aws: enable GPU AMI support for GPU instances

Add support for GPU-optimized AMIs when using GPU instance types.
This includes:

- AWS Deep Learning AMI with pre-installed NVIDIA drivers, CUDA, and
  ML frameworks
- NVIDIA Deep Learning AMI option for NGC containers
- Custom GPU AMI support for specialized images
- Automatic detection of GPU instance types
- Conditional display of GPU AMI options only for GPU instances
- Update terraform.tfvars template to use GPU AMI when configured
- Add defconfig for AWS G6e.2xlarge GPU instance with Deep Learning AMI

The system automatically detects when you select a GPU instance family
(like G6E) and provides appropriate GPU-optimized AMI options including
the AWS Deep Learning AMI with all necessary drivers and frameworks
pre-installed.

Generated-by: Claude AI
Signed-off-by: Luis Chamberlain <[email protected]>

Author: mcgrof

defconfigs/aws-gpu-g6e-ai

@@ -0,0 +1,42 @@
+# AWS G6e.2xlarge GPU instance with Deep Learning AMI for AI/ML workloads
+# This configuration sets up an AWS G6e.2xlarge instance with NVIDIA L40S GPU
+# optimized for machine learning, AI inference, and GPU-accelerated workloads
+
+# Cloud provider configuration
+CONFIG_KDEVOPS_ENABLE_TERRAFORM=y
+CONFIG_TERRAFORM=y
+CONFIG_TERRAFORM_AWS=y
+
+# AWS Dynamic configuration (required for G6E instance family and GPU AMIs)
+CONFIG_TERRAFORM_AWS_USE_DYNAMIC_CONFIG=y
+
+# AWS Instance configuration - G6E family with NVIDIA L40S GPU
+# G6E.2XLARGE specifications:
+# - 8 vCPUs (3rd Gen AMD EPYC processors)
+# - 32 GB system RAM
+# - 1x NVIDIA L40S Tensor Core GPU
+# - 48 GB GPU memory
+# - Up to 15 Gbps network performance
+# - Up to 10 Gbps EBS bandwidth
+CONFIG_TERRAFORM_AWS_INSTANCE_TYPE_G6E=y
+CONFIG_TERRAFORM_AWS_INSTANCE_G6E_2XLARGE=y
+
+# AWS Region - US East (N. Virginia) - primary availability for G6E
+CONFIG_TERRAFORM_AWS_REGION_US_EAST_1=y
+
+# GPU-optimized Deep Learning AMI
+# Includes: NVIDIA drivers 535+, CUDA 12.x, cuDNN, TensorFlow, PyTorch, MXNet
+CONFIG_TERRAFORM_AWS_USE_GPU_AMI=y
+CONFIG_TERRAFORM_AWS_GPU_AMI_DEEP_LEARNING=y
+CONFIG_TERRAFORM_AWS_GPU_AMI_NAME="Deep Learning OSS Nvidia Driver AMI GPU PyTorch*Ubuntu 22.04*"
+CONFIG_TERRAFORM_AWS_GPU_AMI_OWNER="amazon"
+
+# Storage configuration optimized for ML workloads
+# 200 GB for datasets, models, and experiment artifacts
+CONFIG_TERRAFORM_AWS_DATA_VOLUME_SIZE=200
+
+# Note: After provisioning, the instance will have:
+# - Jupyter notebook server ready for ML experiments
+# - Pre-installed deep learning frameworks
+# - NVIDIA GPU drivers and CUDA toolkit
+# - Docker with NVIDIA Container Toolkit for containerized ML workloads

playbooks/roles/gen_tfvars/templates/aws/terraform.tfvars.j2

@@ -1,8 +1,13 @@
 aws_profile = "{{ terraform_aws_profile }}"
 aws_region = "{{ terraform_aws_region }}"
 aws_availability_zone = "{{ terraform_aws_av_zone }}"
+{% if terraform_aws_use_gpu_ami is defined and terraform_aws_use_gpu_ami %}
+aws_name_search = "{{ terraform_aws_gpu_ami_name }}"
+aws_ami_owner = "{{ terraform_aws_gpu_ami_owner }}"
+{% else %}
 aws_name_search = "{{ terraform_aws_ns }}"
 aws_ami_owner = "{{ terraform_aws_ami_owner }}"
+{% endif %}
 aws_instance_type = "{{ terraform_aws_instance_type }}"
 aws_ebs_volumes_per_instance = "{{ terraform_aws_ebs_volumes_per_instance }}"
 aws_ebs_volume_size = {{ terraform_aws_ebs_volume_size }}

scripts/aws_api.py

@@ -956,7 +956,7 @@ def generate_gpu_amis_kconfig() -> str:
 config TERRAFORM_AWS_GPU_AMI_NAME
 	string
 	output yaml
-	default "Deep Learning AMI GPU TensorFlow*"
+	default "Deep Learning OSS Nvidia Driver AMI GPU PyTorch*Ubuntu 22.04*"
 	help
 	  AMI name pattern for AWS Deep Learning AMI.
 
@@ -1061,7 +1061,7 @@ def generate_default_gpu_amis_kconfig() -> str:
 config TERRAFORM_AWS_GPU_AMI_NAME
 	string
 	output yaml
-	default "Deep Learning AMI GPU TensorFlow*"
+	default "Deep Learning OSS Nvidia Driver AMI GPU PyTorch*Ubuntu 22.04*"
 
 config TERRAFORM_AWS_GPU_AMI_OWNER
 	string

scripts/dynamic-cloud-kconfig.Makefile

@@ -45,6 +45,7 @@ dynamic_aws_kconfig_touch:
 	$(Q)touch $(AWS_KCONFIG_DIR)/Kconfig.gpu-amis.generated
 	$(Q)touch $(AWS_KCONFIG_DIR)/Kconfig.compute.static
 	$(Q)touch $(AWS_KCONFIG_DIR)/Kconfig.location.static
+	$(Q)touch $(AWS_KCONFIG_DIR)/Kconfig.gpu-amis.static
 	$(Q)for family in $(AWS_INSTANCE_TYPE_FAMILIES); do \
 		touch $(AWS_INSTANCE_TYPES_DIR)/Kconfig.$$family.generated; \
 		touch $(AWS_INSTANCE_TYPES_DIR)/Kconfig.$$family.static; \
@@ -117,6 +118,11 @@ cloud-update:
 		sed -i 's/Kconfig\.\([^.]*\)\.generated/Kconfig.\1.static/g' $(AWS_KCONFIG_DIR)/Kconfig.location.static; \
 		echo "  Created $(AWS_KCONFIG_DIR)/Kconfig.location.static"; \
 	fi
+	$(Q)if [ -f $(AWS_KCONFIG_DIR)/Kconfig.gpu-amis.generated ]; then \
+		cp $(AWS_KCONFIG_DIR)/Kconfig.gpu-amis.generated $(AWS_KCONFIG_DIR)/Kconfig.gpu-amis.static; \
+		sed -i 's/Kconfig\.\([^.]*\)\.generated/Kconfig.\1.static/g' $(AWS_KCONFIG_DIR)/Kconfig.gpu-amis.static; \
+		echo "  Created $(AWS_KCONFIG_DIR)/Kconfig.gpu-amis.static"; \
+	fi
 	# AWS instance type families
 	$(Q)for file in $(AWS_INSTANCE_TYPES_DIR)/Kconfig.*.generated; do \
 		if [ -f "$$file" ]; then \

terraform/aws/kconfigs/Kconfig.compute

@@ -76,3 +76,8 @@ source "terraform/aws/kconfigs/distros/Kconfig.fedora"
 source "terraform/aws/kconfigs/distros/Kconfig.rhel"
 source "terraform/aws/kconfigs/distros/Kconfig.sles"
 source "terraform/aws/kconfigs/distros/Kconfig.custom"
+
+# Include GPU AMI configuration if available (generated by cloud-config)
+if TERRAFORM_AWS_USE_DYNAMIC_CONFIG
+source "terraform/aws/kconfigs/Kconfig.gpu-amis.static"
+endif