Skip to content

Adding DCGMI linux-arm64 support #377

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.

Sign up for GitHub

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

Merged
imadityaa merged 5 commits into from
Nov 12, 2024
Merged

Adding DCGMI linux-arm64 support #377

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
7697295
Adding DCGMI arm64 support
DEVAID-MSFT Jul 23, 2024
1f56423
Adding DCGMI installation for linux-arm64
DEVAID-MSFT Sep 9, 2024
cd85e26
Adding ppc64le link
DEVAID-MSFT Sep 27, 2024
0014616
Adding username
DEVAID-MSFT Sep 30, 2024
c616a70
Merge branch 'main' into users/devaid/AddingLinuxArm64Support
nmalkapuram Nov 12, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 12 additions & 1 deletion src/VirtualClient/VirtualClient.Actions/DCGMI/DCGMIExecutor.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,6 +122,17 @@ public string ListOfFieldIDsDmon
}
}

/// <summary>
/// The version of CUDA to be installed in Linux Systems
/// </summary>
public string LinuxCudaVersion
{
get
{
return this.Parameters.GetValue<string>(nameof(DCGMIExecutor.LinuxCudaVersion), "11.6");
}
}

/// <summary>
/// Initializes enviroment to run DCGMI.
/// </summary>
Expand Down Expand Up @@ -361,7 +372,7 @@ private async Task ExecuteDCGMIProfTesterSubsystemAsync(EventContext telemetryCo
using (BackgroundOperations profiling = BackgroundOperations.BeginProfiling(this, cancellationToken))
{
List<Task<string>> tasksList = new List<Task<string>>();
string dcgmproftestercommand = $"/usr/bin/dcgmproftester11 --no-dcgm-validation -t {this.FieldIDProftester} -d 10";
string dcgmproftestercommand = $"/usr/bin/dcgmproftester{(int)Convert.ToDouble(this.LinuxCudaVersion)} --no-dcgm-validation -t {this.FieldIDProftester} -d 10";
string dmoncommand = $"dcgmi dmon -e {this.ListOfFieldIDsDmon} -c 15";
DateTime startTime = DateTime.UtcNow;

Expand Down
8 changes: 6 additions & 2 deletions src/VirtualClient/VirtualClient.Dependencies/DCGMIInstallation.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,15 +107,19 @@ private async Task InstallDCGMIUbuntuOrDebianAsync(EventContext telemetryContext
List<string> commands = new List<string>();

string delKeyCommand = "apt-key del 7fa2af80";
string metaPackageDownloadCommand;
string metaPackageDownloadCommand = string.Empty;
if (this.PlatformSpecifics.CpuArchitecture == Architecture.X64)
{
metaPackageDownloadCommand = $@"bash -c ""wget https://developer.download.nvidia.com/compute/cuda/repos/$(echo $(. /etc/os-release; echo $ID$VERSION_ID) | sed -e 's/\.//g')/x86_64/cuda-keyring_1.0-1_all.deb""";
}
else
else if (this.PlatformSpecifics.CpuArchitecture == Architecture.Arm64)
{
metaPackageDownloadCommand = $@"bash -c ""wget https://developer.download.nvidia.com/compute/cuda/repos/$(echo $(. /etc/os-release; echo $ID$VERSION_ID) | sed -e 's/\.//g')/sbsa/cuda-keyring_1.0-1_all.deb""";
}
else if (this.PlatformSpecifics.CpuArchitecture == Architecture.Ppc64le)
{
metaPackageDownloadCommand = $@"bash -c ""wget https://developer.download.nvidia.com/compute/cuda/repos/$(echo $(. /etc/os-release; echo $ID$VERSION_ID) | sed -e 's/\.//g')/ppc64le/cuda-keyring_1.0-1_all.deb""";
}

string cudaGPGKeyInstallCommand = @"dpkg -i cuda-keyring_1.0-1_all.deb";
string updateCommand = @"apt-get update";
Expand Down
6 changes: 4 additions & 2 deletions src/VirtualClient/VirtualClient.Main/profiles/QUAL-GPU-DCGMI.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,8 @@
},
"Parameters": {
"Level": "4",
"Username": "null"
"Username": "",
"LinuxCudaVersion": "12.4"
},
"Actions": [
{
Expand Down Expand Up @@ -59,6 +60,7 @@
"Scenario": "CUDAIntegrationDiagnostics",
"Subsystem": "CUDATestGenerator",
"FieldIDProftester": "1004",
"LinuxCudaVersion": "$.Parameters.LinuxCudaVersion",
"ListOfFieldIDsDmon": "1004,1005,1001"
}
}
Expand All @@ -68,7 +70,7 @@
"Type": "NvidiaCudaInstallation",
"Parameters": {
"Scenario": "InstallNvidiaCuda",
"LinuxCudaVersion": "11.6",
"LinuxCudaVersion": "$.Parameters.LinuxCudaVersion",
"LinuxDriverVersion": "510",
"Username": "$.Parameters.Username",
"LinuxLocalRunFile": "https://developer.download.nvidia.com/compute/cuda/11.6.0/local_installers/cuda_11.6.0_510.39.01_linux.run"
Expand Down