Merge branch 'develop' into develop

Author: efim-a-efim

CHANGELOG.md

@@ -8,6 +8,7 @@ This file is used to list changes made in each version of the AWS ParallelCluste
 
 **ENHANCEMENTS**
 - Add support for P6e-GB200 instances. ParallelCluster sets up Slurm topology plugin to handle P6e-GB200 UltraServers. See limitations section for important additional setup requirements.
+- Add support for P6-B200 instances for all OSs except AL2.
 - Add `build-image` support for Amazon Linux 2023 AMIs based on kernel 6.12 (in addition to 6.1).
 
 **LIMITATIONS**
@@ -29,7 +30,7 @@ This file is used to list changes made in each version of the AWS ParallelCluste
 - Upgrade Cinc Client to version 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 DCGM to version 4.4.1 (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 Python to 3.9.23 (from 3.9.20) for AL2.
 - Upgrade Intel MPI Library to 2021.16.0 (from 2021.13.1).

cookbooks/aws-parallelcluster-awsbatch/metadata.rb

@@ -7,12 +7,12 @@
 issues_url 'https://github.com/aws/aws-parallelcluster/issues'
 source_url 'https://github.com/aws/aws-parallelcluster-cookbook'
 chef_version '>= 18'
-version '3.14.0'
+version '3.15.0'
 
 depends 'iptables', '~> 8.0.0'
 depends 'nfs', '~> 5.1.5'
 depends 'line', '~> 4.5.21'
 depends 'openssh', '~> 2.11.14'
 depends 'yum', '~> 7.4.20'
 depends 'yum-epel', '~> 5.0.8'
-depends 'aws-parallelcluster-shared', '~> 3.14.0'
+depends 'aws-parallelcluster-shared', '~> 3.15.0'

cookbooks/aws-parallelcluster-computefleet/metadata.rb

@@ -7,6 +7,6 @@
 issues_url 'https://github.com/aws/aws-parallelcluster-cookbook/issues'
 source_url 'https://github.com/aws/aws-parallelcluster-cookbook'
 chef_version '>= 18'
-version '3.14.0'
+version '3.15.0'
 
-depends 'aws-parallelcluster-shared', '~> 3.14.0'
+depends 'aws-parallelcluster-shared', '~> 3.15.0'

cookbooks/aws-parallelcluster-entrypoints/metadata.rb

@@ -7,11 +7,11 @@
 issues_url 'https://github.com/aws/aws-parallelcluster-cookbook/issues'
 source_url 'https://github.com/aws/aws-parallelcluster-cookbook'
 chef_version '>= 18'
-version '3.14.0'
+version '3.15.0'
 
-depends 'aws-parallelcluster-shared', '~> 3.14.0'
-depends 'aws-parallelcluster-platform', '~> 3.14.0'
-depends 'aws-parallelcluster-environment', '~> 3.14.0'
-depends 'aws-parallelcluster-computefleet', '~> 3.14.0'
-depends 'aws-parallelcluster-slurm', '~> 3.14.0'
-depends 'aws-parallelcluster-awsbatch', '~> 3.14.0'
+depends 'aws-parallelcluster-shared', '~> 3.15.0'
+depends 'aws-parallelcluster-platform', '~> 3.15.0'
+depends 'aws-parallelcluster-environment', '~> 3.15.0'
+depends 'aws-parallelcluster-computefleet', '~> 3.15.0'
+depends 'aws-parallelcluster-slurm', '~> 3.15.0'
+depends 'aws-parallelcluster-awsbatch', '~> 3.15.0'

cookbooks/aws-parallelcluster-environment/metadata.rb

@@ -7,9 +7,9 @@
 issues_url 'https://github.com/aws/aws-parallelcluster-cookbook/issues'
 source_url 'https://github.com/aws/aws-parallelcluster-cookbook'
 chef_version '>= 18'
-version '3.14.0'
+version '3.15.0'
 
 depends 'line', '~> 4.5.21'
 depends 'nfs', '~> 5.1.5'
 
-depends 'aws-parallelcluster-shared', '~> 3.14.0'
+depends 'aws-parallelcluster-shared', '~> 3.15.0'

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

@@ -17,7 +17,7 @@
 # NVidia
 default['cluster']['nvidia']['enabled'] = 'no'
 default['cluster']['nvidia']['driver_version'] = '570.172.08'
-default['cluster']['nvidia']['dcgm_version'] = '4.2.3-2'
+default['cluster']['nvidia']['dcgm_version'] = '4.4.1-1'
 if platform?('amazon') && node['platform_version'] == "2"
   default['cluster']['nvidia']['driver_version'] = '550.127.08'
   default['cluster']['nvidia']['dcgm_version'] = '3.3.6-1'
@@ -27,6 +27,9 @@
 default['cluster']['nvidia']['imex']['shared_dir'] = "#{node['cluster']['shared_dir']}/nvidia-imex"
 default['cluster']['nvidia']['imex']['force_configuration'] = false
 
+# NVIDIA NVLSM
+default['cluster']['nvidia']['nvlsm']['enabled'] = true
+
 # DCV
 default['cluster']['dcv']['authenticator']['user'] = "dcvextauth"
 default['cluster']['dcv']['authenticator']['user_id'] = node['cluster']['reserved_base_uid'] + 3

cookbooks/aws-parallelcluster-platform/files/infiniband/infiniband.conf

@@ -0,0 +1 @@
+ib_umad

cookbooks/aws-parallelcluster-platform/libraries/nvidia.rb

@@ -27,11 +27,12 @@ def get_nvswitch_count(device_id)
 end
 
 def get_device_ids
-  #  A100 (P4), H100(P5), B200(P6) and GB200()p6e) systems have NVSwitches
+  #  A100 (P4), H100(P5), B200(P6) and GB200(p6e) systems have NVSwitches
   # NVSwitch device id is 10de:1af1 for P4 instance
   # NVSwitch device id is 10de:22a3 for P5 instance
+  # NVSwitch device id is 10de:2901 for P6 instance
   # NVSwitch device id is 10de:2941 for P6e instance
-  { 'a100' => '10de:1af1', 'h100' => '10de:22a3', 'gb200' => '10de:2941' }
+  { 'a100' => '10de:1af1', 'h100' => '10de:22a3', 'b200' => '10de:2901', 'gb200' => '10de:2941' }
 end
 
 def is_gb200_node?

cookbooks/aws-parallelcluster-platform/metadata.rb

@@ -7,8 +7,8 @@
 issues_url 'https://github.com/aws/aws-parallelcluster-cookbook/issues'
 source_url 'https://github.com/aws/aws-parallelcluster-cookbook'
 chef_version '>= 18'
-version '3.14.0'
+version '3.15.0'
 
 depends 'line', '~> 4.5.21'
 
-depends 'aws-parallelcluster-shared', '~> 3.14.0'
+depends 'aws-parallelcluster-shared', '~> 3.15.0'

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

@@ -21,6 +21,8 @@
 
 gdrcopy 'Install Nvidia gdrcopy'
 
+nvidia_nvlsm 'Install Nvidia NVLink Subnet Manager'
+
 fabric_manager 'Install Nvidia Fabric Manager'
 
 nvidia_dcgm 'install Nvidia datacenter-gpu-manager'