Overview
NICE DCV is a high performance remote streaming protocol that enables user to securely access remote desktop or application sessions, including 3D graphics applications hosted on servers with high-performance GPUs.
NICE DCV offers end users a wide range of client devices, including native clients for Windows, Linux, and MacOS operating systems. Native clients support up to 4 monitors at 4K resolution each and the Windows client also supports USB redirection for 3D mice and USB storage devices. The QUIC/UDP protocol is enabled as well for best interactive performance.
NICE DCV Ubuntu 22 Desktop supports high end remote 3D access for e.g. HPC or media pre-/post-processing applications. Includes support for remote USB devices and file transfer. NVIDIA drivers pre-installed for high-end remote 3D experience. On AWS, NICE DCV provides the streaming protocol e.g. used by Amazon Appstream 2.0, AWS RoboMaker and AWS Nimble Studio.
Latest version includes CUDA Toolkit 12.2 and nvcc. Includes NIVIDIA DOCKER Container support.
Latest version includes neural network inference support for quantized models via llama.cpp. See Usage Information for more background and https://www.ai-sp.com/how-to-run-a-70b-nn-model-on-a-standard-server/ . g4dn and g5 instances supported for inference.
This AMI with Ubuntu 22 supports g5, g4dn, g3 and p3 (V100) instance families.
Highlights
- Remote Performance: Responsive and secure streaming experience allowing customers to run graphics intensive applications remotely removing the need for expensive dedicated workstations or transferring large amounts of data. Based on NICE DCV from AWS.
- Secure TLS encrypted high-end 3D remote desktop connection on powerful NVIDIA based cloud GPUs. Includes remote USB support and file transfer.
- Ubuntu 22 desktop with full superuser access to add and manage own applications. Leverages high NVIDIA GPU cloud GPUs.
Details
Typical total price
$0.792/hour
Pricing
Free trial
Instance type | Product cost/hour | EC2 cost/hour | Total/hour |
---|---|---|---|
p3.2xlarge | $0.30 | $3.06 | $3.36 |
p3.8xlarge | $1.20 | $12.24 | $13.44 |
p3.16xlarge | $2.40 | $24.48 | $26.88 |
p3dn.24xlarge | $3.00 | $31.212 | $34.212 |
g4dn.xlarge | $0.03 | $0.526 | $0.556 |
g4dn.2xlarge Recommended | $0.04 | $0.752 | $0.792 |
g4dn.4xlarge | $0.08 | $1.204 | $1.284 |
g4dn.8xlarge | $0.16 | $2.176 | $2.336 |
g4dn.12xlarge | $0.32 | $3.912 | $4.232 |
g4dn.16xlarge | $0.36 | $4.352 | $4.712 |
Additional AWS infrastructure costs
Type | Cost |
---|---|
EBS General Purpose SSD (gp2) volumes | $0.10/per GB/month of provisioned storage |
Vendor refund policy
No refund
Legal
Vendor terms and conditions
Content disclaimer
Delivery details
64-bit (x86) Amazon Machine Image (AMI)
Amazon Machine Image (AMI)
An AMI is a virtual image that provides the information required to launch an instance. Amazon EC2 (Elastic Compute Cloud) instances are virtual servers on which you can run your applications and workloads, offering varying combinations of CPU, memory, storage, and networking resources. You can launch as many instances from as many different AMIs as you need.
Version release notes
Updated to latest NVIDIA driver 560.35.03 and CUDA Toolkit 12.6.1. Includes NICE DCV 2023.1-16388 with support for redirection of in-session WebAuthN and other new features and patches. More information can be found here: https://www.ni-sp.com/9-11-2023-nice-releases-dcv-2023-1-including-new-features/
Additional details
Usage instructions
Make sure the instance security groups allow inbound traffic to TCP and UDP port 8443 and 22.
To connect you have different options:
Option 1: Connect with the native NICE DCV Client for best performance
- Download the NICE DCV client from: https://download.nice-dcv.com/ (includes Windows portable client)
- In the DCV client connection field enter the instance public IP to connect.
- Sign in using the following credentials: User: ubuntu. Password: last 6 digits of the instance ID.
Option 2: Connect with NICE DCV Web Client for convenience
- Connect with the following URL: https://IP_OR_FQDN:8443/, e.g. https://3.70.184.235:8443/
- Sign in using the following credentials: User: ubuntu. Password: last 6 digits of the instance ID.
Option 3: Set your own password and connect
- Connect to your remote machine with ssh -i
ubuntu@ - Set the password for the user "ubuntu" with sudo passwd ubuntu. This is the password you will use to log in to DCV
- Connect to your remote machine with the NICE DCV native client or web client as described above
- Enter your credentials and you are ready to rock
With DCV QUIC/UDP will be used automatically together with the DCV native client. In the DCV client connection settings you can select TCP as well. Please do not perform an update to a new kernel or higher releases as it might disable the GPU driver.
In case of interest in Inferencing with llama.cpp we have created a dedicated Inference server: https://aws.amazon.com/marketplace/pp/prodview-y3u47mo7fsbdm
Resources
Support
Vendor support
Technical documentation (https://aws.amazon.com/documentation/dcv/ ) and NI SP Tips and Tricks (https://www.ni-sp.com/nice-dcv-tips-and-tricks/ ). Free support is available through forums (https://forums.aws.amazon.com/forum.jspa?forumID=366 )
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
Customer reviews
working well
This AMI is working well for CUDA computing + NVIDIA graphics + NICE DCV remote interactive visualization on P and G instances