Upgrade NVIDIA driver and cuda version (aws#2887)

* Upgrade NVIDIA driver and cuda version

* Update CHANGELOG

* Fix unit tests

Author: hgreebe

CHANGELOG.md

@@ -10,6 +10,8 @@ This file is used to list changes made in each version of the AWS ParallelCluste
 - Disable unused services like cups and wpa_supplicant from Official ParallelCluster AMIs to improve security.
 
 **CHANGES**
+- Upgrade NVIDIA driver to version 570.86.15 (from 550.127.08) for all OSs except AL2.
+- Upgrade CUDA Toolkit to version 12.8.0 (from 12.4.1) for all OSs except AL2.
 - On Ubuntu 22.04, install the Nvidia driver with the same compiler version used to compile the kernel.
 - Upgrade `aws-cfn-bootstrap` to version 2.0-32.
 - Upgrade amazon-efs-utils to version 2.1.0.

cookbooks/aws-parallelcluster-platform/attributes/platform.rb

@@ -16,8 +16,11 @@
 
 # NVidia
 default['cluster']['nvidia']['enabled'] = 'no'
-default['cluster']['nvidia']['driver_version'] = '550.127.08'
+default['cluster']['nvidia']['driver_version'] = '570.86.15'
 default['cluster']['nvidia']['dcgm_version'] = '3.3.6'
+if platform?('amazon') && node['platform_version'] == "2"
+  default['cluster']['nvidia']['driver_version'] = '550.127.08'
+end
 
 # DCV
 default['cluster']['dcv']['authenticator']['user'] = "dcvextauth"

cookbooks/aws-parallelcluster-platform/recipes/install/cuda.rb

@@ -19,13 +19,20 @@
 
 # Cuda installer from https://developer.nvidia.com/cuda-toolkit-archive
 # Cuda installer naming: cuda_11.8.0_520.61.05_linux
-cuda_version = '12.4'
-cuda_patch = '1'
+cuda_version = '12.8'
+cuda_patch = '0'
 cuda_complete_version = "#{cuda_version}.#{cuda_patch}"
-cuda_version_suffix = '550.54.15'
+cuda_version_suffix = '570.86.10'
+cuda_samples_version = '12.8'
+if platform?('amazon') && node['platform_version'] == "2"
+  cuda_version = '12.4'
+  cuda_patch = '1'
+  cuda_complete_version = "#{cuda_version}.#{cuda_patch}"
+  cuda_version_suffix = '550.54.15'
+  cuda_samples_version = '12.4'
+end
 cuda_arch = arm_instance? ? 'linux_sbsa' : 'linux'
 cuda_url = "#{node['cluster']['artifacts_s3_url']}/dependencies/cuda/cuda_#{cuda_complete_version}_#{cuda_version_suffix}_#{cuda_arch}.run"
-cuda_samples_version = '12.4'
 cuda_samples_url = "#{node['cluster']['artifacts_s3_url']}/dependencies/cuda/samples/v#{cuda_samples_version}.tar.gz"
 tmp_cuda_run = '/tmp/cuda.run'
 tmp_cuda_sample_archive = '/tmp/cuda-sample.tar.gz'

cookbooks/aws-parallelcluster-platform/resources/fabric_manager/fabric_manager_ubuntu20+.rb

@@ -20,7 +20,7 @@
 use 'partial/_fabric_manager_install_debian.rb'
 
 def fabric_manager_package
-  'nvidia-fabricmanager-550'
+  'nvidia-fabricmanager-570'
 end
 
 def fabric_manager_version

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

@@ -1,10 +1,10 @@
 require 'spec_helper'
 
 describe 'aws-parallelcluster-platform::cuda' do
-  cached(:cuda_version) { '12.4' }
-  cached(:cuda_patch) { '1' }
+  cached(:cuda_version) { '12.8' }
+  cached(:cuda_patch) { '0' }
   cached(:cuda_complete_version) { "#{cuda_version}.#{cuda_patch}" }
-  cached(:cuda_version_suffix) { '550.54.15' }
+  cached(:cuda_version_suffix) { '570.86.10' }
 
   context 'when nvidia not enabled' do
     cached(:chef_run) do
@@ -20,7 +20,7 @@
   context 'when on arm' do
     cached(:cuda_arch) { 'linux_sbsa' }
     cached(:cuda_url) { "#{node['cluster']['artifacts_s3_url']}/dependencies/cuda/cuda_#{cuda_complete_version}_#{cuda_version_suffix}_#{cuda_arch}.run" }
-    cached(:cuda_samples_version) { '12.4' }
+    cached(:cuda_samples_version) { '12.8' }
     cached(:cuda_samples_url) { "#{node['cluster']['artifacts_s3_url']}/dependencies/cuda/samples/v#{cuda_samples_version}.tar.gz" }
 
     cached(:chef_run) do

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

@@ -168,7 +168,7 @@ def self.configure(chef_run)
 
   for_all_oses do |platform, version|
     context "on #{platform}#{version}" do
-      cached(:fabric_manager_package) { platform == 'ubuntu' ? 'nvidia-fabricmanager-550' : 'nvidia-fabric-manager' }
+      cached(:fabric_manager_package) { platform == 'ubuntu' ? 'nvidia-fabricmanager-570' : 'nvidia-fabric-manager' }
       cached(:fabric_manager_version) { platform == 'ubuntu' ? "#{nvidia_driver_version}" : nvidia_driver_version }
 
       context 'when fabric manager is to install' do