fix

Signed-off-by: Hanwen <[email protected]>

Author: hanwen-cluster

CHANGELOG.md

@@ -20,6 +20,11 @@ This file is used to list changes made in each version of the AWS ParallelCluste
   - Rdma-core: rdma-core-57.0-1
   - Open MPI: openmpi40-aws-4.1.7-2 and openmpi50-aws-5.0.6-11
 - Upgrade Cinc Client to version to 18.4.12 from 18.2.7.
+- Upgrade NVIDIA driver to version 570.172.08 (from 570.86.15) for all OSs except AL2.
+- Upgrade CUDA Toolkit to version 12.8.1 (from 12.8.0) for all OSs except AL2.
+- Upgrade DCGM to version 4.2.3 (from 3.3.6) for all OSs except AL2.
+- Upgrade Python to 3.12.11 (from 3.12.8) for all OSs except AL2.
+- Upgrade Intel MPI Library to 2021.16.0 (from 2021.13.1).
 - Addressed cluster id mismatch known issue by deleting the file `/var/spool/slurm.state/clustername` before configuring Slurm accounting.
 - Upgrade DCV to version 2024.0-19030.
 - Remove `berkshelf`. All cookbooks are local and do not need `berkshelf` dependency management.

cookbooks/aws-parallelcluster-platform/resources/nvidia_dcgm/partial/_nvidia_dcgm_debian.rb

@@ -13,12 +13,12 @@
 # See the License for the specific language governing permissions and limitations under the License.
 
 action :install_package do
-  if package_version.start_with?("3.")
-    packages_urls_list = [dcgm_package]
-  else
-    packages_urls_list = [dcgm4_core_package, dcgm4_package]
-  end
-  for package in packages_urls_list
+  packages_urls_list = if package_version.start_with?("3.")
+                         [dcgm_package]
+                       else
+                         [dcgm4_core_package, dcgm4_package]
+                       end
+  packages_urls_list.each do |package|
     remote_file "#{node['cluster']['sources_dir']}/#{package}-#{package_version}.deb" do
       source "#{node['cluster']['artifacts_s3_url']}/dependencies/nvidia_dcgm/#{platform}/#{package}_#{package_version}_#{arch_suffix}.deb"
       mode '0644'

cookbooks/aws-parallelcluster-platform/resources/nvidia_dcgm/partial/_nvidia_dcgm_rhel.rb

@@ -20,7 +20,7 @@
     packages_urls_list = [dcgm4_core_package, dcgm4_package]
     package_url_separator = "."
   end
-  for package in packages_urls_list
+  packages_urls_list.each do |package|
     remote_file "#{node['cluster']['sources_dir']}/#{package}-#{package_version}.rpm" do
       source "#{node['cluster']['artifacts_s3_url']}/dependencies/nvidia_dcgm/#{platform}/#{package}-#{package_version}#{package_url_separator}#{arch_suffix}.rpm"
       mode '0644'

cookbooks/aws-parallelcluster-platform/spec/unit/recipes/intel_mpi_spec.rb

@@ -20,7 +20,7 @@
   end
 
   it 'fetches intel mpi installer script' do
-    is_expected.to create_remote_file("#{source_dir}/intel-mpi-2021.13.1.769_offline.sh").with(
+    is_expected.to create_remote_file("#{source_dir}/intel-mpi-2021.16.0.443_offline.sh").with(
       source: "https://#{aws_region}-aws-parallelcluster.s3.#{aws_region}.test_aws_domain/archives/impi/intel-mpi-2021.16.0.443_offline.sh",
       mode: '0744',
       retries: 3,
@@ -43,7 +43,7 @@
 
   it 'renames intel mpi module' do
     is_expected.to run_execute('rename intel mpi modules file name').with(
-      command: "mv /opt/intel/mpi/2021.16/etc/modulefiles/mpi /opt/intel/mpi/2021.13/etc/modulefiles/intelmpi",
+      command: "mv /opt/intel/mpi/2021.16/etc/modulefiles/mpi /opt/intel/mpi/2021.16/etc/modulefiles/intelmpi",
       creates: '/opt/intel/mpi/2021.16/etc/modulefiles/intelmpi'
     )
   end

cookbooks/aws-parallelcluster-platform/spec/unit/resources/nvidia_dcgm_spec.rb

@@ -170,7 +170,8 @@ def self.setup(chef_run, nvidia_enabled: nil)
             end
           else
             it 'installs datacenter gpu manager' do
-              is_expected.to run_bash('Install datacenter-gpu-manager')
+              is_expected.to run_bash('Install datacenter-gpu-manager-4-core')
+              is_expected.to run_bash('Install datacenter-gpu-manager-4-cuda12')
             end
           end
         end

cookbooks/aws-parallelcluster-platform/test/controls/nvidia_dcgm_spec.rb

@@ -14,8 +14,13 @@
     ['yes', true, 'true'].include?(node['cluster']['nvidia']['enabled']) && !instance.custom_ami? &&
       (!os_properties.arm? || !(os_properties.alinux2? || os_properties.centos?))
   end
-
-  describe package('datacenter-gpu-manager-4-cuda12') do
-    it { should be_installed }
+  if os_properties.alinux2?
+    describe package('datacenter-gpu-manager') do
+      it { should be_installed }
+    end
+  else
+    describe package('datacenter-gpu-manager-4-cuda12') do
+      it { should be_installed }
+    end
   end
 end