無法讓 AMDGPU-Pro 或 ROCm 在 20.04 上偵測設備

無法讓 AMDGPU-Pro 或 ROCm 在 20.04 上偵測設備

我已經嘗試了一周,但沒有成功讓 OpenGL 在 Asus x570-p 主機板上與我的 Ryzen 3 3200g APU 配合使用。我嘗試使用找到的最新 20.04 AMDGPU-Pro 驅動程式進行全新安裝這裡以及全新安裝和安裝 ROCm 3.7 驅動程式這裡,似乎模組正在加載,但我只是不知道如何讓 OpenGL 檢測設備。

AMDGPU-Pro 安裝中的 clinfo:

frnt@mxm-2:~$ /opt/amdgpu-pro/bin/clinfo
Number of platforms:                 1
  Platform Profile:              FULL_PROFILE
  Platform Version:              OpenCL 2.1 AMD-APP (3110.6)
  Platform Name:                 AMD Accelerated Parallel Processing
  Platform Vendor:               Advanced Micro Devices, Inc.
  Platform Extensions:               cl_khr_icd cl_amd_event_callback cl_amd_offline_devices 


  Platform Name:                 AMD Accelerated Parallel Processing
ERROR: clGetDeviceIDs(-1)

來自 ROCm 安裝的 clinfo:

frnt@mxm-2:~$ /opt/rocm/opencl/bin/clinfo
Number of platforms:                 1
  Platform Profile:              FULL_PROFILE
  Platform Version:              OpenCL 2.1 AMD-APP (3110.6)
  Platform Name:                 AMD Accelerated Parallel Processing
  Platform Vendor:               Advanced Micro Devices, Inc.
  Platform Extensions:               cl_khr_icd cl_amd_event_callback cl_amd_offline_devices 


  Platform Name:                 AMD Accelerated Parallel Processing
Number of devices:               0

羅克姆資訊:

frnt@mxm-2:~$ /opt/rocm/bin/rocminfo
ROCk module is loaded
Unable to open /dev/kfd read-write: Bad address
strato is member of render group
hsa api call failure at: /src/rocminfo/rocminfo.cc:1142
Call returned HSA_STATUS_ERROR_OUT_OF_RESOURCES: The runtime failed to allocate the necessary resources. This error may also occur when the core runtime library needs to spawn threads or create internal OS-specific events.

其他:

frnt@mxm-2:~$ sudo dmesg | grep -e "amdgpu\|kfd"
[sudo] password for frnt: 
[   10.526983] [drm] amdgpu kernel modesetting enabled.
[   10.526984] [drm] amdgpu version: 5.6.12
[   10.527760] amdgpu: Topology: Add APU node [0x0:0x0]
[   10.533545] amdgpu 0000:09:00.0: remove_conflicting_pci_framebuffers: bar 0: 0xd0000000 -> 0xdfffffff
[   10.533547] amdgpu 0000:09:00.0: remove_conflicting_pci_framebuffers: bar 2: 0xe0000000 -> 0xe01fffff
[   10.533548] amdgpu 0000:09:00.0: remove_conflicting_pci_framebuffers: bar 5: 0xfce00000 -> 0xfce7ffff
[   10.533550] fb0: switching to amdgpudrmfb from EFI VGA
[   10.533640] amdgpu 0000:09:00.0: vgaarb: deactivate vga console
[   10.533681] amdgpu 0000:09:00.0: enabling device (0006 -> 0007)
[   10.533762] amdgpu 0000:09:00.0: amdgpu: Trusted Memory Zone (TMZ) feature disabled as experimental (default)
[   10.534640] amdgpu: ATOM BIOS: 113-PICASSO-117
[   10.534910] amdgpu 0000:09:00.0: amdgpu: VRAM: 2048M 0x000000F400000000 - 0x000000F47FFFFFFF (2048M used)
[   10.534911] amdgpu 0000:09:00.0: amdgpu: GART: 1024M 0x0000000000000000 - 0x000000003FFFFFFF
[   10.534912] amdgpu 0000:09:00.0: amdgpu: AGP: 267419648M 0x000000F800000000 - 0x0000FFFFFFFFFFFF
[   10.539652] [drm] amdgpu: 2048M of VRAM memory ready
[   10.539655] [drm] amdgpu: 13964M of GTT memory ready.
[   10.576252] amdgpu: [powerplay] hwmgr_sw_init smu backed is smu10_smu
[   10.821210] amdgpu 0000:09:00.0: amdgpu: RAS: optional ras ta ucode is not available
[   10.850191] snd_hda_intel 0000:09:00.1: bound 0000:09:00.0 (ops amdgpu_dm_audio_component_bind_ops [amdgpu])
[   10.878632] kfd kfd: amdgpu: Allocated 3969056 bytes on gart
[   10.879374] amdgpu: Topology: Add APU node [0x15d8:0x1002]
[   10.879376] kfd kfd: amdgpu: added device 1002:15d8
[   10.879379] amdgpu 0000:09:00.0: amdgpu: SE 1, SH per SE 1, CU per SH 11, active_cu_number 8
[   10.880386] fbcon: amdgpudrmfb (fb0) is primary device
[   10.880454] amdgpu 0000:09:00.0: fb0: amdgpudrmfb frame buffer device
[   10.913455] amdgpu 0000:09:00.0: amdgpu: ring gfx uses VM inv eng 0 on hub 0
[   10.913458] amdgpu 0000:09:00.0: amdgpu: ring comp_1.0.0 uses VM inv eng 1 on hub 0
[   10.913459] amdgpu 0000:09:00.0: amdgpu: ring comp_1.1.0 uses VM inv eng 4 on hub 0
[   10.913459] amdgpu 0000:09:00.0: amdgpu: ring comp_1.2.0 uses VM inv eng 5 on hub 0
[   10.913460] amdgpu 0000:09:00.0: amdgpu: ring comp_1.3.0 uses VM inv eng 6 on hub 0
[   10.913461] amdgpu 0000:09:00.0: amdgpu: ring comp_1.0.1 uses VM inv eng 7 on hub 0
[   10.913462] amdgpu 0000:09:00.0: amdgpu: ring comp_1.1.1 uses VM inv eng 8 on hub 0
[   10.913463] amdgpu 0000:09:00.0: amdgpu: ring comp_1.2.1 uses VM inv eng 9 on hub 0
[   10.913463] amdgpu 0000:09:00.0: amdgpu: ring comp_1.3.1 uses VM inv eng 10 on hub 0
[   10.913465] amdgpu 0000:09:00.0: amdgpu: ring kiq_2.1.0 uses VM inv eng 11 on hub 0
[   10.913466] amdgpu 0000:09:00.0: amdgpu: ring sdma0 uses VM inv eng 0 on hub 1
[   10.913467] amdgpu 0000:09:00.0: amdgpu: ring vcn_dec uses VM inv eng 1 on hub 1
[   10.913468] amdgpu 0000:09:00.0: amdgpu: ring vcn_enc0 uses VM inv eng 4 on hub 1
[   10.913468] amdgpu 0000:09:00.0: amdgpu: ring vcn_enc1 uses VM inv eng 5 on hub 1
[   10.913469] amdgpu 0000:09:00.0: amdgpu: ring jpeg_dec uses VM inv eng 6 on hub 1
[   10.927722] [drm] Initialized amdgpu 3.39.0 20150101 for 0000:09:00.0 on minor 0
[   46.749998] amdgpu: Failure to set tba address. error -1.
[   46.750893] amdgpu: Failure to set tba address. error -1.
[   62.084623] amdgpu: Failure to set tba address. error -1.
[  499.603954] amdgpu: Failure to set tba address. error -1.
[  499.604835] amdgpu: Failure to set tba address. error -1.

相關內容