【当前背景】
代码版本:25.03
MCU固件版本:24.5.9
系统固件版本:7.5.0.5.220
【问题描述】
当前在openUBMC适配300V Pro的NPU卡,适配后显示的信息不全,没有显示内存容量和系统固件版本
300V Pro CSR配置
"PCIeDevice_1": {
"Segment": 1,
"DeviceName": "PCIe Card $ (NPU)",
"DiagnosticFault": 0,
"PredictiveFault": 0,
"FunctionClass": 9,
"LinkSpeedReduced": 0,
"CorrectableError": 0,
"UncorrectableError": 0,
"FatalError": 0,
"Position": "",
"Container": "${Container}",
"GroupPosition": "PCIeDevice_${GroupPosition}",
"DeviceType": 8,
"PCIeDeviceType": "SingleFunction",
"SlotType": "FullLength",
"FunctionProtocol": "PCIe",
"FunctionType": "Physical"
},
"FruData_NPUCard": {
"FruId": 1,
"StorageType": "MCU",
"FruDev": "#/Chip_Dmini_Elabel",
"FruName":"<=/PCIeCard_1.Name"
},
"NPUCard_1":{
"Name": "<=/PCIeCard_1.Name",
"CardDescription": "<=/PCIeCard_1.Description",
"DeviceName": "<=/PCIeDevice_1.DeviceName",
"RefChip":"#/Chip_Dmini",
"RefEeprom":"#/Chip_Dmini_Elabel",
"RefFrudata": "#/FruData_NPUCard",
"Model": "Atlas_300I_Pro",
"SlotNumber": "${Slot}",
"PcbVersion": ".A",
"BoardID": 171,
"FirmwareVersion": "N/A",
"CardPartNumber": "03028DFH",
"SerialNumber":"<=/FruData_NPUCard.BoardSerialNumber"
},
"Fru_NPUCard": {
"PcbVersion": ".A",
"FruId": 1,
"PowerState": 1,
"FruName": "<=/PCIeCard_1.Name",
"Health": 0,
"EepStatus": 1,
"Type": 8,
"FruDataId": "#/FruData_NPUCard"
},
"PCIeCard_1": {
"DeviceName": "<=/PCIeDevice_1.DeviceName",
"SlotID": "<=/PCIeDevice_1.SlotID",
"NodeID": "<=/PCIeDevice_1.SlotID |> string.format('PCIeCard%s',$1)",
"Health": "<=/Component_PCIeCard.Health",
"Name": "#/NPUCard_1.BoardID |> expr( $1==182 ? 'Atlas 300V Video Analysis Card' : $1==175 ? 'Atlas 300V Pro Video Analysis Card' : 'Atlas 300I Pro Inference Card')",
"BoardName": "<=/FruData_NPUCard.BoardProductName;<=/FruData_NPUCard.BoardProductName |> string.cmp($1, '') |> expr($1 ? 'IT21PDDA' : $2)",
"Description": "#/PCIeCard_1.Name |> string.format('%s PCI-E 1*16x (HHHL)', $1)",
"FunctionClass": 9,
"VendorID": 6629,
"DeviceID": 54528,
"SubVendorID": 512,
"SubDeviceID": 256,
"Position": "<=/PCIeDevice_1.Position",
"LaneOwner": "<=/PCIeDevice_1.SocketID",
"FirmwareVersion": "#/NPUCard_1.FirmwareVersion",
"Manufacturer": "Huawei",
"PartNumber": "03028DFH",
"MaxFrameLen": 64,
"LinkSpeed": "N/A",
"LinkSpeedCapability": "N/A",
"PcbVersion": "#/NPUCard_1.PcbVersion",
"BoardID": "#/NPUCard_1.BoardID",
"DevBus": "<=/PCIeDevice_1.DevBus",
"DevDevice": "<=/PCIeDevice_1.DevDevice",
"SerialNumber": "<=/FruData_NPUCard.BoardSerialNumber",
"DevFunction": "<=/PCIeDevice_1.DevFunction"
},
在ibmc v2版本上进行交叉验证发现这些信息可以正常显示
使用300I Duo的卡适配openUBMC后,系统版本和内存容量可以正常显示
300I Duo CSR配置文件
"PCIeDevice_1": {
"Segment": 1,
"DeviceName": "PCIe Card $ (Atlas 300I Duo)",
"DiagnosticFault": 0,
"PredictiveFault": 0,
"FunctionClass": 9,
"LinkSpeedReduced": 0,
"CorrectableError": 0,
"UncorrectableError": 0,
"FatalError": 0,
"Position": "",
"Container": "${Container}",
"GroupPosition": "PCIeDevice_${GroupPosition}",
"DeviceType": 8,
"PCIeDeviceType": "SingleFunction",
"SlotType": "FullLength",
"FunctionProtocol": "PCIe",
"FunctionType": "Physical"
},
"FruData_NPUCard": {
"FruId": 1,
"StorageType": "MCU",
"FruDev": "#/Chip_Dmini_Elabel"
},
"Fru_NPUCard": {
"PcbVersion": ".A",
"FruId": 1,
"PowerState": 1,
"FruName": "Atlas 300I Duo",
"Health": 0,
"EepStatus": 1,
"Type": 8,
"FruDataId": "#/FruData_NPUCard"
},
"NPUCard_1":{
"Name": "Atlas 300I Duo Inference Card",
"CardDescription": "Atlas 300I Duo Inference Card PCI-E 1*16x(FHFL)",
"DeviceName": "<=/PCIeDevice_1.DeviceName",
"RefChip":"#/Chip_Dmini",
"RefEeprom":"#/Chip_Dmini_Elabel",
"RefFrudata": "#/FruData_NPUCard",
"Model": "Atlas_300I_Duo",
"SlotNumber": "${Slot}",
"PcbVersion": ".A",
"BoardID": 177,
"FirmwareVersion": "N/A",
"CardPartNumber": "03029WRV",
"SerialNumber":"<=/FruData_NPUCard.BoardSerialNumber"
},
"PCIeCard_1": {
"DeviceName": "<=/PCIeDevice_1.DeviceName",
"SlotID": "<=/PCIeDevice_1.SlotID",
"NodeID": "<=/PCIeDevice_1.SlotID |> string.format('PCIeCard%s',$1)",
"Health": "<=/Component_PCIeCard.Health",
"Name": "Atlas 300I Duo",
"BoardName": "<=/FruData_NPUCard.BoardProductName;<=/FruData_NPUCard.BoardProductName |> string.cmp($1, '') |> expr($1 ? 'IT21PD2E' : $2)",
"Description": "Atlas 300I Duo Inference Card PCI-E 1*16x(FHFL)",
"FunctionClass": 9,
"VendorID": 6629,
"DeviceID": 54528,
"SubVendorID": 512,
"SubDeviceID": 272,
"Position": "<=/PCIeDevice_1.Position",
"LaneOwner": "<=/PCIeDevice_1.SocketID",
"FirmwareVersion": "#/NPUCard_1.FirmwareVersion",
"Manufacturer": "Huawei",
"PartNumber": "03029WRV",
"MaxFrameLen": 32,
"LinkSpeed": "N/A",
"LinkSpeedCapability": "N/A",
"PcbVersion": "#/NPUCard_1.PcbVersion",
"BoardID": "#/NPUCard_1.BoardID",
"DevBus": "<=/PCIeDevice_1.DevBus",
"DevDevice": "<=/PCIeDevice_1.DevDevice",
"SerialNumber": "",
"DevFunction": "<=/PCIeDevice_1.DevFunction"
},
【疑问点】
使用类似的CSR配置文件对两张NPU卡进行适配,为什么300I DUO的卡可以正常显示信息,300V Pro却不能显示系统固件版本和内存容量,300V Pro的卡是否支持显示这两条信息