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

Query UBB/OAM temperature API (#581)

Browse Source 
Add support to Query UBB/OAM temperature.
* Updated Python API with new temperature metrics enum

---------

Co-authored-by: Bill Liu <shuzhliu@amd.com>
Co-authored-by: gabrpham_amdeng <Gabriel.Pham@amd.com>
This commit is contained in:
Liu, Shuzhou (Bill)
2025-08-05 21:37:45 -04:00
committed by GitHub
parent 753a5ea326
commit abd3c02a3c
12 changed files with 964 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/amd_smi/amdsmi.h
+60 -1
View File
@@ -464,7 +464,66 @@ typedef enum {
AMDSMI_TEMPERATURE_TYPE_HBM_2, //!< High Bandwidth 2 temperature per stack
AMDSMI_TEMPERATURE_TYPE_HBM_3, //!< High Bandwidth 3 temperature per stack
AMDSMI_TEMPERATURE_TYPE_PLX, //!< PCIe switch temperature
AMDSMI_TEMPERATURE_TYPE__MAX = AMDSMI_TEMPERATURE_TYPE_PLX
// GPU Board Node temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_NODE_FIRST = 100,
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_NODE_RETIMER_X
= AMDSMI_TEMPERATURE_TYPE_GPUBOARD_NODE_FIRST, //!< Retimer X temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_NODE_OAM_X_IBC, //!< OAM X IBC temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_NODE_OAM_X_IBC_2, //!< OAM X IBC 2 temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_NODE_OAM_X_VDD18_VR, //!< OAM X VDD 1.8V voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_NODE_OAM_X_04_HBM_B_VR, //!< OAM X 0.4V HBM B voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_NODE_OAM_X_04_HBM_D_VR, //!< OAM X 0.4V HBM D voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_NODE_LAST = 149,
// GPU Board VR (Voltage Regulator) temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_VR_FIRST = 150,
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_VDDCR_VDD0
= AMDSMI_TEMPERATURE_TYPE_GPUBOARD_VR_FIRST, //!< VDDCR VDD0 voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_VDDCR_VDD1, //!< VDDCR VDD1 voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_VDDCR_VDD2, //!< VDDCR VDD2 voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_VDDCR_VDD3, //!< VDDCR VDD3 voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_VDDCR_SOC_A, //!< VDDCR SOC A voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_VDDCR_SOC_C, //!< VDDCR SOC C voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_VDDCR_SOCIO_A, //!< VDDCR SOCIO A voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_VDDCR_SOCIO_C, //!< VDDCR SOCIO C voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_VDD_085_HBM, //!< VDD 0.85V HBM voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_VDDCR_11_HBM_B, //!< VDDCR 1.1V HBM B voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_VDDCR_11_HBM_D, //!< VDDCR 1.1V HBM D voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_VDD_USR, //!< VDD USR voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_VDDIO_11_E32, //!< VDDIO 1.1V E32 voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_GPUBOARD_VR_LAST = 199,
// Baseboard System temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_FIRST = 200,
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_UBB_FPGA
= AMDSMI_TEMPERATURE_TYPE_BASEBOARD_FIRST, //!< UBB FPGA temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_UBB_FRONT, //!< UBB front temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_UBB_BACK, //!< UBB back temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_UBB_OAM7, //!< UBB OAM7 temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_UBB_IBC, //!< UBB IBC temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_UBB_UFPGA, //!< UBB UFPGA temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_UBB_OAM1, //!< UBB OAM1 temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_OAM_0_1_HSC, //!< OAM 0-1 HSC temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_OAM_2_3_HSC, //!< OAM 2-3 HSC temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_OAM_4_5_HSC, //!< OAM 4-5 HSC temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_OAM_6_7_HSC, //!< OAM 6-7 HSC temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_UBB_FPGA_0V72_VR, //!< UBB FPGA 0.72V voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_UBB_FPGA_3V3_VR, //!< UBB FPGA 3.3V voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_RETIMER_0_1_2_3_1V2_VR, //!< Retimer 0-1-2-3 1.2V voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_RETIMER_4_5_6_7_1V2_VR, //!< Retimer 4-5-6-7 1.2V voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_RETIMER_0_1_0V9_VR, //!< Retimer 0-1 0.9V voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_RETIMER_4_5_0V9_VR, //!< Retimer 4-5 0.9V voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_RETIMER_2_3_0V9_VR, //!< Retimer 2-3 0.9V voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_RETIMER_6_7_0V9_VR, //!< Retimer 6-7 0.9V voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_OAM_0_1_2_3_3V3_VR, //!< OAM 0-1-2-3 3.3V voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_OAM_4_5_6_7_3V3_VR, //!< OAM 4-5-6-7 3.3V voltage regulator temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_IBC_HSC, //!< IBC HSC temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_IBC, //!< IBC temperature
AMDSMI_TEMPERATURE_TYPE_BASEBOARD_LAST = 249,
AMDSMI_TEMPERATURE_TYPE__MAX = AMDSMI_TEMPERATURE_TYPE_BASEBOARD_LAST, //!< Maximum per GPU temperature type
} amdsmi_temperature_type_t;
/**