        """Get Static information for target gpu and cpu
        Args:
@@ -804,6 +824,7 @@ class AMDSMICommands():
            interface_ver (bool, optional): Value override for args.interface_ver. Defaults to None
            policy (bool, optional): Value override for args.policy. Defaults to None.
            xgmi_plpd (bool, optional): Value override for args.xgmi_plpd. Defaults to None.
            process_isolation (bool, optional): Value override for args.process_isolation. Defaults to None.
        Raises:
            IndexError: Index error if gpu list is empty
@@ -829,7 +850,8 @@ class AMDSMICommands():
        gpu_args_enabled = False
        gpu_attributes = ["asic", "bus", "vbios", "limit", "driver", "ras",
                          "board", "numa", "vram", "cache", "partition",
-                          "dfc_ucode", "fb_info", "num_vf", "policy", "xgmi_plpd"]
+                          "dfc_ucode", "fb_info", "num_vf", "policy", "xgmi_plpd",
                          "process_isolation"]
        for attr in gpu_attributes:
            if hasattr(args, attr):
                if getattr(args, attr):
@@ -859,7 +881,8 @@ class AMDSMICommands():
                self.static_gpu(args, multiple_devices, gpu, asic,
                                    bus, vbios, limit, driver, ras,
                                    board, numa, vram, cache, partition,
-                                    dfc_ucode, fb_info, num_vf, policy)
+                                    dfc_ucode, fb_info, num_vf, policy,
                                    process_isolation)
        elif self.helpers.is_amd_hsmp_initialized(): # Only CPU is initialized
            if args.cpu == None:
                args.cpu = self.cpu_handles
@@ -873,7 +896,8 @@ class AMDSMICommands():
            self.static_gpu(args, multiple_devices, gpu, asic,
                                bus, vbios, limit, driver, ras,
                                board, numa, vram, cache, partition,
-                                dfc_ucode, fb_info, num_vf, policy, xgmi_plpd)
+                                dfc_ucode, fb_info, num_vf, policy, xgmi_plpd,
                                process_isolation)
    def firmware(self, args, multiple_devices=False, gpu=None, fw_list=True):
@@ -998,14 +1022,19 @@ class AMDSMICommands():
        # Get gpu_id for logging
        gpu_id = self.helpers.get_gpu_id_from_device_handle(args.gpu)
        bad_pages_not_found = "No bad pages found."
        try:
            bad_page_info = amdsmi_interface.amdsmi_get_gpu_bad_page_info(args.gpu)
            # If bad_page_info is an empty list overwrite with not found error statement
            if bad_page_info == []:
                bad_page_info = bad_pages_not_found
                bad_page_error = True
            else:
                bad_page_error = False
        except amdsmi_exception.AmdSmiLibraryException as e:
            bad_page_info = "N/A"
            logging.debug("Failed to get bad page info for gpu %s | %s", gpu_id, e.get_error_info())
        if bad_page_info == "N/A" or bad_page_info == "No bad pages found.":
            bad_page_error = True
            logging.debug("Failed to get bad page info for gpu %s | %s", gpu_id, e.get_error_info())
        if args.retired:
            if bad_page_error:
@@ -1017,13 +1046,17 @@ class AMDSMICommands():
                        bad_page_info_entry = {}
                        bad_page_info_entry["page_address"] = bad_page["page_address"]
                        bad_page_info_entry["page_size"] = bad_page["page_size"]
-                        bad_page_info_entry["status"] = bad_page["status"].name
+                        status_string = amdsmi_interface.amdsmi_wrapper.amdsmi_memory_page_status_t__enumvalues[bad_page["status"]]
                        bad_page_info_entry["status"] = status_string.replace("AMDSMI_MEM_PAGE_STATUS_", "")
                        bad_page_info_output.append(bad_page_info_entry)
                # Remove brackets if there is only one value
                if len(bad_page_info_output) == 1:
                    bad_page_info_output = bad_page_info_output[0]
-                values_dict['retired'] = bad_page_info_output
+                if bad_page_info_output == []:
                    values_dict['retired'] = bad_pages_not_found
                else:
                    values_dict['retired'] = bad_page_info_output
        if args.pending:
            if bad_page_error:
@@ -1035,13 +1068,17 @@ class AMDSMICommands():
                        bad_page_info_entry = {}
                        bad_page_info_entry["page_address"] = bad_page["page_address"]
                        bad_page_info_entry["page_size"] = bad_page["page_size"]
-                        bad_page_info_entry["status"] = bad_page["status"].name
+                        status_string = amdsmi_interface.amdsmi_wrapper.amdsmi_memory_page_status_t__enumvalues[bad_page["status"]]
                        bad_page_info_entry["status"] = status_string.replace("AMDSMI_MEM_PAGE_STATUS_", "")
                        bad_page_info_output.append(bad_page_info_entry)
                # Remove brackets if there is only one value
                if len(bad_page_info_output) == 1:
                    bad_page_info_output = bad_page_info_output[0]
-                values_dict['pending'] = bad_page_info_output
+                if bad_page_info_output == []:
                    values_dict['pending'] = bad_pages_not_found
                else:
                    values_dict['pending'] = bad_page_info_output
        if args.un_res:
            if bad_page_error:
@@ -1053,13 +1090,17 @@ class AMDSMICommands():
                        bad_page_info_entry = {}
                        bad_page_info_entry["page_address"] = bad_page["page_address"]
                        bad_page_info_entry["page_size"] = bad_page["page_size"]
-                        bad_page_info_entry["status"] = bad_page["status"].name
+                        status_string = amdsmi_interface.amdsmi_wrapper.amdsmi_memory_page_status_t__enumvalues[bad_page["status"]]
                        bad_page_info_entry["status"] = status_string.replace("AMDSMI_MEM_PAGE_STATUS_", "")
                        bad_page_info_output.append(bad_page_info_entry)
                # Remove brackets if there is only one value
                if len(bad_page_info_output) == 1:
                    bad_page_info_output = bad_page_info_output[0]
-                values_dict['un_res'] = bad_page_info_output
+                if bad_page_info_output == []:
                    values_dict['un_res'] = bad_pages_not_found
                else:
                    values_dict['un_res'] = bad_page_info_output
        # Store values in logger.output
        self.logger.store_output(args.gpu, 'values', values_dict)
@@ -1295,24 +1336,19 @@ class AMDSMICommands():
                    for key, value in power_info.items():
                        if value == 0xFFFF:
                            power_info[key] = "N/A"
-                        elif self.logger.is_human_readable_format():
+                        elif "voltage" in key:
-                            if "voltage" in key:
+                            power_info[key] = self.helpers.unit_format(self.logger,
-                                power_info[key] = f"{value} {voltage_unit}"
+                                                                       value,
-                            elif "power" in key:
+                                                                       voltage_unit)
-                                power_info[key] = f"{value} {power_unit}"
+                        elif "power" in key:
-                        elif self.logger.is_json_format():
+                            if ((key == "current_socket_power" or key == "average_socket_power")
-                            if "voltage" in key:
+                                and value != "N/A"):
-                                power_info[key] = {"value" : value,
+                                power_dict['socket_power'] = self.helpers.unit_format(self.logger,
-                                                  "unit" : voltage_unit}
+                                                                       value,
-                            elif "power" in key:
+                                                                       power_unit)
-                                power_info[key] = {"value" : value,
+                            power_info[key] = self.helpers.unit_format(self.logger,
-                                                  "unit" : power_unit}
+                                                                       value,
-
+                                                                       power_unit)
                    power_dict['socket_power'] = power_info['current_socket_power']
                    if power_dict['socket_power'] == "N/A":
                        # For older gpu's when current power doesn't populate we use the average socket power instead
                        power_dict['socket_power'] = power_info['average_socket_power']
                    power_dict['gfx_voltage'] = power_info['gfx_voltage']
                    power_dict['soc_voltage'] = power_info['soc_voltage']
@@ -3326,7 +3362,8 @@ class AMDSMICommands():
    def set_gpu(self, args, multiple_devices=False, gpu=None, fan=None, perf_level=None,
                  profile=None, perf_determinism=None, compute_partition=None,
-                  memory_partition=None, power_cap=None, dpm_policy=None, xgmi_plpd = None):
+                  memory_partition=None, power_cap=None, dpm_policy=None, xgmi_plpd = None,
                  process_isolation=None, clear_sram_data = None):
        """Issue reset commands to target gpu(s)
        Args:
@@ -3342,7 +3379,8 @@ class AMDSMICommands():
            power_cap (int, optional): Value override for args.power_cap. Defaults to None.
            dpm_policy (int, optional): Value override for args.dpm_policy. Defaults to None.
            xgmi_plpd (int, optional): Value override for args.xgmi_plpd. Defaults to None.
-
+            process_isolation (int, optional): Value override for args.process_isolation. Defaults to None.
            clear_sram_data (int, optional): Value override for args.clear_sram_data. Defaults to None.
        Raises:
            ValueError: Value error if no gpu value is provided
            IndexError: Index error if gpu list is empty
@@ -3371,6 +3409,10 @@ class AMDSMICommands():
            args.dpm_policy = dpm_policy
        if xgmi_plpd:
            args.xgmi_plpd = xgmi_plpd
        if process_isolation:
            args.process_isolation = process_isolation
        if clear_sram_data:
            args.clear_sram_data = clear_sram_data
        # Handle No GPU passed
        if args.gpu == None:
            raise ValueError('No GPU provided, specific GPU target(s) are needed')
@@ -3389,9 +3431,11 @@ class AMDSMICommands():
                    args.compute_partition,
                    args.memory_partition,
                    args.perf_determinism is not None,
-                    args.power_cap,
+                    args.power_cap is not None,
-                    args.dpm_policy,
+                    args.dpm_policy is not None,
-                    args.xgmi_plpd]):
+                    args.xgmi_plpd is not None,
                    args.process_isolation is not None,
                    args.clear_sram_data]):
            command = " ".join(sys.argv[1:])
            raise AmdSmiRequiredCommandException(command, self.logger.format)
@@ -3455,32 +3499,16 @@ class AMDSMICommands():
                    raise PermissionError('Command requires elevation') from e
                raise ValueError(f"Unable to set memory partition to {args.memory_partition} on {gpu_string}") from e
            self.logger.store_output(args.gpu, 'memorypartition', f"Successfully set memory partition to {args.memory_partition}")
        if args.dpm_policy:
            try:
                amdsmi_interface.amdsmi_set_dpm_policy(args.gpu, args.dpm_policy)
            except amdsmi_exception.AmdSmiLibraryException as e:
                if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
                    raise PermissionError('Command requires elevation') from e
                raise ValueError(f"Unable to set dpm policy to {args.dpm_policy} on {gpu_string}") from e
            self.logger.store_output(args.gpu, 'dpmpolicy', f"Successfully set dpm policy to id {args.dpm_policy}")
        if args.xgmi_plpd:
            try:
                amdsmi_interface.amdsmi_set_xgmi_plpd(args.gpu, args.xgmi_plpd)
            except amdsmi_exception.AmdSmiLibraryException as e:
                if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
                    raise PermissionError('Command requires elevation') from e
                raise ValueError(f"Unable to set XGMI policy to {args.xgmi_plpd} on {gpu_string}") from e
            self.logger.store_output(args.gpu, 'xgmiplpd', f"Successfully set per-link power down policy to id {args.dpm_policy}")
        if isinstance(args.power_cap, int):
            try:
                power_cap_info = amdsmi_interface.amdsmi_get_power_cap_info(args.gpu)
                logging.debug(f"Power cap info for gpu {gpu_id} | {power_cap_info}")
                min_power_cap = power_cap_info["min_power_cap"]
                min_power_cap = AMDSMIHelpers.convert_SI_unit(min_power_cap, AMDSMIHelpers.SI_Unit.MICRO)
                max_power_cap = power_cap_info["max_power_cap"]
                max_power_cap = AMDSMIHelpers.convert_SI_unit(max_power_cap, AMDSMIHelpers.SI_Unit.MICRO)
                current_power_cap = power_cap_info["power_cap"]
                current_power_cap = AMDSMIHelpers.convert_SI_unit(current_power_cap, AMDSMIHelpers.SI_Unit.MICRO)
            except amdsmi_exception.AmdSmiLibraryException as e:
                raise ValueError(f"Unable to get power cap info from {gpu_string}") from e
@@ -3488,7 +3516,9 @@ class AMDSMICommands():
                self.logger.store_output(args.gpu, 'powercap', f"Power cap is already set to {args.power_cap}")
            elif args.power_cap >= min_power_cap and args.power_cap <= max_power_cap:
                try:
-                    amdsmi_interface.amdsmi_set_power_cap(args.gpu, 0, args.power_cap * 1000000)
+                    new_power_cap = AMDSMIHelpers.convert_SI_unit(args.power_cap, AMDSMIHelpers.SI_Unit.BASE,
                                                                  AMDSMIHelpers.SI_Unit.MICRO)
                    amdsmi_interface.amdsmi_set_power_cap(args.gpu, 0, new_power_cap)
                except amdsmi_exception.AmdSmiLibraryException as e:
                    if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
                        raise PermissionError('Command requires elevation') from e
@@ -3499,6 +3529,48 @@ class AMDSMICommands():
                if min_power_cap == 0:
                    min_power_cap = 1
                self.logger.store_output(args.gpu, 'powercap', f"Power cap must be between {min_power_cap} and {max_power_cap}")
        if isinstance(args.dpm_policy, int):
            try:
                amdsmi_interface.amdsmi_set_dpm_policy(args.gpu, args.dpm_policy)
            except amdsmi_exception.AmdSmiLibraryException as e:
                if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
                    raise PermissionError('Command requires elevation') from e
                raise ValueError(f"Unable to set dpm policy to {args.dpm_policy} on {gpu_string}") from e
            self.logger.store_output(args.gpu, 'dpmpolicy', f"Successfully set dpm policy to id {args.dpm_policy}")
        if isinstance(args.xgmi_plpd, int):
            try:
                amdsmi_interface.amdsmi_set_xgmi_plpd(args.gpu, args.xgmi_plpd)
            except amdsmi_exception.AmdSmiLibraryException as e:
                if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
                    raise PermissionError('Command requires elevation') from e
                raise ValueError(f"Unable to set XGMI policy to {args.xgmi_plpd} on {gpu_string}") from e
            self.logger.store_output(args.gpu, 'xgmiplpd', f"Successfully set per-link power down policy to id {args.dpm_policy}")
        if isinstance(args.process_isolation, int):
            status_string = "Enabled" if args.process_isolation else "Disabled"
            result = f"Requested process isolation to {status_string}" # This should not print out
            try:
                current_status = amdsmi_interface.amdsmi_get_gpu_process_isolation(args.gpu)
                if current_status == args.process_isolation:
                    result = f"Process isolation is already {status_string}"
                else:
                    amdsmi_interface.amdsmi_set_gpu_process_isolation(args.gpu, args.process_isolation)
                    result = f"Successfully set process isolation to {status_string}"
            except amdsmi_exception.AmdSmiLibraryException as e:
                if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
                    raise PermissionError('Command requires elevation') from e
                raise ValueError(f"Unable to set process isolation to {status_string} on {gpu_string}") from e
            self.logger.store_output(args.gpu, 'process_isolation', result)
        if args.clear_sram_data:
            try:
                # Only 1 can be used for now.
                amdsmi_interface.amdsmi_set_gpu_clear_sram_data(args.gpu, 1)
                result = 'Successfully clear GPU SRAM data'
            except amdsmi_exception.AmdSmiLibraryException as e:
                if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
                    raise PermissionError('Command requires elevation') from e
                raise ValueError(f"Unable to clear SRAM data on GPU {gpu_id}") from e
            self.logger.store_output(args.gpu, 'clear_sram_data', result)
        if multiple_devices:
            self.logger.store_multiple_device_output()
@@ -3513,7 +3585,8 @@ class AMDSMICommands():
                  cpu=None, cpu_pwr_limit=None, cpu_xgmi_link_width=None, cpu_lclk_dpm_level=None,
                  cpu_pwr_eff_mode=None, cpu_gmi3_link_width=None, cpu_pcie_link_rate=None,
                  cpu_df_pstate_range=None, cpu_enable_apb=None, cpu_disable_apb=None,
-                  soc_boost_limit=None, core=None, core_boost_limit=None, dpm_policy=None, xgmi_plpd=None):
+                  soc_boost_limit=None, core=None, core_boost_limit=None, dpm_policy=None, xgmi_plpd=None,
                  process_isolation=None, clear_sram_data=None):
        """Issue reset commands to target gpu(s)
        Args:
@@ -3544,7 +3617,8 @@ class AMDSMICommands():
            core_boost_limit (int, optional): Value override for args.core_boost_limit. Defaults to None
            dpm_policy (int, optional): Value override for args.dpm_policy. Defaults to None.
            xgmi_plpd (int, optional): Value override for args.xgmi_plpd. Defaults to None.
-
+            process_isolation (int, optional): Value override for args.process_isolation. Defaults to None.
            clear_sram_data (int, optional): Value override for args.clear_sram_data. Defaults to None.
        Raises:
            ValueError: Value error if no gpu value is provided
            IndexError: Index error if gpu list is empty
@@ -3564,13 +3638,13 @@ class AMDSMICommands():
        # Check if a GPU argument has been set
        gpu_args_enabled = False
        gpu_attributes = ["fan", "perf_level", "profile", "perf_determinism", "compute_partition",
-                          "memory_partition", "power_cap", "dpm_policy", "xgmi_plpd"]
+                          "memory_partition", "power_cap", "dpm_policy", "xgmi_plpd", "process_isolation",
                          "clear_sram_data"]
        for attr in gpu_attributes:
            if hasattr(args, attr):
                if getattr(args, attr) is not None:
                    gpu_args_enabled = True
                    break
        # Check if a CPU argument has been set
        cpu_args_enabled = False
        cpu_attributes = ["cpu_pwr_limit", "cpu_xgmi_link_width", "cpu_lclk_dpm_level", "cpu_pwr_eff_mode",
@@ -3578,7 +3652,7 @@ class AMDSMICommands():
                          "cpu_enable_apb", "cpu_disable_apb", "soc_boost_limit"]
        for attr in cpu_attributes:
            if hasattr(args, attr):
-                if getattr(args, attr) is not None:
+                if getattr(args, attr) not in [None, False]:
                    cpu_args_enabled = True
                    break
@@ -3620,7 +3694,8 @@ class AMDSMICommands():
                self.logger.clear_multiple_devices_ouput()
                self.set_gpu(args, multiple_devices, gpu, fan, perf_level,
                                profile, perf_determinism, compute_partition,
-                                memory_partition, power_cap, dpm_policy, xgmi_plpd)
+                                memory_partition, power_cap, dpm_policy, xgmi_plpd,
                                process_isolation, clear_sram_data)
        elif self.helpers.is_amd_hsmp_initialized(): # Only CPU is initialized
            if args.cpu == None and args.core == None:
                raise ValueError('No CPU or CORE provided, specific target(s) are needed')
@@ -3639,7 +3714,8 @@ class AMDSMICommands():
            self.logger.clear_multiple_devices_ouput()
            self.set_gpu(args, multiple_devices, gpu, fan, perf_level,
                            profile, perf_determinism, compute_partition,
-                            memory_partition, power_cap, dpm_policy, xgmi_plpd)
+                            memory_partition, power_cap, dpm_policy, xgmi_plpd,
                            process_isolation, clear_sram_data)
    def reset(self, args, multiple_devices=False, gpu=None, gpureset=None,
@@ -3660,7 +3736,6 @@ class AMDSMICommands():
            compute_partition (bool, optional): Value override for args.compute_partition. Defaults to None.
            memory_partition (bool, optional): Value override for args.memory_partition. Defaults to None.
            power_cap (int, optional): Value override for args.power_cap. Defaults to None.
        Raises:
            ValueError: Value error if no gpu value is provided
            IndexError: Index error if gpu list is empty
@@ -3838,20 +3913,26 @@ class AMDSMICommands():
            try:
                power_cap_info = amdsmi_interface.amdsmi_get_power_cap_info(args.gpu)
                logging.debug(f"Power cap info for gpu {gpu_id} | {power_cap_info}")
-                default_power_cap = power_cap_info["default_power_cap"]
+                default_power_cap_in_w = power_cap_info["default_power_cap"]
                default_power_cap_in_w = AMDSMIHelpers.convert_SI_unit(default_power_cap_in_w, AMDSMIHelpers.SI_Unit.MICRO)
                current_power_cap_in_w = power_cap_info["power_cap"]
                current_power_cap_in_w = AMDSMIHelpers.convert_SI_unit(current_power_cap_in_w, AMDSMIHelpers.SI_Unit.MICRO)
            except amdsmi_exception.AmdSmiLibraryException as e:
                raise ValueError(f"Unable to get power cap info from {gpu_id}") from e
-            if args.power_cap == default_power_cap:
+            if current_power_cap_in_w == default_power_cap_in_w:
-                self.logger.store_output(args.gpu, 'powercap', f"Power cap is already set to {default_power_cap}")
+                self.logger.store_output(args.gpu, 'powercap', f"Power cap is already set to {default_power_cap_in_w}")
            else:
                try:
-                    amdsmi_interface.amdsmi_set_power_cap(args.gpu, 0, default_power_cap * 1000000)
+                    default_power_cap_in_uw = AMDSMIHelpers.convert_SI_unit(default_power_cap_in_w,
                                                                            AMDSMIHelpers.SI_Unit.BASE,
                                                                            AMDSMIHelpers.SI_Unit.MICRO)
                    amdsmi_interface.amdsmi_set_power_cap(args.gpu, 0, default_power_cap_in_uw)
                except amdsmi_exception.AmdSmiLibraryException as e:
                    if e.get_error_code() == amdsmi_interface.amdsmi_wrapper.AMDSMI_STATUS_NO_PERM:
                        raise PermissionError('Command requires elevation') from e
-                    raise ValueError(f"Unable to reset power cap to {default_power_cap} on GPU {gpu_id}") from e
+                    raise ValueError(f"Unable to reset power cap to {default_power_cap_in_w} on GPU {gpu_id}") from e
-                self.logger.store_output(args.gpu, 'powercap', f"Successfully set power cap to {default_power_cap}")
+                self.logger.store_output(args.gpu, 'powercap', f"Successfully set power cap to {default_power_cap_in_w}")
        if multiple_devices:
            self.logger.store_multiple_device_output()
@@ -4234,38 +4315,14 @@ class AMDSMICommands():
            self.logger.table_header += 'VRAM_TOTAL'.rjust(12)
        if args.pcie:
            try:
-                pcie_bw = amdsmi_interface.amdsmi_get_gpu_pci_throughput(args.gpu)
+                pcie_info = amdsmi_interface.amdsmi_get_pcie_info(args.gpu)['pcie_metric']
-                sent = pcie_bw['sent'] * pcie_bw['max_pkt_sz']
+                pcie_bw_unit = 'Mb/s'
-                received = pcie_bw['received'] * pcie_bw['max_pkt_sz']
+                monitor_values['pcie_bw'] = self.helpers.unit_format(self.logger, pcie_info['pcie_bandwidth'], pcie_bw_unit)
                bw_unit = "Mb/s"
                packet_size_unit = "B"
                if sent > 0:
                    sent = sent // 1024 // 1024
                if received > 0:
                    received = received // 1024 // 1024
                if self.logger.is_human_readable_format():
                    sent = f"{sent} {bw_unit}"
                    received = f"{received} {bw_unit}"
                    pcie_bw['max_pkt_sz'] = f"{pcie_bw['max_pkt_sz']} {packet_size_unit}"
                if self.logger.is_json_format():
                    sent = {"value" : sent,
                            "unit" : bw_unit}
                    received = {"value" : received,
                                "unit" : bw_unit}
                    pcie_bw['max_pkt_sz'] = {"value" : pcie_bw['max_pkt_sz'],
                                                "unit" : packet_size_unit}
                monitor_values['pcie_tx'] = sent
                monitor_values['pcie_rx'] = received
            except amdsmi_exception.AmdSmiLibraryException as e:
-                monitor_values['pcie_tx'] = "N/A"
+                monitor_values['pcie_bw'] = "N/A"
-                monitor_values['pcie_rx'] = "N/A"
+                logging.debug("Failed to get pci bandwidth on gpu %s | %s", gpu_id, e.get_error_info())
                logging.debug("Failed to get pci throughput on gpu %s | %s", gpu_id, e.get_error_info())
-            self.logger.table_header += 'PCIE_TX'.rjust(10)
+            self.logger.table_header += 'PCIE_BW'.rjust(10)
            self.logger.table_header += 'PCIE_RX'.rjust(10)
        self.logger.store_output(args.gpu, 'values', monitor_values)
@@ -29,6 +29,7 @@ import time
 from subprocess import run
 from subprocess import PIPE, STDOUT
 from typing import List
 from enum import Enum
 from amdsmi_init import *
 from BDF import BDF
@@ -726,3 +727,46 @@ class AMDSMIHelpers():
        if logger.is_human_readable_format():
            return f"{value} {unit}"
        return f"{value}"
    class SI_Unit(float, Enum):
        GIGA = 1000000000  # 10^9
        MEGA = 1000000     # 10^6
        KILO = 1000        # 10^3
        HECTO = 100        # 10^2
        DEKA = 10          # 10^1
        BASE = 1           # 10^0
        DECI = 0.1         # 10^-1
        CENTI = 0.01       # 10^-2
        MILLI = 0.001      # 10^-3
        MICRO = 0.000001   # 10^-6
        NANO = 0.000000001 # 10^-9
    def convert_SI_unit(val: float, unit_in: SI_Unit, unit_out = SI_Unit.BASE) -> float:
        """This function will convert a value into another
         scientific (SI) unit. Defaults unit_out to SI_Unit.BASE
         This function returns a float.
        params:
            val: float unit to convert
            unit_in: Requires using SI_Unit to set current value's SI unit (eg. SI_Unit.MICRO)
            unit_out - Requires using SI_Unit to set current value's SI unit
             default value is SI_Unit.BASE (eg. SI_Unit.MICRO)
        return:
            float : converted SI unit of value requested
        """
        return val * unit_in / unit_out
    def convert_SI_unit(val: int, unit_in: SI_Unit, unit_out=SI_Unit.BASE) -> int:
        """This function will convert a value into another
         scientific (SI) unit. Defaults unit_out to SI_Unit.BASE
         This function returns a int.
        params:
            val: int unit to convert
            unit_in: Requires using SI_Unit to set current value's SI unit (eg. SI_Unit.MICRO)
            unit_out - Requires using SI_Unit to set current value's SI unit
             default value is SI_Unit.BASE (eg. SI_Unit.MICRO)
        return:
            int : converted SI unit of value requested
        """
        return int(float(val) * unit_in / unit_out)
@@ -545,6 +545,7 @@ class AMDSMIParser(argparse.ArgumentParser):
        board_help = "All board information"
        dpm_policy_help = "The available DPM policy"
        xgmi_plpd_help = "The available XGMI per-link power down policy"
        process_isolation_help = "The process isolation status"
        # Options arguments help text for Hypervisors and Baremetal
        ras_help = "Displays RAS features information"
@@ -586,6 +587,7 @@ class AMDSMIParser(argparse.ArgumentParser):
                static_parser.add_argument('-l', '--limit', action='store_true', required=False, help=limit_help)
                static_parser.add_argument('-P', '--policy', action='store_true', required=False, help=dpm_policy_help)
                static_parser.add_argument('-x', '--xgmi-plpd', action='store_true', required=False, help=xgmi_plpd_help)
                static_parser.add_argument('-R', '--process-isolation', action='store_true', required=False, help=process_isolation_help)
            if self.helpers.is_linux() and not self.helpers.is_virtual_os():
                static_parser.add_argument('-u', '--numa', action='store_true', required=False, help=numa_help)
@@ -967,8 +969,9 @@ class AMDSMIParser(argparse.ArgumentParser):
        set_compute_partition_help = f"Set one of the following the compute partition modes:\n\t{compute_partition_choices_str}"
        set_memory_partition_help = f"Set one of the following the memory partition modes:\n\t{memory_partition_choices_str}"
        set_power_cap_help = "Set power capacity limit"
-        set_dpm_policy_help = f"Set the GPU DPM policy using policy id\n"
+        set_dpm_policy_help = "Set the GPU DPM policy using policy id\n"
-        set_xgmi_plpd_help = f"Set the GPU XGMI per-link power down policy using policy id\n"
+        set_xgmi_plpd_help = "Set the GPU XGMI per-link power down policy using policy id\n"
        set_process_isolation_help = "Enable or disable the GPU process isolation: 0 for disable and 1 for enable.\n"
        # Help text for CPU set options
        set_cpu_pwr_limit_help = "Set power limit for the given socket. Input parameter is power limit value."
@@ -982,6 +985,7 @@ class AMDSMIParser(argparse.ArgumentParser):
        set_cpu_enable_apb_help = "Enables the DF p-state performance boost algorithm"
        set_cpu_disable_apb_help = "Disables the DF p-state performance boost algorithm. Input parameter is DFPstate (0-3)"
        set_soc_boost_limit_help = "Sets the boost limit for the given socket. Input parameter is socket BOOST_LIMIT value"
        run_gpu_clear_sram_data_help = f"Clear the GPU SRAM data\n"
        # Help text for CPU Core set options
        set_core_boost_limit_help = "Sets the boost limit for the given core. Input parameter is core BOOST_LIMIT value"
@@ -1006,6 +1010,8 @@ class AMDSMIParser(argparse.ArgumentParser):
            set_value_parser.add_argument('-o', '--power-cap', action='store', type=self._positive_int, required=False, help=set_power_cap_help, metavar='WATTS')
            set_value_parser.add_argument('-p', '--dpm-policy', action='store', required=False,  type=self._not_negative_int, help=set_dpm_policy_help, metavar='POLICY_ID')
            set_value_parser.add_argument('-x', '--xgmi-plpd', action='store', required=False,  type=self._not_negative_int, help=set_xgmi_plpd_help, metavar='POLICY_ID')
            set_value_parser.add_argument('-R', '--process-isolation', action='store', choices=[0,1], type=self._not_negative_int, required=False, help=set_process_isolation_help, metavar='STATUS')
            set_value_parser.add_argument('-c', '--clear-sram-data', action='store_true', required=False, help=run_gpu_clear_sram_data_help)
        if self.helpers.is_amd_hsmp_initialized():
            # Optional CPU Args
@@ -1104,7 +1110,7 @@ class AMDSMIParser(argparse.ArgumentParser):
        throttle_help = "Monitor thermal throttle status"
        ecc_help = "Monitor ECC single bit, ECC double bit, and PCIe replay error counts"
        mem_usage_help = "Monitor memory usage in MB"
-        pcie_throughput_help = "Monitor PCIe Tx/Rx in MB/s"
+        pcie_bandwidth_help = "Monitor PCIe bandwidth in Mb/s"
        # Create monitor subparser
        monitor_parser = subparsers.add_parser('monitor', help=monitor_help, description=monitor_subcommand_help)
@@ -1127,7 +1133,7 @@ class AMDSMIParser(argparse.ArgumentParser):
        monitor_parser.add_argument('-s', '--throttle-status', action='store_true', required=False, help=throttle_help)
        monitor_parser.add_argument('-e', '--ecc', action='store_true', required=False, help=ecc_help)
        monitor_parser.add_argument('-v', '--vram-usage', action='store_true', required=False, help=mem_usage_help)
-        monitor_parser.add_argument('-r', '--pcie', action='store_true', required=False, help=pcie_throughput_help)
+        monitor_parser.add_argument('-r', '--pcie', action='store_true', required=False, help=pcie_bandwidth_help)
    def _add_rocm_smi_parser(self, subparsers, func):
@@ -48,7 +48,7 @@ PROJECT_NAME           = AMD SMI
 # could be handy for archiving the generated documentation or if some version
 # control system is used.
-PROJECT_NUMBER         = "24.5.1.0"
+PROJECT_NUMBER         = "24.5.2.0"
 # Using the PROJECT_BRIEF tag one can provide an optional one line description
 # for a project that appears at the top of each page and should give viewer a
@@ -657,15 +657,15 @@ int main() {
            CHK_AMDSMI_RET(ret)
            printf("    Output of amdsmi_get_power_cap_info:\n");
            std::cout << "\t\t Power Cap: " << cap_info.power_cap
-                      << "W\n";
+                      << " uW\n";
            std::cout << "\t\t Default Power Cap: " << cap_info.default_power_cap
-                      << "\n\n";
+                      << " uW\n\n";
            std::cout << "\t\t Dpm Cap: " << cap_info.dpm_cap
-                      << "\n\n";
+                      << " MHz\n\n";
            std::cout << "\t\t Min Power Cap: " << cap_info.min_power_cap
-                      << "\n\n";
+                      << " uW\n\n";
            std::cout << "\t\t Max Power Cap: " << cap_info.max_power_cap
-                      << "\n\n";
+                      << " uW\n\n";
            /// Get GPU Metrics info
            std::cout << "\n\n";
@@ -154,7 +154,7 @@ typedef enum {
 #define AMDSMI_LIB_VERSION_MAJOR 5
 //! Minor version should be updated for each API change, but without changing headers
-#define AMDSMI_LIB_VERSION_MINOR 1
+#define AMDSMI_LIB_VERSION_MINOR 2
 //! Release version should be set to 0 as default and can be updated by the PMs for each CSP point release
 #define AMDSMI_LIB_VERSION_RELEASE 0
@@ -522,11 +522,11 @@ typedef struct {
 } amdsmi_pcie_info_t;
 typedef struct {
-  uint64_t power_cap;
+  uint64_t power_cap;           //!< current power cap (uW)
-  uint64_t default_power_cap;
+  uint64_t default_power_cap;   //!< default power cap (uW)
-  uint64_t dpm_cap;
+  uint64_t dpm_cap;             //!< dpm power cap (MHz)
-  uint64_t min_power_cap;
+  uint64_t min_power_cap;       //!< minimum power cap (uW)
-  uint64_t max_power_cap;
+  uint64_t max_power_cap;       //!< maximum power cap (uW)
  uint64_t reserved[3];
 } amdsmi_power_cap_info_t;
@@ -3455,6 +3455,68 @@ amdsmi_status_t amdsmi_get_xgmi_plpd(amdsmi_processor_handle processor_handle,
 amdsmi_status_t amdsmi_set_xgmi_plpd(amdsmi_processor_handle processor_handle,
                             uint32_t plpd_id);
 /**
 * @brief Get the status of the Process Isolation
 *
 * @platform{gpu_bm_linux} @platform{guest_1vf}
 *
 * @details Given a processor handle @p processor_handle, this function will write
 * current process isolation status to @p pisolate. The 0 is the process isolation
 * disabled, and the 1 is the process isolation enabled.
 *
 *  @param[in] processor_handle a processor handle
 *
 *  @param[in, out] pisolate the process isolation status.
 *  If this parameter is nullptr, this function will return
 *  ::AMDSMI_STATUS_INVAL
 *
 *  @return ::amdsmi_status_t | ::AMDSMI_STATUS_SUCCESS on success, non-zero on fail
 */
 amdsmi_status_t amdsmi_get_gpu_process_isolation(amdsmi_processor_handle processor_handle,
                             uint32_t* pisolate);
 /**
 * @brief Enable/disable the system Process Isolation
 *
 * @platform{gpu_bm_linux} @platform{guest_1vf}
 *
 * @details Given a processor handle @p processor_handle and a process isolation @p pisolate,
 * flag, this function will set the Process Isolation for this processor. The 0 is the process
 * isolation disabled, and the 1 is the process isolation enabled.
 *
 *  @note This function requires root access
 *
 *  @param[in] processor_handle a processor handle
 *
 *  @param[in] pisolate the process isolation status to set.
 *
 *  @return ::amdsmi_status_t | ::AMDSMI_STATUS_SUCCESS on success, non-zero on fail
 */
 amdsmi_status_t amdsmi_set_gpu_process_isolation(amdsmi_processor_handle processor_handle,
                             uint32_t pisolate);
 /**
 * @brief Clear the GPU SRAM data
 *
 * @platform{gpu_bm_linux} @platform{guest_1vf}
 *
 * @details Given a processor handle @p processor_handle, and a sclean flag @p sclean,
 * this function will clear the SRAM data of this processor. This can be called between 
 * user logins to prevent information leak.
 *
 *  @note This function requires root access
 *
 *  @param[in] processor_handle a processor handle
 *
 *  @param[in] sclean the clean flag. Only 1 will take effect and other number
 *  are reserved for future usage.
 *
 *  @return ::amdsmi_status_t | ::AMDSMI_STATUS_SUCCESS on success, non-zero on fail
 */
 amdsmi_status_t amdsmi_set_gpu_clear_sram_data(amdsmi_processor_handle processor_handle,
                  uint32_t sclean);
 /** @} End PerfCont */
 /*****************************************************************************/
@@ -4546,7 +4608,8 @@ amdsmi_get_gpu_board_info(amdsmi_processor_handle processor_handle, amdsmi_board
 /**
 *  @brief          Returns the power caps as currently configured in the
- *                  system. It is not supported on virtual machine guest
+ *                  system. Power in units of uW.
 *                  It is not supported on virtual machine guest
 *
 *  @platform{gpu_bm_linux}  @platform{host}
 *
@@ -414,13 +414,13 @@ Input parameters:
 Output: Dictionary with fields
-Field | Description
+Field | Description | Units
---|---
+---|---|---
-`power_cap` |  power capability
+`power_cap` |  power capability | uW
-`dpm_cap` |  dynamic power management capability
+`dpm_cap` |  dynamic power management capability | MHz
-`default_power_cap` |  default power capability
+`default_power_cap` |  default power capability | uW
-`min_power_cap` | min power capability
+`min_power_cap` | min power capability | uW
-`max_power_cap` | max power capability
+`max_power_cap` | max power capability | uW
 Exceptions that can be thrown by `amdsmi_get_power_cap_info` function:
@@ -843,7 +843,7 @@ Input parameters:
 * `processor_handle` device which to query
-Output: List consisting of dictionaries with fields for each bad page found
+Output: List consisting of dictionaries with fields for each bad page found; can be an empty list
 Field | Description
 ---|---
@@ -868,7 +868,7 @@ try:
    else:
        for device in devices:
            bad_page_info = amdsmi_get_gpu_bad_page_info(device)
-            if not len(bad_page_info):
+            if not bad_page_info: # Can be empty list
                print("No bad pages found")
                continue
            for bad_page in bad_page_info:
@@ -880,6 +880,53 @@ except AmdSmiException as e:
    print(e)
 ```
 ### amdsmi_get_gpu_memory_reserved_pages
 Description: Returns reserved memory page info for the given GPU.
 It is not supported on virtual machine guest
 Input parameters:
 * `processor_handle` device which to query
 Output: List consisting of dictionaries with fields for each reserved memory page found; can be an empty list
 Field | Description
 ---|---
 `value` | Value of memory reserved page
 `page_address` | Address of memory reserved page
 `page_size` | Size of memory reserved page
 `status` | Status of memory reserved page
 Exceptions that can be thrown by `amdsmi_get_gpu_memory_reserved_pages` function:
 * `AmdSmiLibraryException`
 * `AmdSmiRetryException`
 * `AmdSmiParameterException`
 Example:
 ```python
 try:
    devices = amdsmi_get_processor_handles()
    if len(devices) == 0:
        print("No GPUs on machine")
    else:
        for device in devices:
            reserved_memory_page_info = amdsmi_get_gpu_memory_reserved_pages(device)
            if not reserved_memory_page_info: # Can be empty list
                print("No memory reserved pages found")
                continue
            for reserved_memory_page in reserved_memory_page_info:
                print(reserved_memory_page["value"])
                print(reserved_memory_page["page_address"])
                print(reserved_memory_page["page_size"])
                print(reserved_memory_page["status"])
 except AmdSmiException as e:
    print(e)
 ```
 ### amdsmi_get_gpu_process_list
 Description: Returns the list of processes running on the target GPU; May require root level access
@@ -1963,6 +2010,98 @@ except AmdSmiException as e:
    print(e)
 ```
 ### amdsmi_get_gpu_process_isolation
 Description: Get the status of the Process Isolation
 Input parameters:
 * `processor_handle` handle for the given device
 Output: integer corresponding to isolation_status; 0 - disabled, 1 - enabled
 Exceptions that can be thrown by `amdsmi_get_gpu_process_isolation` function:
 * `AmdSmiLibraryException`
 * `AmdSmiRetryException`
 * `AmdSmiParameterException`
 Example:
 ```python
 try:
    devices = amdsmi_get_processor_handles()
    if len(devices) == 0:
        print("No GPUs on machine")
    else:
        for device in devices:
            isolate = amdsmi_get_gpu_process_isolation(device)
            print("Process Isolation Status: ", isolate)
 except AmdSmiException as e:
    print(e)
 ```
 ### amdsmi_set_gpu_process_isolation
 Description: Enable/disable the system Process Isolation for the given device handle.
 Input parameters:
 * `processor_handle` handle for the given device
 * `pisolate` the process isolation status to set. 0 is the process isolation disabled, and 1 is the process isolation enabled.
 Output: None
 Exceptions that can be thrown by `amdsmi_set_gpu_process_isolation` function:
 * `AmdSmiLibraryException`
 * `AmdSmiRetryException`
 * `AmdSmiParameterException`
 Example:
 ```python
 try:
    devices = amdsmi_get_processor_handles()
    if len(devices) == 0:
        print("No GPUs on machine")
    else:
        for device in devices:
            amdsmi_set_gpu_process_isolation(device, 1)
 except AmdSmiException as e:
    print(e)
 ```
 ### amdsmi_set_gpu_clear_sram_data
 Description: Clear the SRAM data of the given device. This can be called between user logins to prevent information leak.
 Input parameters:
 * `processor_handle` handle for the given device
 * `sclean` the clean flag. Only 1 will take effect and other number are reserved for future usage.
 Output: None
 Exceptions that can be thrown by `amdsmi_set_gpu_clear_sram_data` function:
 * `AmdSmiLibraryException`
 * `AmdSmiRetryException`
 * `AmdSmiParameterException`
 Example:
 ```python
 try:
    devices = amdsmi_get_processor_handles()
    if len(devices) == 0:
        print("No GPUs on machine")
    else:
        for device in devices:
            amdsmi_set_gpu_clear_sram_data(device, 1)
 except AmdSmiException as e:
    print(e)
 ```
 ### amdsmi_get_gpu_overdrive_level
 Description: Get the overdrive percent associated with the device with provided
@@ -2602,6 +2741,75 @@ except AmdSmiException as e:
    print(e)
 ```
 ### amdsmi_get_dpm_policy
 Description: Get dpm policy information.
 Input parameters:
 * `processor_handle` handle for the given device
 * `policy_id` the policy id to set.
 Output: Dictionary with fields
 Field | Description
 ---|---
 `num_supported` | total number of supported policies
 `current_id` | current policy id
 `policies` | list of dictionaries containing possible policies
 Exceptions that can be thrown by `amdsmi_get_dpm_policy` function:
 * `AmdSmiLibraryException`
 * `AmdSmiRetryException`
 * `AmdSmiParameterException`
 Example:
 ```python
 try:
    devices = amdsmi_get_processor_handles()
    if len(devices) == 0:
        print("No GPUs on machine")
    else:
        for device in devices:
            dpm_policies = amdsmi_get_dpm_policy(device)
            print(dpm_policies)
 except AmdSmiException as e:
    print(e)
 ```
 ### amdsmi_set_dpm_policy
 Description: Set the dpm policy to corresponding policy_id. Typically following: 0(default),1,2,3
 Input parameters:
 * `processor_handle` handle for the given device
 * `policy_id` the policy id to set.
 Output: None
 Exceptions that can be thrown by `amdsmi_set_dpm_policy` function:
 * `AmdSmiLibraryException`
 * `AmdSmiRetryException`
 * `AmdSmiParameterException`
 Example:
 ```python
 try:
    devices = amdsmi_get_processor_handles()
    if len(devices) == 0:
        print("No GPUs on machine")
    else:
        for device in devices:
            amdsmi_set_dpm_policy(device, 0)
 except AmdSmiException as e:
    print(e)
 ```
 ### amdsmi_set_xgmi_plpd
 Description: Set the xgmi per-link power down policy parameter for the processor
@@ -3159,13 +3367,8 @@ Example:
 ```python
 try:
-    devices = amdsmi_get_processor_handles()
+    version = amdsmi_get_lib_version()
-    if len(devices) == 0:
+    print(version)
        print("No GPUs on machine")
    else:
        for device in devices:
            version = amdsmi_get_lib_version()
            print(version)
 except AmdSmiException as e:
    print(e)
 ```
@@ -134,6 +134,10 @@ from .amdsmi_interface import amdsmi_set_gpu_fan_speed
 from .amdsmi_interface import amdsmi_reset_gpu_fan
 from .amdsmi_interface import amdsmi_set_clk_freq
 from .amdsmi_interface import amdsmi_set_gpu_overdrive_level
 from .amdsmi_interface import amdsmi_set_dpm_policy
 from .amdsmi_interface import amdsmi_set_xgmi_plpd
 from .amdsmi_interface import amdsmi_set_gpu_clear_sram_data
 from .amdsmi_interface import amdsmi_set_gpu_process_isolation
 # # Physical State Queries
 from .amdsmi_interface import amdsmi_get_gpu_fan_rpms
@@ -365,6 +365,7 @@ class AmdSmiProcessorType(IntEnum):
    NON_AMD_GPU = amdsmi_wrapper.NON_AMD_GPU
    NON_AMD_CPU = amdsmi_wrapper.NON_AMD_CPU
 class AmdSmiEventReader:
    def __init__(
        self, processor_handle: amdsmi_wrapper.amdsmi_processor_handle,
@@ -439,21 +440,22 @@ def _format_bad_page_info(bad_page_info, bad_page_count: ctypes.c_uint32) -> Lis
    Format bad page info data retrieved.
    Parameters:
-        bad_page_info(`POINTER(amdsmi_retired_page_record_t)`): Pointer to bad page info
+        bad_page_info(`amdsmi_retired_page_record_t`): A populated list of amdsmi_retired_page_record_t(s)
-        retrieved.
+        retrieved. Ex: (amdsmi_wrapper.amdsmi_retired_page_record_t * #)()
        bad_page_count(`c_uint32`): Bad page count.
    Returns:
-        `list`: List containing formatted bad pages.
+        `list`: List containing formatted bad pages. Can be empty
    """
-    if not isinstance(
+    if bad_page_count == 0:
-        bad_page_info, ctypes.POINTER(
+        return []
-            amdsmi_wrapper.amdsmi_retired_page_record_t)
+
-    ):
+    # Check if each struct within bad_page_info is valid
-        raise AmdSmiParameterException(
+    for bad_page in bad_page_info:
-            bad_page_info, ctypes.POINTER(
+        if not isinstance(bad_page, amdsmi_wrapper.amdsmi_retired_page_record_t):
-                amdsmi_wrapper.amdsmi_retired_page_record_t)
+            raise AmdSmiParameterException(
-        )
+                bad_page, amdsmi_wrapper.amdsmi_retired_page_record_t
            )
    table_records = []
    for i in range(bad_page_count.value):
@@ -1802,23 +1804,24 @@ def amdsmi_get_gpu_bad_page_info(
        )
    num_pages = ctypes.c_uint32()
-    retired_page_record = ctypes.POINTER(
+    nullptr = ctypes.POINTER(amdsmi_wrapper.amdsmi_retired_page_record_t)()
        amdsmi_wrapper.amdsmi_retired_page_record_t)()
    _check_res(
        amdsmi_wrapper.amdsmi_get_gpu_bad_page_info(
-            processor_handle, ctypes.byref(num_pages), retired_page_record
+            processor_handle, ctypes.byref(num_pages), nullptr
        )
    )
    table_records = _format_bad_page_info(retired_page_record, num_pages)
    if num_pages.value == 0:
-        return "No bad pages found."
+        return []
    else:
        table_records = _format_bad_page_info(retired_page_record, num_pages)
-    return table_records
+    bad_pages = (amdsmi_wrapper.amdsmi_retired_page_record_t * num_pages.value)()
    _check_res(
        amdsmi_wrapper.amdsmi_get_gpu_bad_page_info(
            processor_handle, ctypes.byref(num_pages), bad_pages
        )
    )
    return _format_bad_page_info(bad_pages, num_pages)
 def amdsmi_get_gpu_total_ecc_count(
@@ -2734,6 +2737,7 @@ def amdsmi_set_clk_freq(
        )
    )
 def amdsmi_set_dpm_policy(
    processor_handle: amdsmi_wrapper.amdsmi_processor_handle,
    policy_id: int,
@@ -2748,6 +2752,7 @@ def amdsmi_set_dpm_policy(
        )
    )
 def amdsmi_set_xgmi_plpd(
    processor_handle: amdsmi_wrapper.amdsmi_processor_handle,
    policy_id: int,
@@ -2762,6 +2767,37 @@ def amdsmi_set_xgmi_plpd(
        )
    )
 def amdsmi_set_gpu_process_isolation(
    processor_handle: amdsmi_wrapper.amdsmi_processor_handle,
    pisolate: int,
 ):
    if not isinstance(processor_handle, amdsmi_wrapper.amdsmi_processor_handle):
        raise AmdSmiParameterException(
            processor_handle, amdsmi_wrapper.amdsmi_processor_handle
        )
    _check_res(
        amdsmi_wrapper.amdsmi_set_gpu_process_isolation(
            processor_handle, pisolate
        )
    )
 def amdsmi_set_gpu_clear_sram_data(
    processor_handle: amdsmi_wrapper.amdsmi_processor_handle,
    sclean: int,
 ):
    if not isinstance(processor_handle, amdsmi_wrapper.amdsmi_processor_handle):
        raise AmdSmiParameterException(
            processor_handle, amdsmi_wrapper.amdsmi_processor_handle
        )
    _check_res(
        amdsmi_wrapper.amdsmi_set_gpu_clear_sram_data(
            processor_handle, sclean
        )
    )
 def amdsmi_set_gpu_overdrive_level(
    processor_handle: amdsmi_wrapper.amdsmi_processor_handle, overdrive_value: int
 ):
@@ -2793,6 +2829,7 @@ def amdsmi_get_gpu_bdf_id(processor_handle: amdsmi_wrapper.amdsmi_processor_hand
    return bdfid.value
 def amdsmi_set_gpu_pci_bandwidth(
    processor_handle: amdsmi_wrapper.amdsmi_processor_handle, bitmask: int
 ) -> None:
@@ -3089,7 +3126,6 @@ def amdsmi_set_gpu_od_volt_info(
    )
 def amdsmi_get_gpu_fan_rpms(
    processor_handle: amdsmi_wrapper.amdsmi_processor_handle, sensor_idx: int
 ) -> int:
@@ -3320,6 +3356,7 @@ def amdsmi_get_clk_freq(
        "frequency": list(freq.frequency)[: freq.num_supported - 1],
    }
 def amdsmi_get_dpm_policy(
    processor_handle: amdsmi_wrapper.amdsmi_processor_handle,
 ) -> Dict[str, Any]:
@@ -3351,6 +3388,7 @@ def amdsmi_get_dpm_policy(
        "policies": polices,
    }
 def amdsmi_get_xgmi_plpd(
    processor_handle: amdsmi_wrapper.amdsmi_processor_handle,
 ) -> Dict[str, Any]:
@@ -3382,6 +3420,25 @@ def amdsmi_get_xgmi_plpd(
        "plpds": polices,
    }
 def amdsmi_get_gpu_process_isolation(
    processor_handle: amdsmi_wrapper.amdsmi_processor_handle,
 ) -> int:
    if not isinstance(processor_handle, amdsmi_wrapper.amdsmi_processor_handle):
        raise AmdSmiParameterException(
            processor_handle, amdsmi_wrapper.amdsmi_processor_handle
        )
    pisolate = ctypes.c_uint32()
    _check_res(
        amdsmi_wrapper.amdsmi_get_gpu_process_isolation(
            processor_handle, ctypes.byref(pisolate)
        )
    )
    return pisolate.value
 def amdsmi_get_gpu_od_volt_info(
    processor_handle: amdsmi_wrapper.amdsmi_processor_handle,
 ) -> Dict[str, Any]:
@@ -3804,21 +3861,24 @@ def amdsmi_get_gpu_memory_reserved_pages(
        )
    num_pages = ctypes.c_uint32()
-    retired_page_record = ctypes.POINTER(
+    nullptr = ctypes.POINTER(amdsmi_wrapper.amdsmi_retired_page_record_t)()
        amdsmi_wrapper.amdsmi_retired_page_record_t)()
    _check_res(
        amdsmi_wrapper.amdsmi_get_gpu_memory_reserved_pages(
-            processor_handle, ctypes.byref(num_pages), retired_page_record
+            processor_handle, ctypes.byref(num_pages), nullptr
        )
    )
    table_records = _format_bad_page_info(retired_page_record, num_pages)
    if num_pages.value == 0:
-        return "No bad pages found."
+        return []
    else:
        table_records = _format_bad_page_info(retired_page_record, num_pages)
-    return table_records
+    mem_reserved_pages = (amdsmi_wrapper.amdsmi_retired_page_record_t * num_pages)()
    _check_res(
        amdsmi_wrapper.amdsmi_get_gpu_memory_reserved_pages(
            processor_handle, ctypes.byref(num_pages), mem_reserved_pages
        )
    )
    return _format_bad_page_info(mem_reserved_pages, num_pages)
 def amdsmi_get_gpu_metrics_header_info(
@@ -2076,6 +2076,15 @@ amdsmi_get_xgmi_plpd.argtypes = [amdsmi_processor_handle, ctypes.POINTER(struct_
 amdsmi_set_xgmi_plpd = _libraries['libamd_smi.so'].amdsmi_set_xgmi_plpd
 amdsmi_set_xgmi_plpd.restype = amdsmi_status_t
 amdsmi_set_xgmi_plpd.argtypes = [amdsmi_processor_handle, uint32_t]
 amdsmi_get_gpu_process_isolation = _libraries['libamd_smi.so'].amdsmi_get_gpu_process_isolation
 amdsmi_get_gpu_process_isolation.restype = amdsmi_status_t
 amdsmi_get_gpu_process_isolation.argtypes = [amdsmi_processor_handle, ctypes.POINTER(ctypes.c_uint32)]
 amdsmi_set_gpu_process_isolation = _libraries['libamd_smi.so'].amdsmi_set_gpu_process_isolation
 amdsmi_set_gpu_process_isolation.restype = amdsmi_status_t
 amdsmi_set_gpu_process_isolation.argtypes = [amdsmi_processor_handle, uint32_t]
 amdsmi_set_gpu_clear_sram_data = _libraries['libamd_smi.so'].amdsmi_set_gpu_clear_sram_data
 amdsmi_set_gpu_clear_sram_data.restype = amdsmi_status_t
 amdsmi_set_gpu_clear_sram_data.argtypes = [amdsmi_processor_handle, uint32_t]
 amdsmi_get_lib_version = _libraries['libamd_smi.so'].amdsmi_get_lib_version
 amdsmi_get_lib_version.restype = amdsmi_status_t
 amdsmi_get_lib_version.argtypes = [ctypes.POINTER(struct_amdsmi_version_t)]
@@ -2589,7 +2598,7 @@ __all__ = \
    'amdsmi_get_gpu_pci_throughput', 'amdsmi_get_gpu_perf_level',
    'amdsmi_get_gpu_pm_metrics_info',
    'amdsmi_get_gpu_power_profile_presets',
-    'amdsmi_get_gpu_process_list',
+    'amdsmi_get_gpu_process_isolation', 'amdsmi_get_gpu_process_list',
    'amdsmi_get_gpu_ras_block_features_enabled',
    'amdsmi_get_gpu_ras_feature_info',
    'amdsmi_get_gpu_reg_table_info', 'amdsmi_get_gpu_revision',
@@ -2646,18 +2655,19 @@ __all__ = \
    'amdsmi_set_cpu_socket_boostlimit',
    'amdsmi_set_cpu_socket_lclk_dpm_level',
    'amdsmi_set_cpu_socket_power_cap', 'amdsmi_set_cpu_xgmi_width',
-    'amdsmi_set_dpm_policy', 'amdsmi_set_gpu_clk_range',
+    'amdsmi_set_dpm_policy', 'amdsmi_set_gpu_clear_sram_data',
-    'amdsmi_set_gpu_compute_partition',
+    'amdsmi_set_gpu_clk_range', 'amdsmi_set_gpu_compute_partition',
    'amdsmi_set_gpu_event_notification_mask',
    'amdsmi_set_gpu_fan_speed', 'amdsmi_set_gpu_memory_partition',
    'amdsmi_set_gpu_od_clk_info', 'amdsmi_set_gpu_od_volt_info',
    'amdsmi_set_gpu_overdrive_level', 'amdsmi_set_gpu_pci_bandwidth',
    'amdsmi_set_gpu_perf_determinism_mode',
    'amdsmi_set_gpu_perf_level', 'amdsmi_set_gpu_power_profile',
-    'amdsmi_set_power_cap', 'amdsmi_set_xgmi_plpd',
+    'amdsmi_set_gpu_process_isolation', 'amdsmi_set_power_cap',
-    'amdsmi_shut_down', 'amdsmi_smu_fw_version_t',
+    'amdsmi_set_xgmi_plpd', 'amdsmi_shut_down',
-    'amdsmi_socket_handle', 'amdsmi_status_code_to_string',
+    'amdsmi_smu_fw_version_t', 'amdsmi_socket_handle',
-    'amdsmi_status_t', 'amdsmi_stop_gpu_event_notification',
+    'amdsmi_status_code_to_string', 'amdsmi_status_t',
    'amdsmi_stop_gpu_event_notification',
    'amdsmi_temp_range_refresh_rate_t', 'amdsmi_temperature_metric_t',
    'amdsmi_temperature_type_t', 'amdsmi_topo_get_link_type',
    'amdsmi_topo_get_link_weight', 'amdsmi_topo_get_numa_node_number',
@@ -3362,7 +3362,7 @@ rsmi_status_t rsmi_dev_dpm_policy_get(uint32_t dv_ind,
 *
 *  @note This function requires root access
 *
- *  @param[in] processor_handle a processor handle
+ *  @param[in] dv_ind a device index
 *
 *  @param[in] policy_id the dpm policy will be modified
 *
@@ -3410,6 +3410,61 @@ rsmi_status_t rsmi_dev_xgmi_plpd_get(uint32_t dv_ind,
 */
 rsmi_status_t rsmi_dev_xgmi_plpd_set(uint32_t dv_ind,
                             uint32_t plpd_id);
 /**
 * @brief Get the status of the Process Isolation
 *
 * @details Given a device index @p dv_ind, this function will write
 * current process isolation status to @p pisolate. The 0 is the process isolation
 * disabled, and the 1 is the process isolation enabled.
 *
 *  @param[in] dv_ind a device index
 *
 *  @param[in, out] pisolate the process isolation status.
 *  If this parameter is nullptr, this function will return
 *  ::RSMI_STATUS_INVAL
 *
 *  @return ::RSMI_STATUS_SUCCESS is returned upon successful call, non-zero on fail
 */
 rsmi_status_t rsmi_dev_process_isolation_get(uint32_t dv_ind,
                             uint32_t* pisolate);
 /**
 * @brief Enable/disable the system Process Isolation
 *
 * @details Given a device index @p dv_ind and a process isolation @p pisolate,
 * flag, this function will set the Process Isolation for this device. The 0 is the process
 * isolation disabled, and the 1 is the process isolation enabled.
 *
 *  @note This function requires root access
 *
 *  @param[in] dv_ind a device index
 *
 *  @param[in] pisolate the process isolation status to set.
 *
 *  @return ::RSMI_STATUS_SUCCESS is returned upon successful call, non-zero on fail
 */
 rsmi_status_t rsmi_dev_process_isolation_set(uint32_t dv_ind,
                             uint32_t pisolate);
 /**
 * @brief Clear the GPU SRAM data 
 *
 *
 * @details Given a device index @p dv_ind, this function will clear the
 * GPU SRAM data  of this device. This can be called between user logins to prevent information leak.
 *
 *  @note This function requires root access
 *
 *  @param[in] dv_ind a device index
 *
 *  @param[in] sclean the clean flag. Only 1 will take effect and other number
 *  are reserved for future usage.
 *
 *  @return ::RSMI_STATUS_SUCCESS is returned upon successful call, non-zero on fail
 */
 rsmi_status_t rsmi_dev_gpu_clear_sram_data(uint32_t dv_ind, uint32_t sclean);
 /** @} */  // end of PerfCont
 /*****************************************************************************/
@@ -101,6 +101,8 @@ enum DevKFDNodePropTypes {
 enum DevInfoTypes {
  kDevPerfLevel,
  kDevProcessIsolation,
  kDevShaderClean,
  kDevOverDriveLevel,
  kDevMemOverDriveLevel,
  kDevDevID,
@@ -222,6 +224,7 @@ class Device {
    void set_drm_render_minor(uint32_t minor) {drm_render_minor_ = minor;}
    static rsmi_dev_perf_level perfLvlStrToEnum(std::string s);
    uint64_t bdfid(void) const {return bdfid_;}
    int get_partition_id() const {return (bdfid_ >> 28) & 0xf; }  // location_id[31:28]
    void set_bdfid(uint64_t val) {bdfid_ = val;}
    pthread_mutex_t *mutex(void) {return mutex_.ptr;}
    evt::dev_evt_grp_set_t* supported_event_groups(void) {
@@ -59,6 +59,7 @@
 #include <cstring>
 #include <fstream>
 #include <iostream>
 #include <iterator>
 #include <map>
 #include <sstream>
 #include <vector>
@@ -1974,6 +1975,144 @@ rsmi_dev_gpu_clk_freq_set(uint32_t dv_ind,
 }
 rsmi_status_t rsmi_dev_process_isolation_get(uint32_t dv_ind,
                             uint32_t* pisolate) {
  std::ostringstream ss;
  ss << __PRETTY_FUNCTION__ << "| ======= start ======= dev_ind:"
    << dv_ind;
  LOG_TRACE(ss);
  CHK_SUPPORT_NAME_ONLY(pisolate)
  // the enforce_isolation sysfs is in this format <partition_id, enable_flag>
  // Get the partition_id. For SPX, the partition_id will be 0.
  int partition_id = dev->get_partition_id();
  DEVICE_MUTEX
  std::string str_val;
  rsmi_status_t ret = get_dev_value_line(amd::smi::kDevProcessIsolation, dv_ind, &str_val);
  if (ret == RSMI_STATUS_FILE_ERROR) {
    ss << __PRETTY_FUNCTION__ << " | ======= end ======="
       << ", get_dev_value_str() ret was RSMI_STATUS_FILE_ERROR "
       << "-> reporting RSMI_STATUS_NOT_SUPPORTED";
    LOG_ERROR(ss);
    return RSMI_STATUS_NOT_SUPPORTED;
  }
  if (ret != RSMI_STATUS_SUCCESS) {
    ss << __PRETTY_FUNCTION__ << " | ======= end ======="
       << ", get_dev_value_str() ret was not RSMI_STATUS_SUCCESS"
       << " -> reporting " << amd::smi::getRSMIStatusString(ret);
    LOG_ERROR(ss);
    return ret;
  }
  /*
  for 4 partition: enforce isolation is enabled on partition 2 and 
  disabled on partitions 0, 1, 3.
  $ cat /sys/class/drm/cardX/device/enforce_isolation
   0 0 1 0
  */
  std::stringstream iss(str_val);
  int number;
  std::vector<int> partition_status;
  while ( iss >> number )
    partition_status.push_back(number);
  if (partition_status.size() <= partition_id) {
    ss << __PRETTY_FUNCTION__ << " | ======= end ======="
              << ", the sysfs line " << str_val
              << " does not have the partition_id "
              << partition_id;
              LOG_ERROR(ss);
              return RSMI_STATUS_UNEXPECTED_DATA;
  }
  *pisolate = partition_status[partition_id];
  return RSMI_STATUS_SUCCESS;
 }
 rsmi_status_t rsmi_dev_process_isolation_set(uint32_t dv_ind,
                             uint32_t pisolate) {
  rsmi_status_t ret;
  TRY
  std::ostringstream ss;
  ss << __PRETTY_FUNCTION__ << " | ======= start =======";
  LOG_TRACE(ss);
  REQUIRE_ROOT_ACCESS
  DEVICE_MUTEX
  GET_DEV_FROM_INDX
  // To set the values,need to specify the setting for all of the partitions
  // For two partition
  // echo "1 0"  | sudo tee  /sys/class/drm/cardX/device/enforce_isolation
  int partition_id = dev->get_partition_id();
  std::string str_val;
  rsmi_status_t ret = get_dev_value_line(amd::smi::kDevProcessIsolation, dv_ind, &str_val);
  if (ret == RSMI_STATUS_FILE_ERROR) {
    ss << __PRETTY_FUNCTION__ << " | ======= end ======="
       << ", get_dev_value_str() ret was RSMI_STATUS_FILE_ERROR "
       << "-> reporting RSMI_STATUS_NOT_SUPPORTED";
    LOG_ERROR(ss);
    return RSMI_STATUS_NOT_SUPPORTED;
  }
  if (ret != RSMI_STATUS_SUCCESS) {
    ss << __PRETTY_FUNCTION__ << " | ======= end ======="
       << ", get_dev_value_str() ret was not RSMI_STATUS_SUCCESS"
       << " -> reporting " << amd::smi::getRSMIStatusString(ret);
    LOG_ERROR(ss);
    return ret;
  }
  // craft the string need to be writeen.
  // (1) parse the read enforce_isolation data into a vector
  std::stringstream iss(str_val);
  int number;
  std::vector<int> partition_status;
  while ( iss >> number ) {
    partition_status.push_back(number);
  }
  // (2) Validate the data
  if (partition_status.size() <= partition_id) {
    ss << __PRETTY_FUNCTION__ << " | ======= end ======="
              << ", the sysfs line " << str_val
              << " does not have the partition_id "
              << partition_id;
    LOG_ERROR(ss);
    return RSMI_STATUS_UNEXPECTED_DATA;
  }
  // (3) Create the complete list with the update
  partition_status[partition_id] = pisolate;
  std::stringstream result;
  std::copy(partition_status.begin(), partition_status.end(),
        std::ostream_iterator<int>(result, " "));
  std::string value = result.str().c_str();
  int write_ret = dev->writeDevInfo(amd::smi::kDevProcessIsolation , value);
  return amd::smi::ErrnoToRsmiStatus(write_ret);
  CATCH
 }
 rsmi_status_t rsmi_dev_gpu_clear_sram_data(uint32_t dv_ind,
    uint32_t sclean) {
  rsmi_status_t ret;
  TRY
  std::ostringstream ss;
  ss << __PRETTY_FUNCTION__ << " | ======= start =======";
  LOG_TRACE(ss);
  REQUIRE_ROOT_ACCESS
  DEVICE_MUTEX
  GET_DEV_FROM_INDX
  std::string value = std::to_string(sclean);
  int ret = dev->writeDevInfo(amd::smi::kDevShaderClean , value);
  return amd::smi::ErrnoToRsmiStatus(ret);
  CATCH
 }
 rsmi_status_t
 rsmi_dev_dpm_policy_set(uint32_t dv_ind,
                      uint32_t policy_id) {
@@ -82,6 +82,8 @@ static const char *kDevPCieVendorIDFName = "vendor";
 // Device sysfs file names
 static const char *kDevPerfLevelFName = "power_dpm_force_performance_level";
 static const char *kDevProcessIsolationFName = "enforce_isolation";
 static const char *kDevShaderCleanFName = "run_cleaner_shader";
 static const char *kDevDevProdNameFName = "product_name";
 static const char *kDevDevProdNumFName = "product_number";
 static const char *kDevDevIDFName = "device";
@@ -317,6 +319,8 @@ static const std::map<DevInfoTypes, const char *> kDevAttribNameMap = {
    {kDevGpuMetrics, kDevGpuMetricsFName},
    {kDevPmMetrics, kDevPmMetricsFName},
    {kDevDPMPolicy, kDevDPMPolicyFName},
    {kDevProcessIsolation, kDevProcessIsolationFName},
    {kDevShaderClean, kDevShaderCleanFName},
    {kDevRegMetrics, kDevRegMetricsFName},
    {kDevGpuReset, kDevGpuResetFName},
    {kDevAvailableComputePartition, kDevAvailableComputePartitionFName},
@@ -475,6 +479,8 @@ Device::devInfoTypesStrings = {
  {kDevMemoryPartition, "kDevMemoryPartition"},
  {kDevPCieVendorID, "kDevPCieVendorID"},
  {kDevDPMPolicy, "kDevDPMPolicy"},
  {kDevProcessIsolation, "kDevProcessIsolation"},
  {kDevShaderClean, "kDevShaderClean"},
 };
 static const std::map<const char *, dev_depends_t> kDevFuncDependsMap = {
@@ -516,6 +522,9 @@ static const std::map<const char *, dev_depends_t> kDevFuncDependsMap = {
  {"rsmi_dev_perf_level_set",            {{kDevPerfLevelFName}, {}}},
  {"rsmi_dev_perf_level_set_v1",         {{kDevPerfLevelFName}, {}}},
  {"rsmi_dev_perf_level_get",            {{kDevPerfLevelFName}, {}}},
  {"rsmi_dev_process_isolation_set",             {{kDevProcessIsolationFName}, {}}},
  {"rsmi_dev_process_isolation_get",             {{kDevProcessIsolationFName}, {}}},
  {"rsmi_dev_gpu_shader_clean",            {{kDevShaderCleanFName}, {}}},
  {"rsmi_perf_determinism_mode_set",     {{kDevPerfLevelFName,
                                           kDevPowerODVoltageFName}, {}}},
  {"rsmi_dev_overdrive_level_set",       {{kDevOverDriveLevelFName}, {}}},
@@ -939,6 +948,8 @@ int Device::writeDevInfo(DevInfoTypes type, std::string val) {
  sysfs_path += kDevAttribNameMap.at(type);
  switch (type) {
    case kDevGPUMClk:
    case kDevProcessIsolation:
    case kDevShaderClean:
    case kDevDCEFClk:
    case kDevFClk:
    case kDevGPUSClk:
@@ -1212,6 +1223,7 @@ int Device::readDevInfo(DevInfoTypes type, std::vector<std::string> *val) {
  switch (type) {
    case kDevGPUMClk:
    case kDevProcessIsolation:
    case kDevGPUSClk:
    case kDevDCEFClk:
    case kDevFClk:
@@ -1279,6 +1291,7 @@ int Device::readDevInfo(DevInfoTypes type, std::string *val) {
    case kDevMemoryPartition:
    case kDevNumaNode:
    case kDevXGMIPhysicalID:
    case kDevProcessIsolation:
      return readDevInfoStr(type, val);
      break;
@@ -1208,15 +1208,10 @@ amdsmi_get_power_cap_info(amdsmi_processor_handle processor_handle,
    if ((status == AMDSMI_STATUS_SUCCESS) && !set_ret_success)
        set_ret_success = true;
    // Dividing by 1000000 to get measurement in Watts
    (info->default_power_cap) /= 1000000;
    status = rsmi_wrapper(rsmi_dev_power_cap_range_get, processor_handle, sensor_ind,
                        &(info->max_power_cap), &(info->min_power_cap));
    // Dividing by 1000000 to get measurement in Watts
    (info->max_power_cap) /= 1000000;
    (info->min_power_cap) /= 1000000;
    if ((status == AMDSMI_STATUS_SUCCESS) && !set_ret_success)
        set_ret_success = true;
@@ -1385,6 +1380,30 @@ amdsmi_status_t amdsmi_get_xgmi_plpd(amdsmi_processor_handle processor_handle,
                    reinterpret_cast<rsmi_dpm_policy_t*>(policy));
 }
 amdsmi_status_t amdsmi_get_gpu_process_isolation(amdsmi_processor_handle processor_handle,
                             uint32_t* pisolate) {
    AMDSMI_CHECK_INIT();
    return rsmi_wrapper(rsmi_dev_process_isolation_get, processor_handle,
                    pisolate);
 }
 amdsmi_status_t amdsmi_set_gpu_process_isolation(amdsmi_processor_handle processor_handle,
                             uint32_t pisolate) {
    AMDSMI_CHECK_INIT();
    return rsmi_wrapper(rsmi_dev_process_isolation_set, processor_handle,
                   pisolate);
 }
 amdsmi_status_t amdsmi_set_gpu_clear_sram_data(amdsmi_processor_handle processor_handle,
                  uint32_t sclean) {
    AMDSMI_CHECK_INIT();
    return rsmi_wrapper(rsmi_dev_gpu_clear_sram_data, processor_handle,
                    sclean);
 }
 amdsmi_status_t
 amdsmi_get_gpu_memory_reserved_pages(amdsmi_processor_handle processor_handle,
                                    uint32_t *num_pages,
@@ -201,8 +201,6 @@ amdsmi_status_t smi_amdgpu_get_power_cap(amd::smi::AMDSmiGPUDevice* device, int
        return AMDSMI_STATUS_API_FAILED;
    }
    // Dividing by 1000000 to get measurement in Watts
    *cap /= 1000000;
    return AMDSMI_STATUS_SUCCESS;
 }
@@ -89,9 +89,10 @@ void TestPowerCapReadWrite::Close() {
 void TestPowerCapReadWrite::Run(void) {
  amdsmi_status_t ret;
-  uint64_t orig, min, max, new_cap;
+  uint64_t default_cap, min, max, new_cap, curr_cap;
  clock_t start, end;
  double cpu_time_used;
  const uint64_t MICRO_CONVERSION = 1000000;
  TestBase::Run();
  if (setup_failed_) {
@@ -110,22 +111,24 @@ void TestPowerCapReadWrite::Run(void) {
    ASSERT_EQ(ret, AMDSMI_STATUS_INVAL);
    min = info.min_power_cap;
    max = info.max_power_cap;
-    orig = info.default_power_cap;
+    default_cap = info.default_power_cap;
    curr_cap = info.power_cap;
    new_cap = (max + min)/2;
    // Check if power cap is within the range
    // skip the test otherwise
-    if (orig < min || orig > max) {
+    if (new_cap < min || new_cap > max) {
-      std::cout << "Power cap is not within the range. Skipping test for " << dv_ind << std::endl;
+      std::cout << "Power cap requested (" << new_cap
                << " uW) is not within the range. Skipping test for " << dv_ind << std::endl;
      continue;
    }
    new_cap = (max + min)/2;
    IF_VERB(STANDARD) {
-      std::cout << "Original Power Cap: " << orig << " uW" << std::endl;
+      std::cout << "[Before Set]  Default Power Cap: " << default_cap << " uW" << std::endl;
-      std::cout << "Power Cap Range: " << max << " uW to " << min <<
+      std::cout << "[Before Set]  Current Power Cap: " << curr_cap << " uW" << std::endl;
      std::cout << "[Before Set]  Power Cap Range [max to min]: " << max << " uW to " << min <<
                                                             " uW" << std::endl;
-      std::cout << "Setting new cap to " << new_cap << "..." << std::endl;
+      std::cout << "[Before Set]  Setting new cap to " << new_cap << "..." << std::endl;
    }
    start = clock();
    ret =  amdsmi_set_power_cap(processor_handles_[dv_ind], 0, new_cap);
@@ -142,25 +145,35 @@ void TestPowerCapReadWrite::Run(void) {
    ret = amdsmi_get_power_cap_info(processor_handles_[dv_ind], 0, &info);
    CHK_ERR_ASRT(ret)
-    new_cap = info.default_power_cap;
+    curr_cap = info.power_cap;
    // TODO(cfreehil) add some kind of assertion to verify new_cap is correct
    //       (or within a range)
    IF_VERB(STANDARD) {
-      std::cout << "Time spent: " << cpu_time_used << " uS" << std::endl;
+      std::cout << "[After Set]   Time spent: " << cpu_time_used << " uS" << std::endl;
-      std::cout << "New Power Cap: " << new_cap << " uW" << std::endl;
+      std::cout << "[After Set]   Current Power Cap: " << curr_cap << " uW" << std::endl;
-      std::cout << "Resetting cap to " << orig << "..." << std::endl;
+      std::cout << "[After Set]   Requested Power Cap: " << new_cap << " uW" << std::endl;
      std::cout << "[After Set]   Power Cap Range [max to min]: " << max << " uW to "
                                                                  << min << " uW" << std::endl;
      std::cout << "[After Set]   Resetting cap to " << default_cap << "..." << std::endl;
    }
    // Confirm in watts the values are equal
    ASSERT_EQ(curr_cap/MICRO_CONVERSION, new_cap/MICRO_CONVERSION);
-    ret =  amdsmi_set_power_cap(processor_handles_[dv_ind], 0, orig);
+    // Reset to default power cap
    ret =  amdsmi_set_power_cap(processor_handles_[dv_ind], 0, default_cap);
    CHK_ERR_ASRT(ret)
    ret = amdsmi_get_power_cap_info(processor_handles_[dv_ind], 0, &info);
    CHK_ERR_ASRT(ret)
-    new_cap = info.default_power_cap;
+    curr_cap = info.power_cap;
    IF_VERB(STANDARD) {
-      std::cout << "Current Power Cap: " << new_cap << " uW" << std::endl;
+      std::cout << "[After Reset] Current Power Cap: " << curr_cap << " uW" << std::endl;
      std::cout << "[After Reset] Requested Power Cap (default): " << default_cap << " uW"
                                                                   << std::endl;
      std::cout << "[After Reset] Power Cap Range [max to min]: " << max << " uW to "
                                                                  << min << " uW" << std::endl;
    }
    // Confirm in watts the values are equal
    ASSERT_EQ(curr_cap/MICRO_CONVERSION, default_cap/MICRO_CONVERSION);
  }
 }