H100 Attestation failure in the CVM


I recently started configuring AMD-SEV-SNP with H100 GPU and tried to do some small demos on my machine. Everything went on smoothly except that the attestation validation went awry.

My machine’s specs:

CPU: Dual AMD EPYC 9124 16-Core Processor
GPU: H100 10de:2331 (vbios: cuda: 12.2 nvidia driver: 535.104.05)
Host OS: Ubuntu 22.04 with 5.19.0-rc6-snp-host-c4daeffce56e kernel
Guest OS: Ubuntu 22.04.2 with 5.19.0-rc6-snp-guest-c4daeffce56e kernel

I tried to run /attestation_sdk/tests/LocalGPUTest.py but encountered the following error:

        Comparing measurements (runtime vs golden)
                        The runtime measurements are not matching with the
                        golden measurements at the following indexes(starting from 0) :
The verification of GPU 0 resulted in failure.
        GPU Attestation failed

I also tried to set the cc-mode to devtools but it didn’t help.

Do you have any ideas on the error? Any help is more than appreciated!

I can definitely make x-nv-gpu-measurements-match to false but it seems to make no sense to do so.

During the EA, we had a mild regression which caused this issue. Please reopen a new topic if you continue to see any issues.