From e52380a9b914a87d22da4a5f5bb7f7a3ab5c5183 Mon Sep 17 00:00:00 2001 From: "Pham, Gabriel" Date: Tue, 18 Feb 2025 15:04:17 -0600 Subject: [PATCH] Updated amdsmi-cli-tool documentation and made fix for nps_flags (#107) Signed-off-by: gabrpham [ROCm/amdsmi commit: b8f1d29251d0d8977479039fdeb764990cde2df5] --- .../amdsmi/docs/how-to/amdsmi-cli-tool.md | 311 +++++++++--------- 1 file changed, 157 insertions(+), 154 deletions(-) diff --git a/projects/amdsmi/docs/how-to/amdsmi-cli-tool.md b/projects/amdsmi/docs/how-to/amdsmi-cli-tool.md index 80de32cc7b..a759cc6fc2 100644 --- a/projects/amdsmi/docs/how-to/amdsmi-cli-tool.md +++ b/projects/amdsmi/docs/how-to/amdsmi-cli-tool.md @@ -97,10 +97,10 @@ GPU with some basic information for each VF. options: -h, --help show this help message and exit -g, --gpu GPU [GPU ...] Select a GPU ID, BDF, or UUID from the possible choices: - ID: 0 | BDF: 0000:01:00.0 | UUID: 7eff74a0-0000-1000-808f-7e20764e2714 - ID: 1 | BDF: 0001:01:00.0 | UUID: b6ff74a0-0000-1000-80ae-7c8cefe1f084 - ID: 2 | BDF: 0002:01:00.0 | UUID: 36ff74a0-0000-1000-8071-25d815189854 - ID: 3 | BDF: 0003:01:00.0 | UUID: f4ff74a0-0000-1000-80c4-4c2be5e66537 + ID: 0 | BDF: 0000:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 1 | BDF: 0001:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 2 | BDF: 0002:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 3 | BDF: 0003:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX all | Selects all devices -U, --cpu CPU [CPU ...] Select a CPU ID from the possible choices: ID: 0 @@ -138,10 +138,10 @@ If no static argument is provided, all static information will be displayed. Static Arguments: -h, --help show this help message and exit -g, --gpu GPU [GPU ...] Select a GPU ID, BDF, or UUID from the possible choices: - ID: 0 | BDF: 0000:01:00.0 | UUID: 7eff74a0-0000-1000-808f-7e20764e2714 - ID: 1 | BDF: 0001:01:00.0 | UUID: b6ff74a0-0000-1000-80ae-7c8cefe1f084 - ID: 2 | BDF: 0002:01:00.0 | UUID: 36ff74a0-0000-1000-8071-25d815189854 - ID: 3 | BDF: 0003:01:00.0 | UUID: f4ff74a0-0000-1000-80c4-4c2be5e66537 + ID: 0 | BDF: 0000:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 1 | BDF: 0001:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 2 | BDF: 0002:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 3 | BDF: 0003:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX all | Selects all devices -U, --cpu CPU [CPU ...] Select a CPU ID from the possible choices: ID: 0 @@ -162,7 +162,7 @@ Static Arguments: SYS, DF, DCEF, SOC, MEM, VCLK0, VCLK1, DCLK0, DCLK1, ALL -p, --partition Partition information -l, --limit All limit metric values (i.e. power and thermal limits) - -P, --policy The available DPM policy + -P, --soc-pstate The available soc pstate policy -x, --xgmi-plpd The available XGMI per-link power down policy -u, --numa All numa node information @@ -193,10 +193,10 @@ If no GPU is specified, return firmware information for all GPUs on the system. Firmware Arguments: -h, --help show this help message and exit -g, --gpu GPU [GPU ...] Select a GPU ID, BDF, or UUID from the possible choices: - ID: 0 | BDF: 0000:01:00.0 | UUID: 7eff74a0-0000-1000-808f-7e20764e2714 - ID: 1 | BDF: 0001:01:00.0 | UUID: b6ff74a0-0000-1000-80ae-7c8cefe1f084 - ID: 2 | BDF: 0002:01:00.0 | UUID: 36ff74a0-0000-1000-8071-25d815189854 - ID: 3 | BDF: 0003:01:00.0 | UUID: f4ff74a0-0000-1000-80c4-4c2be5e66537 + ID: 0 | BDF: 0000:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 1 | BDF: 0001:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 2 | BDF: 0002:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 3 | BDF: 0003:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX all | Selects all devices -U, --cpu CPU [CPU ...] Select a CPU ID from the possible choices: ID: 0 @@ -233,10 +233,10 @@ If no GPU is specified, return bad page information for all GPUs on the system. Bad Pages Arguments: -h, --help show this help message and exit -g, --gpu GPU [GPU ...] Select a GPU ID, BDF, or UUID from the possible choices: - ID: 0 | BDF: 0000:01:00.0 | UUID: 7eff74a0-0000-1000-808f-7e20764e2714 - ID: 1 | BDF: 0001:01:00.0 | UUID: b6ff74a0-0000-1000-80ae-7c8cefe1f084 - ID: 2 | BDF: 0002:01:00.0 | UUID: 36ff74a0-0000-1000-8071-25d815189854 - ID: 3 | BDF: 0003:01:00.0 | UUID: f4ff74a0-0000-1000-80c4-4c2be5e66537 + ID: 0 | BDF: 0000:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 1 | BDF: 0001:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 2 | BDF: 0002:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 3 | BDF: 0003:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX all | Selects all devices -U, --cpu CPU [CPU ...] Select a CPU ID from the possible choices: ID: 0 @@ -286,10 +286,10 @@ If no metric argument is provided, all metric information will be displayed. Metric arguments: -h, --help show this help message and exit -g, --gpu GPU [GPU ...] Select a GPU ID, BDF, or UUID from the possible choices: - ID: 0 | BDF: 0000:01:00.0 | UUID: 7eff74a0-0000-1000-808f-7e20764e2714 - ID: 1 | BDF: 0001:01:00.0 | UUID: b6ff74a0-0000-1000-80ae-7c8cefe1f084 - ID: 2 | BDF: 0002:01:00.0 | UUID: 36ff74a0-0000-1000-8071-25d815189854 - ID: 3 | BDF: 0003:01:00.0 | UUID: f4ff74a0-0000-1000-80c4-4c2be5e66537 + ID: 0 | BDF: 0000:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 1 | BDF: 0001:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 2 | BDF: 0002:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 3 | BDF: 0003:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX all | Selects all devices -U, --cpu CPU [CPU ...] Select a CPU ID from the possible choices: ID: 0 @@ -313,7 +313,7 @@ Metric arguments: -k, --ecc-blocks Number of ECC errors per block -f, --fan Current fan speed -C, --voltage-curve Display voltage curve - -o, --overdrive Current GPU clock overdrive level + -o, --overdrive Current GPU clock overdrive and GPU memory clock overdrive level -l, --perf-level Current DPM performance level -x, --xgmi-err XGMI error information since last read -E, --energy Amount of energy consumed @@ -325,17 +325,17 @@ CPU Arguments: --cpu-freq-metrics Displays currentFclkMemclk frequencies and cclk frequency limit --cpu-c0-res Displays C0 residency --cpu-lclk-dpm-level NBIOID Displays lclk dpm level range. Requires socket ID and NBOID as inputs - --cpu-pwr-svi-telemetry-rails Displays svi based telemetry for all rails - --cpu-io-bandwidth IO_BW LINKID_NAME Displays current IO bandwidth for the selected CPU. - input parameters are bandwidth type(1) and link ID encodings + --cpu-pwr-svi-telemetry-rails Displays svi based telemetry for all rails + --cpu-io-bandwidth IO_BW LINKID_NAME Displays current IO bandwidth for the selected CPU. + input parameters are bandwidth type(1) and link ID encodings i.e. P2, P3, G0 - G7 - --cpu-xgmi-bandwidth XGMI_BW LINKID_NAME Displays current XGMI bandwidth for the selected CPU - input parameters are bandwidth type(1,2,4) and link ID encodings + --cpu-xgmi-bandwidth XGMI_BW LINKID_NAME Displays current XGMI bandwidth for the selected CPU + input parameters are bandwidth type(1,2,4) and link ID encodings i.e. P2, P3, G0 - G7 --cpu-metrics-ver Displays metrics table version --cpu-metrics-table Displays metric table --cpu-socket-energy Displays socket energy for the selected CPU socket - --cpu-ddr-bandwidth Displays per socket max ddr bw, current utilized bw, + --cpu-ddr-bandwidth Displays per socket max ddr bw, current utilized bw, and current utilized ddr bw in percentage --cpu-temp Displays cpu socket temperature --cpu-dimm-temp-range-rate DIMM_ADDR Displays dimm temperature range and refresh rate @@ -373,10 +373,10 @@ If no process argument is provided, all process information will be displayed. Process arguments: -h, --help show this help message and exit -g, --gpu GPU [GPU ...] Select a GPU ID, BDF, or UUID from the possible choices: - ID: 0 | BDF: 0000:01:00.0 | UUID: 7eff74a0-0000-1000-808f-7e20764e2714 - ID: 1 | BDF: 0001:01:00.0 | UUID: b6ff74a0-0000-1000-80ae-7c8cefe1f084 - ID: 2 | BDF: 0002:01:00.0 | UUID: 36ff74a0-0000-1000-8071-25d815189854 - ID: 3 | BDF: 0003:01:00.0 | UUID: f4ff74a0-0000-1000-80c4-4c2be5e66537 + ID: 0 | BDF: 0000:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 1 | BDF: 0001:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 2 | BDF: 0002:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 3 | BDF: 0003:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX all | Selects all devices -U, --cpu CPU [CPU ...] Select a CPU ID from the possible choices: ID: 0 @@ -393,7 +393,7 @@ Process arguments: -G, --general pid, process name, memory usage -e, --engine All engine usages -p, --pid PID Gets all process information about the specified process based on Process ID - -n, --name NAME Gets all process information about the specified process based on Process Name. + -n, --name NAME Gets all process information about the specified process based on Process Name. If multiple processes have the same name, information is returned for all of them. Command Modifiers: @@ -419,10 +419,10 @@ If no GPU is specified, returns event information for all GPUs on the system. Event Arguments: -h, --help show this help message and exit -g, --gpu GPU [GPU ...] Select a GPU ID, BDF, or UUID from the possible choices: - ID: 0 | BDF: 0000:01:00.0 | UUID: 7eff74a0-0000-1000-808f-7e20764e2714 - ID: 1 | BDF: 0001:01:00.0 | UUID: b6ff74a0-0000-1000-80ae-7c8cefe1f084 - ID: 2 | BDF: 0002:01:00.0 | UUID: 36ff74a0-0000-1000-8071-25d815189854 - ID: 3 | BDF: 0003:01:00.0 | UUID: f4ff74a0-0000-1000-80c4-4c2be5e66537 + ID: 0 | BDF: 0000:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 1 | BDF: 0001:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 2 | BDF: 0002:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 3 | BDF: 0003:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX all | Selects all devices -U, --cpu CPU [CPU ...] Select a CPU ID from the possible choices: ID: 0 @@ -459,10 +459,10 @@ If no topology argument is provided, all topology information will be displayed. Topology arguments: -h, --help show this help message and exit -g, --gpu GPU [GPU ...] Select a GPU ID, BDF, or UUID from the possible choices: - ID: 0 | BDF: 0000:01:00.0 | UUID: 7eff74a0-0000-1000-808f-7e20764e2714 - ID: 1 | BDF: 0001:01:00.0 | UUID: b6ff74a0-0000-1000-80ae-7c8cefe1f084 - ID: 2 | BDF: 0002:01:00.0 | UUID: 36ff74a0-0000-1000-8071-25d815189854 - ID: 3 | BDF: 0003:01:00.0 | UUID: f4ff74a0-0000-1000-80c4-4c2be5e66537 + ID: 0 | BDF: 0000:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 1 | BDF: 0001:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 2 | BDF: 0002:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 3 | BDF: 0003:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX all | Selects all devices -U, --cpu CPU [CPU ...] Select a CPU ID from the possible choices: ID: 0 @@ -515,60 +515,66 @@ A set argument must be provided; Multiple set arguments are accepted Set Arguments: -h, --help show this help message and exit -g, --gpu GPU [GPU ...] Select a GPU ID, BDF, or UUID from the possible choices: - ID: 0 | BDF: 0000:01:00.0 | UUID: 7eff74a0-0000-1000-808f-7e20764e2714 - ID: 1 | BDF: 0001:01:00.0 | UUID: b6ff74a0-0000-1000-80ae-7c8cefe1f084 - ID: 2 | BDF: 0002:01:00.0 | UUID: 36ff74a0-0000-1000-8071-25d815189854 - ID: 3 | BDF: 0003:01:00.0 | UUID: f4ff74a0-0000-1000-80c4-4c2be5e66537 + ID: 0 | BDF: 0000:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 1 | BDF: 0001:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 2 | BDF: 0002:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 3 | BDF: 0003:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX all | Selects all devices - -U, --cpu CPU [CPU ...] Select a CPU ID from the possible choices: - ID: 0 - ID: 1 - ID: 2 - ID: 3 - all | Selects all devices - -O, --core CORE [CORE ...] Select a Core ID from the possible choices: - ID: 0 - 95 - all | Selects all devices - -f, --fan % Set GPU fan speed (0-255 or 0-100%) - -l, --perf-level LEVEL Set performance level - -P, --profile SETPROFILE Set power profile level (#) or a quoted string of custom profile attributes - -d, --perf-determinism SCLKMAX Set GPU clock frequency limit and performance level to determinism to get minimal performance variation - -C, --compute-partition PARTITION Set one of the following the compute partition modes: - CPX, SPX, DPX, TPX, QPX - -M, --memory-partition PARTITION Set one of the following the memory partition modes: - NPS1, NPS2, NPS4, NPS8 - -o, --power-cap WATTS Set power capacity limit - -p, --soc-pstate POLICY_ID Set the GPU soc pstate policy using policy id - -x, --xgmi-plpd POLICY_ID Set the GPU XGMI per-link power down policy using policy id - -c, --clk-level CLK_TYPE [PERF_LEVELS ...] Set the sclk (aka gfxclk), mclk, fclk, pcie, or socclk frequency performance level. - Can take range of acceptable levels. - -L, --clk-limit CLK_TYPE LIM_TYPE VALUE Sets the sclk (aka gfxclk) or mclk minimum and maximum frequencies - amd-smi set -L (sclk | mclk) (min | max) value - -R, --process-isolation STATUS Enable or disable the GPU process isolation: - 0 for disable and 1 for enable. + -U, --cpu CPU [CPU ...] Select a CPU ID from the possible choices: + ID: 0 + ID: 1 + ID: 2 + ID: 3 + all | Selects all devices + -O, --core CORE [CORE ...] Select a Core ID from the possible choices: + ID: 0 - 95 + all | Selects all devices + -f, --fan % Set GPU fan speed (0-255 or 0-100%) + -l, --perf-level LEVEL Set one of the following performance levels: + AUTO, LOW, HIGH, MANUAL, STABLE_STD, STABLE_PEAK, STABLE_MIN_MCLK, STABLE_MIN_SCLK, DETERMINISM + -P, --profile SETPROFILE Set power profile level (#) or choose one of available profiles: + CUSTOM_MASK, VIDEO_MASK, POWER_SAVING_MASK, COMPUTE_MASK, VR_MASK, THREE_D_FULL_SCR_MASK, BOOTUP_DEFAULT + -d, --perf-determinism SCLKMAX Set performance determinism and select one of the corresponding performance levels: + AUTO, LOW, HIGH, MANUAL, STABLE_STD, STABLE_PEAK, STABLE_MIN_MCLK, STABLE_MIN_SCLK, DETERMINISM + -C, --compute-partition or Set one of the following the accelerator type or profile index: + SPX, TPX, CPX, 0, 1, 2. + Use `sudo amd-smi partition --accelerator` to find acceptable values. + -M, --memory-partition PARTITION Set one of the following the memory partition modes: + NPS1, NPS2, NPS4, NPS8 + -o, --power-cap WATTS Set power capacity limit: + min cap: 0 W, max cap: 550 W + -p, --soc-pstate POLICY_ID Set the GPU soc pstate policy using policy id, an integer. Valid id's include: + N/A + -x, --xgmi-plpd POLICY_ID Set the GPU XGMI per-link power down policy using policy id, an integer. Valid id's include: + N/A + -c, --clk-level CLK_TYPE [PERF_LEVELS ...] Set a number of sclk (aka gfxclk), mclk, fclk, pcie, or socclk frequency performance levels. + Use `amd-smi static --clock` to find acceptable levels. + -L, --clk-limit CLK_TYPE LIM_TYPE VALUE Sets the sclk (aka gfxclk) or mclk minimum and maximum frequencies. + ex: amd-smi set -L (sclk | mclk) (min | max) value + -R, --process-isolation STATUS Enable or disable the GPU process isolation on a per partition basis: 0 for disable and 1 for enable. CPU Arguments: - --cpu-pwr-limit PWR_LIMIT Set power limit for the given socket. Input parameter is power limit value. - --cpu-xgmi-link-width MIN_WIDTH MAX_WIDTH Set max and Min linkwidth. Input parameters are min and max link width values - --cpu-lclk-dpm-level NBIOID MIN_DPM MAX_DPM Sets the max and min dpm level on a given NBIO. - Input parameters are die_index, min dpm, max dpm. - --cpu-pwr-eff-mode MODE Sets the power efficency mode policy. Input parameter is mode. - --cpu-gmi3-link-width MIN_LW MAX_LW Sets max and min gmi3 link width range - --cpu-pcie-link-rate LINK_RATE Sets pcie link rate - --cpu-df-pstate-range MAX_PSTATE MIN_PSTATE Sets max and min df-pstates - --cpu-enable-apb Enables the DF p-state performance boost algorithm - --cpu-disable-apb DF_PSTATE Disables the DF p-state performance boost algorithm. Input parameter is DFPstate (0-3) - --soc-boost-limit BOOST_LIMIT Sets the boost limit for the given socket. Input parameter is socket BOOST_LIMIT value + --cpu-pwr-limit PWR_LIMIT Set power limit for the given socket. Input parameter is power limit value. + --cpu-xgmi-link-width MIN_WIDTH MAX_WIDTH Set max and Min linkwidth. Input parameters are min and max link width values + --cpu-lclk-dpm-level NBIOID MIN_DPM MAX_DPM Sets the max and min dpm level on a given NBIO. + Input parameters are die_index, min dpm, max dpm. + --cpu-pwr-eff-mode MODE Sets the power efficency mode policy. Input parameter is mode. + --cpu-gmi3-link-width MIN_LW MAX_LW Sets max and min gmi3 link width range + --cpu-pcie-link-rate LINK_RATE Sets pcie link rate + --cpu-df-pstate-range MAX_PSTATE MIN_PSTATE Sets max and min df-pstates + --cpu-enable-apb Enables the DF p-state performance boost algorithm + --cpu-disable-apb DF_PSTATE Disables the DF p-state performance boost algorithm. Input parameter is DFPstate (0-3) + --soc-boost-limit BOOST_LIMIT Sets the boost limit for the given socket. Input parameter is socket BOOST_LIMIT value CPU Core Arguments: - --core-boost-limit BOOST_LIMIT Sets the boost limit for the given core. Input parameter is core BOOST_LIMIT value + --core-boost-limit BOOST_LIMIT Sets the boost limit for the given core. Input parameter is core BOOST_LIMIT value Command Modifiers: - --json Displays output in JSON format (human readable by default). - --csv Displays output in CSV format (human readable by default). - --file FILE Saves output into a file on the provided path (stdout by default). - --loglevel LEVEL Set the logging level from the possible choices: - DEBUG, INFO, WARNING, ERROR, CRITICAL + --json Displays output in JSON format (human readable by default). + --csv Displays output in CSV format (human readable by default). + --file FILE Saves output into a file on the provided path (stdout by default). + --loglevel LEVEL Set the logging level from the possible choices: + DEBUG, INFO, WARNING, ERROR, CRITICAL ``` (cmd-reset)= @@ -588,10 +594,10 @@ A reset argument must be provided; Multiple reset arguments are accepted Reset Arguments: -h, --help show this help message and exit -g, --gpu GPU [GPU ...] Select a GPU ID, BDF, or UUID from the possible choices: - ID: 0 | BDF: 0000:01:00.0 | UUID: 7eff74a0-0000-1000-808f-7e20764e2714 - ID: 1 | BDF: 0001:01:00.0 | UUID: b6ff74a0-0000-1000-80ae-7c8cefe1f084 - ID: 2 | BDF: 0002:01:00.0 | UUID: 36ff74a0-0000-1000-8071-25d815189854 - ID: 3 | BDF: 0003:01:00.0 | UUID: f4ff74a0-0000-1000-80c4-4c2be5e66537 + ID: 0 | BDF: 0000:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 1 | BDF: 0001:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 2 | BDF: 0002:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 3 | BDF: 0003:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX all | Selects all devices -U, --cpu CPU [CPU ...] Select a CPU ID from the possible choices: ID: 0 @@ -609,7 +615,7 @@ Reset Arguments: -x, --xgmierr Reset XGMI error counts -d, --perf-determinism Disable performance determinism -o, --power-cap Reset power capacity limit to max capable - -l, --clean-local-data Clean up the local data in the LDS/GPRs on a per partition basis + -l, --clean-local-data Clean up local data in LDS/GPRs on a per partition basis Command Modifiers: --json Displays output in JSON format (human readable by default). @@ -638,10 +644,10 @@ Use the watch arguments to run continuously. Monitor Arguments: -h, --help show this help message and exit -g, --gpu GPU [GPU ...] Select a GPU ID, BDF, or UUID from the possible choices: - ID: 0 | BDF: 0000:01:00.0 | UUID: 7eff74a0-0000-1000-808f-7e20764e2714 - ID: 1 | BDF: 0001:01:00.0 | UUID: b6ff74a0-0000-1000-80ae-7c8cefe1f084 - ID: 2 | BDF: 0002:01:00.0 | UUID: 36ff74a0-0000-1000-8071-25d815189854 - ID: 3 | BDF: 0003:01:00.0 | UUID: f4ff74a0-0000-1000-80c4-4c2be5e66537 + ID: 0 | BDF: 0000:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 1 | BDF: 0001:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 2 | BDF: 0002:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 3 | BDF: 0003:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX all | Selects all devices -U, --cpu CPU [CPU ...] Select a CPU ID from the possible choices: ID: 0 @@ -691,10 +697,10 @@ If no xgmi argument is provided, all xgmi information will be displayed. XGMI arguments: -h, --help show this help message and exit -g, --gpu GPU [GPU ...] Select a GPU ID, BDF, or UUID from the possible choices: - ID: 0 | BDF: 0000:01:00.0 | UUID: 7eff74a0-0000-1000-808f-7e20764e2714 - ID: 1 | BDF: 0001:01:00.0 | UUID: b6ff74a0-0000-1000-80ae-7c8cefe1f084 - ID: 2 | BDF: 0002:01:00.0 | UUID: 36ff74a0-0000-1000-8071-25d815189854 - ID: 3 | BDF: 0003:01:00.0 | UUID: f4ff74a0-0000-1000-80c4-4c2be5e66537 + ID: 0 | BDF: 0000:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 1 | BDF: 0001:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 2 | BDF: 0002:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX + ID: 3 | BDF: 0003:01:00.0 | UUID: XXXXXXXX-XXXX-XXXX-XXXX-XXXXXXXXXXXX all | Selects all devices -U, --cpu CPU [CPU ...] Select a CPU ID from the possible choices: ID: 0 @@ -706,6 +712,7 @@ XGMI arguments: ID: 0 - 95 all | Selects all devices -m, --metric Metric XGMI information + -l, --link-status XGMI Link Status information Command Modifiers: --json Displays output in JSON format (human readable by default). @@ -732,14 +739,14 @@ CPU: 0 GPU: 0 ASIC: - MARKET_NAME: MI300A + MARKET_NAME: AMD Instinct MI300A VENDOR_ID: 0x1002 VENDOR_NAME: Advanced Micro Devices Inc. [AMD/ATI] SUBVENDOR_ID: 0x1002 DEVICE_ID: 0x74a0 SUBSYSTEM_ID: 0x74a0 REV_ID: 0x00 - ASIC_SERIAL: 0x7E8F7E20764E2714 + ASIC_SERIAL: 0xXXXXXXXXXXXXXX OAM_ID: 0 NUM_COMPUTE_UNITS: 228 TARGET_GRAPHICS_VERSION: gfx942 @@ -766,7 +773,7 @@ GPU: 0 SHUTDOWN_VRAM_TEMPERATURE: 115 °C DRIVER: NAME: amdgpu - VERSION: 6.9.0-rc5+ + VERSION: 6.10.10 BOARD: MODEL_NUMBER: N/A PRODUCT_SERIAL: N/A @@ -774,7 +781,7 @@ GPU: 0 PRODUCT_NAME: Aqua Vanjaram [Instinct MI300A] MANUFACTURER_NAME: Advanced Micro Devices, Inc. [AMD/ATI] RAS: - EEPROM_VERSION: 0x0 + EEPROM_VERSION: 0x21000 PARITY_SCHEMA: DISABLED SINGLE_BIT_SCHEMA: DISABLED DOUBLE_BIT_SCHEMA: DISABLED @@ -803,37 +810,18 @@ GPU: 0 COMPUTE_PARTITION: SPX MEMORY_PARTITION: NPS1 PARTITION_ID: 0 - SOC_PSTATE: - NUM_SUPPORTED: 4 - CURRENT_ID: 1 - POLICIES: - POLICY_ID: 0 - POLICY_DESCRIPTION: pstate_default - POLICY_ID: 1 - POLICY_DESCRIPTION: soc_pstate_0 - POLICY_ID: 2 - POLICY_DESCRIPTION: soc_pstate_1 - POLICY_ID: 3 - POLICY_DESCRIPTION: soc_pstate_2 - XGMI_PLPD: - NUM_SUPPORTED: 3 - CURRENT_ID: 1 - PLPDS: - POLICY_ID: 0 - POLICY_DESCRIPTION: plpd_disallow - POLICY_ID: 1 - POLICY_DESCRIPTION: plpd_default - POLICY_ID: 2 - POLICY_DESCRIPTION: plpd_optimized - PROCESS_ISOLATION: N/A + SOC_PSTATE: N/A + XGMI_PLPD: N/A + PROCESS_ISOLATION: Disabled NUMA: NODE: 0 AFFINITY: 0 VRAM: TYPE: HBM - VENDOR: N/A - SIZE: 64289 MB + VENDOR: UNKNOWN + SIZE: 96434 MB BIT_WIDTH: 8192 + MAX_BANDWIDTH: N/A CACHE_INFO: CACHE_0: CACHE_PROPERTIES: DATA_CACHE, SIMD_CACHE @@ -861,33 +849,48 @@ GPU: 0 NUM_CACHE_INSTANCE: 1 CLOCK: SYS: - CURRENT LEVEL: 2 + CURRENT LEVEL: 1 FREQUENCY_LEVELS: - 0: 300 MHz - 1: 904 MHz - 2: 1165 MHz - 3: 1360 MHz - 4: 1440 MHz - 5: 1544 MHz - 6: 1627 MHz - 7: 1720 MHz - 8: 1800 MHz - DF: - CURRENT LEVEL: 0 - FREQUENCY_LEVELS: - 0: 1400 MHz - DCEF: N/A - SOC: - CURRENT LEVEL: 0 - FREQUENCY_LEVELS: - 0: 302 MHz + LEVEL 0: 700 MHz + LEVEL 1: 903 MHz + LEVEL 2: 900 MHz MEM: CURRENT LEVEL: 0 FREQUENCY_LEVELS: - 0: 167 MHz - VCLK0: N/A - VCLK1: N/A - DCLK1: N/A - DCLK0: N/A + LEVEL 0: 900 MHz + LEVEL 1: 1100 MHz + LEVEL 2: 1200 MHz + LEVEL 3: 1300 MHz + DF: + CURRENT LEVEL: 0 + FREQUENCY_LEVELS: + LEVEL 0: 1200 MHz + LEVEL 1: 1600 MHz + LEVEL 2: 1900 MHz + LEVEL 3: 2000 MHz + SOC: + CURRENT LEVEL: 0 + FREQUENCY_LEVELS: + LEVEL 0: 26 MHz + LEVEL 1: 800 MHz + LEVEL 2: 1000 MHz + LEVEL 3: 1143 MHz + DCEF: N/A + VCLK0: + CURRENT LEVEL: 0 + FREQUENCY_LEVELS: + LEVEL 0: 29 MHz + VCLK1: + CURRENT LEVEL: 0 + FREQUENCY_LEVELS: + LEVEL 0: 29 MHz + DCLK0: + CURRENT LEVEL: 0 + FREQUENCY_LEVELS: + LEVEL 0: 22 MHz + DCLK1: + CURRENT LEVEL: 0 + FREQUENCY_LEVELS: + LEVEL 0: 22 MHz ... ```