Skip to content

Adding test target gfx1101 #438

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
geomin12 opened this issue Apr 17, 2025 · 2 comments · May be fixed by #442
Open

Adding test target gfx1101 #438

geomin12 opened this issue Apr 17, 2025 · 2 comments · May be fixed by #442
Assignees

Comments

@geomin12
Copy link
Contributor

No description provided.

@amd-justchen
Copy link
Contributor

amd-justchen commented Apr 17, 2025

Working with Azure / Microsoft / AMD IT to get Quota for Radeon PRO v710 GPU vms (NV24ads_v710) (equivalent to Radeon RX 7700 xt / 7800 xt)

They are in preview so had to fill out a form and work with them.

Also may be able to setup a lab machine with W7900 (gfx1100)

@geomin12 geomin12 moved this from TODO to In Progress in TheRock CI/CD 🪨🚀 Apr 21, 2025
@geomin12 geomin12 self-assigned this Apr 21, 2025
@erman-gurses erman-gurses self-assigned this Apr 22, 2025
@amd-justchen
Copy link
Contributor

Informed by Microsoft Azure Support that as of today the v710 series is now out of preview and are generally available

https://learn.microsoft.com/en-us/azure/virtual-machines/sizes/gpu-accelerated/nvadsv710-v5-series?tabs=sizebasic

Yesterday, we were given quota for v710s in East US, but it would not appear in create virtual machine azure dashboard and with az vm list-skus --output table | grep -i V710

Microsoft Support had to manually enable it in our subscription for East US and they can now be created.

One has been provisioned per https://learn.microsoft.com/en-us/azure/virtual-machines/linux/azure-n-series-amd-gpu-driver-linux-installation-guide .

It looks like the driver is now loading after sudo modprobe amdgpu and enrolling MOK key

sudo dmesg | grep amdgpu 
[   25.120426] [drm] amdgpu kernel modesetting enabled.
[   25.120431] [drm] amdgpu version: 6.12.12
[   25.120636] amdgpu: Virtual CRAT table created for CPU
[   25.120651] amdgpu: Topology: Add CPU node
[   25.124756] amdgpu 0002:00:00.0: enabling device (0000 -> 0002)
[   25.483534] amdgpu 0002:00:00.0: amdgpu: detected ip block number 0 <soc21_common>
[   25.483539] amdgpu 0002:00:00.0: amdgpu: detected ip block number 1 <gmc_v11_0>
[   25.483542] amdgpu 0002:00:00.0: amdgpu: detected ip block number 2 <psp>
[   25.483544] amdgpu 0002:00:00.0: amdgpu: detected ip block number 3 <ih_v6_0>
[   25.483546] amdgpu 0002:00:00.0: amdgpu: detected ip block number 4 <smu>
[   25.483549] amdgpu 0002:00:00.0: amdgpu: detected ip block number 5 <amdgpu_vkms>
[   25.483551] amdgpu 0002:00:00.0: amdgpu: detected ip block number 6 <gfx_v11_0>
[   25.483553] amdgpu 0002:00:00.0: amdgpu: detected ip block number 7 <sdma_v6_0>
[   25.483554] amdgpu 0002:00:00.0: amdgpu: detected ip block number 8 <vcn_v4_0>
[   25.483556] amdgpu 0002:00:00.0: amdgpu: detected ip block number 9 <jpeg_v4_0>
[   25.483558] amdgpu 0002:00:00.0: amdgpu: detected ip block number 10 <mes_v11_0>
[   25.498736] amdgpu 0002:00:00.0: amdgpu: Fetched VBIOS from VRAM BAR
[   25.498741] amdgpu: ATOM BIOS: 113-D7190300-104
[   25.500566] amdgpu 0002:00:00.0: amdgpu: CP RS64 enable
[   25.504683] amdgpu 0002:00:00.0: amdgpu: Trusted Memory Zone (TMZ) feature not supported
[   25.504743] amdgpu 0002:00:00.0: amdgpu: VRAM: 25712M 0x0000008000000000 - 0x0000008646FFFFFF (25712M used)
[   25.504745] amdgpu 0002:00:00.0: amdgpu: GART: 512M 0x00007FFF00000000 - 0x00007FFF1FFFFFFF
[   25.504882] [drm] amdgpu: 25712M of VRAM memory ready
[   25.504884] [drm] amdgpu: 64403M of GTT memory ready.
[   25.687940] amdgpu 0002:00:00.0: amdgpu: smu driver if version = 0x0000003d, smu fw if version = 0x00000040, smu fw program = 0, smu fw version = 0x00505000 (80.80.0)
[   25.687947] amdgpu 0002:00:00.0: amdgpu: SMU driver if version not matched
[   25.713594] amdgpu 0002:00:00.0: amdgpu: SMU is initialized successfully!
[   25.798326] amdgpu: HMM registered 25712MB device memory
[   25.799336] kfd kfd: amdgpu: Allocated 3969056 bytes on gart
[   25.799350] kfd kfd: amdgpu: Total number of KFD nodes to be created: 1
[   25.799411] amdgpu: Virtual CRAT table created for GPU
[   25.799848] amdgpu: Topology: Add dGPU node [0x7461:0x1002]
[   25.799850] kfd kfd: amdgpu: added device 1002:7461
[   25.799874] amdgpu 0002:00:00.0: amdgpu: SE 3, SH per SE 2, CU per SH 10, active_cu_number 54
[   25.799881] amdgpu 0002:00:00.0: amdgpu: ring gfx_0.0.0 uses VM inv eng 0 on hub 0
[   25.799883] amdgpu 0002:00:00.0: amdgpu: ring comp_1.0.0 uses VM inv eng 1 on hub 0
[   25.799884] amdgpu 0002:00:00.0: amdgpu: ring comp_1.1.0 uses VM inv eng 4 on hub 0
[   25.799886] amdgpu 0002:00:00.0: amdgpu: ring sdma0 uses VM inv eng 6 on hub 0
[   25.799888] amdgpu 0002:00:00.0: amdgpu: ring sdma1 uses VM inv eng 7 on hub 0
[   25.799889] amdgpu 0002:00:00.0: amdgpu: ring vcn_unified_0 uses VM inv eng 0 on hub 8
[   25.799891] amdgpu 0002:00:00.0: amdgpu: ring vcn_unified_1 uses VM inv eng 1 on hub 8
[   25.799893] amdgpu 0002:00:00.0: amdgpu: ring jpeg_dec uses VM inv eng 4 on hub 8
[   25.799894] amdgpu 0002:00:00.0: amdgpu: ring mes_kiq_3.1.0 uses VM inv eng 8 on hub 0
[   25.809826] amdgpu 0002:00:00.0: amdgpu: Runtime PM not available
[   25.810174] [drm] Initialized amdgpu 3.63.0 20150101 for 0002:00:00.0 on minor 0
[   25.810565] amdgpu 0002:00:00.0: [drm] fb1: amdgpudrmfb frame buffer device

@geomin12 geomin12 linked a pull request May 8, 2025 that will close this issue
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
Status: In Progress
Status: TODO
Development

Successfully merging a pull request may close this issue.

3 participants