NVIDIA DOCA Installation Guide for Linux

This guide details the necessary steps to set up NVIDIA DOCA in your Linux environment.

Installation of the NVIDIA® BlueField® networking platform (DPU or SuperNIC) software requires following the following step-by-step procedure.

Supported Platforms

Supported BlueField Platforms

The following NVIDIA® BlueField® platforms are supported with DOCA:

Supported ConnectX NICs

The NVIDIA® ConnectX® NICs supported with DOCA-Host can be found in: NVIDIA DOCA Profiles

Hardware Prerequisites

For BlueField Platform users, this guide assumes that a BlueField device has been installed in a server according to the instructions detailed in your DPU's hardware user guide .

DOCA Packages

See information in the NVIDIA DOCA Release Notes page.

Supported Host OS per DOCA-Host Installation Profile

See information in the NVIDIA DOCA Profiles page.

This guide provides the minimal instructions for setting up DOCA on a standard system.

Installation Files

To download the DOCA for host packages from the links in this table, please register to the NVIDIA Developer Program. Otherwise, please use the public repo from DOCA Downloader.

Uninstalling Software from Host

If an older DOCA (or MLNX_OFED) software version is installed on your host, make sure to uninstall it before proceeding with the installation of the new version:

            

            
$ for f in $( dpkg --list | grep doca | awk '{print $2}' ); do echo $f ; apt remove --purge $f -y ; done
$ /usr/sbin/ofed_uninstall.sh --force
$ sudo apt-get autoremove
        

            

            
host# for f in $(rpm -qa | grep -i doca ) ; do yum -y remove $f; done
host# /usr/sbin/ofed_uninstall.sh --force
host# yum autoremove
host# yum makecache
        

Then perform the following steps:

1. Download NVIDIA's RPM-GPG-KEY-Mellanox-SHA256 key:

   Copy

   Copied!

               
   
               
   # wget http://www.mellanox.com/downloads/ofed/RPM-GPG-KEY-Mellanox-SHA256
   --2018-01-25 13:52:30--  http://www.mellanox.com/downloads/ofed/RPM-GPG-KEY-Mellanox-SHA256
   Resolving www.mellanox.com... 72.3.194.0
   Connecting to www.mellanox.com|72.3.194.0|:80... connected.
   HTTP request sent, awaiting response... 200 OK
   Length: 1354 (1.3K) [text/plain]
   Saving to: ?RPM-GPG-KEY-Mellanox-SHA256?
    
   100%[=================================================>] 1,354       --.-K/s   in 0s
    
   2018-01-25 13:52:30 (247 MB/s) - ?RPM-GPG-KEY-Mellanox-SHA256? saved [1354/1354]
           

2. Install the key:

   Copy

   Copied!

               
   
               
   # sudo rpm --import RPM-GPG-KEY-Mellanox-SHA256
   warning: rpmts_HdrFromFdno: Header V3 DSA/SHA1 Signature, key ID 6224c050: NOKEY
   Retrieving key from file:///repos/MLNX_OFED//RPM-GPG-KEY-Mellanox
   Importing GPG key 0x6224C050:
    Userid: "Mellanox Technologies (Mellanox Technologies - Signing Key v2) "
    From  : /repos/MLNX_OFED//RPM-GPG-KEY-Mellanox-SHA256
   Is this ok [y/N]:
           

3. Verify that the key was successfully imported:

   Copy

   Copied!

               
   
               
   # rpm -q gpg-pubkey --qf '%{NAME}-%{VERSION}-%{RELEASE}\t%{SUMMARY}\n' | grep Mellanox
   gpg-pubkey-a9e4b643-520791ba    gpg(Mellanox Technologies )
           

Installing Prerequisites on Host for Target BlueField

Install RShim to manage and flash the BlueField Platform.

Installing Software on Host

1. Install DOCA local repo package for host:

   Info

   The following table provides instructions for installing the DOCA host repo on your device depending on your OS and desired profile.

   OS	Profile	Instructions
   Deb-based	doca-all	Download the DOCA host repo from section "Installation Files" for the host. Unpack the deb repo. Run: Copy Copied! host# dpkg -i <repo_file> Perform apt update. Run: Copy Copied! host# apt-get update If the kernel version on your host is not supported (not shown under "Supported Operating System Distributions"), refer to section "DOCA Extra Package". Ensure that the kernel headers installed match the version of the currently running kernel. Info If the build directory exists in under /lib/modules/$(uname -r)/build, then the kernel headers are installed. Run apt install for DOCA SDK and DOCA runtime: Copy Copied! host# sudo apt install -y doca-all mlnx-fw-updater
   	doca-networking	Download the DOCA host repo from section "Installation Files" for the host. Unpack the deb repo. Run: Copy Copied! host# dpkg -i <repo_file> Perform apt update. Run: Copy Copied! host# apt-get update If the kernel version on your host is not supported (not shown under "Supported Operating System Distributions"), refer to section "DOCA Extra Package". Ensure that the kernel headers installed match the version of the currently running kernel. Info If the build directory exists in under /lib/modules/$(uname -r)/build, then the kernel headers are installed. Run apt install for DOCA SDK and DOCA runtime: Copy Copied! host# sudo apt install -y doca-networking mlnx-fw-updater
   	doca-ofed	Download the DOCA host repo from section "Installation Files" for the host. Unpack the deb repo. Run: Copy Copied! host# sudo dpkg -i <repo_file> Perform apt update. Run: Copy Copied! host# sudo apt-get update If the kernel version on your host is not supported (not shown under "Supported Operating System Distributions"), refer to section "DOCA Extra Package". Ensure that the kernel headers installed match the version of the currently running kernel. Info If the build directory exists in under /lib/modules/$(uname -r)/build, then the kernel headers are installed. Install doca-ofed. Run: Copy Copied! host# sudo apt install -y doca-ofed mlnx-fw-updater
   RPM-based	doca-all	Download the DOCA host repo from section "Installation Files" for the host . Unpack the rpm repo. Run: Copy Copied! host# rpm -Uvh <repo_file>.rpm Perform yum update. Run: Copy Copied! host# sudo yum makecache If the kernel version on your host is not supported (not shown under "Supported Operating System Distributions"), refer to section "DOCA Extra Package". Run yum install for DOCA SDK and DOCA runtime: Copy Copied! host# sudo yum install -y doca-all mlnx-fw-updater
   	doca-networking	Download the DOCA host repo from section "Installation Files" for the host . Unpack the rpm repo. Run: Copy Copied! host# rpm -Uvh <repo_file>.rpm Perform yum update. Run: Copy Copied! host# sudo yum makecache If the kernel version on your host is not supported (not shown under "Supported Operating System Distributions"), refer to section "DOCA Extra Package". Run yum install for DOCA SDK and DOCA runtime: Copy Copied! host# sudo yum install -y doca-networking mlnx-fw-updater
   	doca-ofed	Download the DOCA host repo from section "Installation Files" for the host. Unpack the RPM repo. Run: Copy Copied! host# sudo rpm -Uvh <repo_file>.rpm Perform yum update. Run: Copy Copied! host# sudo yum makecache If the kernel version on your host is not supported (not shown under "Supported Operating System Distributions"), refer to section "DOCA Extra Package". Install doca-ofed. Run: Copy Copied! host# sudo yum install -y doca-ofed mlnx-fw-updater

2. Load the drivers:

   Copy

   Copied!

               
   
               
   host# sudo /etc/init.d/openibd restart
           

3. Initialize MST. Run:

   Copy

   Copied!

               
   
               
   host# sudo mst restart
           

DOCA Extra Package

If the kernel version on your host is not supported (not shown under "Supported Operating System Distributions"), two options are available:

• Switch to a compatible kernel.

• Install doca-extra package:

  1. Run:

     Copy

     Copied!

                 
     
                 
     host# sudo apt/yum install -y doca-extra
             

  2. Execute the doca-kernel-support script which rebuilds and installs the DOCA-Host kernel modules with the running kernel:

     Copy

     Copied!

                 
     
                 
     host# sudo /opt/mellanox/doca/tools/doca-kernel-support
             

  3. Install user-space packages:

     Copy

     Copied!

                 
     
                 
     host# sudo apt/yum install -y doca-ofed-userspace
             

     Note

     doca-kernel-support does not support customized or unofficial kernels.

  4. (Optional) Retrieve installed packages and their versions as part of DOCA Host installation:

     Collapse Source

     Copy

     Copied!

                 
     
                 
     host# doca-info
      
     Versions:
     - DOCA Base MLNX_OFED_LINUX-24.07-0.5.5.0
     - MFT 4.29.0-127
      
     UEFI\ATF versions:
     - mst_device: mt41692_pciconf0
          UEFI Version: 4.7.0-42-g13081ae
          ATF Version: 4.7.0-25-g5569834
      
     Firmware (Current):
     - BlueField-3 32.41.1000
      
     DOCA:
     - doca-all 2.8.0-0.0.4
     - doca-apsh-config 2.8.0079-1
     - doca-bench 2.8.0079-1
     …
      
     DOCA Dependencies:
     …
     - flexio 24.07.2300
     - mlnx-dpdk 22.11.0-2407.0.10
      
      
     OFED:
     …
     - rdma-core 2407mlnx52-1.2407055
     …
     - ucx 1.17.0-1.2407055
     …
             

     Note

     If BlueField has a BlueField Bundle version older than 2.7.0 installed on it, UEFI\ATF versions appear as N\A. If your version is 2.7.0 or higher and still see N\A, then perform driver restart on the host:

     Copy

     Copied!

                 
     
                 
     /etc/init.d/openibd restart
             

Installing Software on BlueField

Users have two options for installing DOCA on BlueField DPU or SuperNIC:

• Upgrading the full DOCA image on BlueField (recommended) – this option overwrites the entire boot partition with an Ubuntu 22.04 installation and updates BlueField and NIC firmware.

• Upgrading DOCA local repo package on BlueField – this option upgrades DOCA components without overwriting the boot partition. Use this option to preserve configurations or files on BlueField itself.

• Upgrading DOCA online repo package on BlueField – this option upgrades DOCA components without overwriting the boot partition. Use this option to preserve configurations or files on BlueField itself.

Installing Full DOCA Image on DPU via Host

Option 1 – No Pre-defined Password

BFB installation is executed as follows:

            

            
host# sudo bfb-install --rshim rshim<N> --bfb <image_path.bfb>
        

Where rshim<N> is rshim0 if you only have one Bluefield. You may run the following command to verify:

            

            
host# ls -la /dev/ | grep rshim
        

Option 2 – Set Pre-defined Password

Ubuntu users can provide a unique password that will be applied at the end of the BlueField BFB bundle installation. This password needs to be defined in a bf.cfg configuration file.

To set the password for the "ubuntu" user:

1. Create password hash. Run:

   Copy

   Copied!

               
   
               
   host# openssl passwd -1
   Password:
   Verifying - Password:
   $1$3B0RIrfX$TlHry93NFUJzg3Nya00rE1
           

2. Add the password hash in quotes to the bf.cfg file:

   Copy

   Copied!

               
   
               
   host# echo ubuntu_PASSWORD='$1$3B0RIrfX$TlHry93NFUJzg3Nya00rE1' > bf.cfg
           

   When running the installation command, use the --config flag to provide the file containing the password:

   Copy

   Copied!

               
   
               
   host# sudo bfb-install --rshim rshim<N> --bfb <image_path.bfb> --config bf.cfg
           

   Note

   Optionally, to upgrade the BlueField integrated BMC firmware using BFB bundle, please provide the current BMC root credentials in a bf.cfg file, as shown in the following:

   Copy

   Copied!

               
   
               
   BMC_PASSWORD="<root password>"
   BMC_USER="root"
   BMC_REBOOT="yes"
           

   Unless previously changed, the default BMC root password is 0penBmc.

   Note

   If --config is not used, then upon first login to the BlueField device, users will be prompted to update the default 'ubuntu' password.

   The following is an example of Ubuntu-22.04 BFB bundle installation (Release version may vary in the future).

   Collapse Source

   Copy

   Copied!

               
   
               
   host# sudo bfb-install --rshim rshim0 --bfb bf-bundle-2.7.0_24.04_ubuntu-22.04_prod.bfb --config bf.cfg
   Pushing bfb 1.41GiB 0:02:02 [11.7MiB/s] [           <=>                                                                                                                                ]
   Collecting BlueField booting status. Press Ctrl+C to stop
    INFO[PSC]: PSC BL1 START
    INFO[BL2]: start
    INFO[BL2]: boot mode (rshim)
    INFO[BL2]: VDDQ: 1120 mV
    INFO[BL2]: DDR POST passed
    INFO[BL2]: UEFI loaded
    INFO[BL31]: start
    INFO[BL31]: lifecycle GA Secured
    INFO[BL31]: VDD: 850 mV
    INFO[BL31]: runtime
    INFO[BL31]: MB ping success
    INFO[UEFI]: eMMC init
    INFO[UEFI]: eMMC probed
    INFO[UEFI]: UPVS valid
    INFO[UEFI]: PMI: updates started
    INFO[UEFI]: PMI: total updates: 1
    INFO[UEFI]: PMI: updates completed, status 0
    INFO[UEFI]: PCIe enum start
    INFO[UEFI]: PCIe enum end
    INFO[UEFI]: UEFI Secure Boot 
    INFO[UEFI]: PK configured
    INFO[UEFI]: Redfish enabled
    INFO[UEFI]: exit Boot Service
    INFO[MISC]: Found bf.cfg
    INFO[MISC]: Ubuntu installation started
    INFO[MISC]: Installing OS image
    INFO[MISC]: Changing the default password for user ubuntu
    INFO[MISC]: Ubuntu installation completed
    INFO[MISC]: Updating NIC firmware...
    INFO[MISC]: NIC firmware update done
    INFO[MISC]: Installation finished 
           

   To verify the BlueField has completed booting up, allow additional 90 seconds then perform the following:

   Copy

   Copied!

               
   
               
   host# sudo cat /dev/rshim<N>/misc
   ...
    INFO[MISC]: Linux up
    INFO[MISC]: DPU is ready  
           

Installing Full DOCA Image on Multiple BlueField Platforms

On a host with multiple BlueField devices, the BFB image can be installed on all of them using the multi-bfb-install script.

            

            
host# ./multi-bfb-install --bfb <image_path.bfb> --password <password>
        

This script detects the number of RShim devices and configures them statically.

• For Ubuntu – the script creates a configuration file /etc/netplan/20-tmfifo.yaml

• For CentOS/RH 8.0 and 8.2 – the script installs the bridge-utils package to use the brctl command, creates the tm-br bridge, and connects all RShim interfaces to it

After the installation is complete, the configuration of the bridge and each RShim interface can be observed using ifconfig. The expected result is to see the IP on the tm-br bridge configured to 192.168.100.1 with subnet 255.255.255.0.

            

            
ssh ubuntu@192.168.100.2
        

The script burns a new MAC address to each BlueField and configures a new IP, 192.168.100.x, as described earlier.

Installing DOCA Local Repo Package on BlueField

1. Download the DOCA SDK and DOCA Runtime package from section Installation Files.

2. Copy deb repo package into BlueField. Run:

   Copy

   Copied!

               
   
               
   host# sudo scp -r doca-repo-aarch64-ubuntu2204-local_<version>_arm64.deb ubuntu@192.168.100.2:/tmp/
           

3. Unpack the deb repo. Run:

   Copy

   Copied!

               
   
               
   dpu# sudo dpkg -i doca-dpu-repo-ubuntu2204-local_<version>_arm64.deb
           

4. Run apt update.

   Copy

   Copied!

               
   
               
   dpu# sudo apt-get update
           

5. Run apt install for DOCA Runtime and DOCA SDK:

   Copy

   Copied!

               
   
               
   dpu# sudo apt install doca-runtime doca-sdk
           

Upgrading Firmware

This section explains how to update the NIC firmware on a DOCA installed BlueField OS.

An up-to-date NIC firmware image is provided in BlueField BFB bundle and copied to the BlueField filesystem during BFB installation.

To upgrade firmware in the BlueField Arm OS:

1. SSH to your BlueField Arm OS by any means available.

   The following instructions enable to login to the BlueField Arm OS from the host OS over the RShim virtual interface, tmfifo_net<N> and do not require LAN connectivity with the BlueField OOB network port.

   Note

   This operation can be performed over the host's tmfifo_net0 IPv4, 192.168.100.1 (preconfigured) with BlueField Arm OS at 192.168.100.2 (default).

   If multiple BlueField DPUs were updated using the multi-bfb-install script, as explained above, then each target BlueField OS IPv4 address changes in its last octate according to the underlaying RShim interface number: 192.168.100.3 for rshim1, 192.168.100.4 for rshim2, etc.

   The default credentials for Ubuntu are as follows:

   Username	Password
   ubuntu	ubuntu

   For example, to log into BlueField Arm OS over IPv6:

   Copy

   Copied!

               
   
               
   host]# systemctl restart rshim
   // Wait 10 seconds
    
   host]# ssh -6 fe80::21a:caff:feff:ff01%tmfifo_net<N>
   Password: <configured-password>
           

2. Upgrade firmware in BlueField. Run:

   Copy

   Copied!

               
   
               
   dpu# sudo /opt/mellanox/mlnx-fw-updater/mlnx_fw_updater.pl --force-fw-update
           

   Example output:

   Copy

   Copied!

               
   
               
   Device #1:
   ----------
    
     Device Type:      BlueField-2
     [...]
     Versions:         Current        Available
        FW             <Old_FW>       <New_FW>
           

3. For the firmware upgrade to take effect perform a BlueField system reboot.

Post-installation Procedure

1. Restart the driver. Run:

   Copy

   Copied!

               
   
               
   host# sudo /etc/init.d/openibd restart
   Unloading HCA driver:                                      [  OK  ]
   Loading HCA driver and Access Layer:                       [  OK  ]
           

2. Configure the physical function (PF) interfaces.

   Copy

   Copied!

               
   
               
   host# sudo ifconfig <interface-1> <network-1/mask> up
   host# sudo ifconfig <interface-2> <network-2/mask> up
           

   For example:

   Copy

   Copied!

               
   
               
   host# sudo ifconfig p2p1 192.168.200.32/24 up
   host# sudo ifconfig p2p2 192.168.201.32/24 up
           

   Pings between the source and destination should now be operational.

This upgrade procedure enables upgrading DOCA components using standard Linux tools (e.g., apt update and yum update). This process utilizes native package manager repositories to upgrade BlueField networking platforms (DPUs or SuperNICs) without the need for a full installation.

This process has the following benefits :

• Only updates components that include modifications

  • Configurable – user can select specific components (e.g., UEFI-ATF, NIC-FW)

• Includes upgrade of:

  • DOCA drivers and libraries

  • DOCA reference applications

  • BSP (UEFI/ATF) upgrade while maintaining the configuration

  • NIC firmware upgrade while maintaining the configuration

• Does not:

  • Impact user binaries

  • Upgrade non-Ubuntu OS kernels

  • Upgrade BlueField BMC firmware

• After completion of BlueField upgrade:

  • If NIC firmware was not updated, perform BlueField Arm reset (software reset/reboot BlueField )

  • If NIC firmware was updated, perform firmware reset (mlxfwreset) or perform a graceful shutdown and power cycle

            

            
<bf> $ apt remove --purge mlxbf-bootimages* -y
        

            

            
<bf> $ apt update
<bf> $ apt install gnupg2
        

            

            
<bf> $ export DOCA_REPO="https://linux.mellanox.com/public/repo/doca/2.8.0/ubuntu22.04/dpu-arm64"
        

            

            
<bf> $ curl $DOCA_REPO/GPG-KEY-Mellanox.pub | gpg --dearmor > /etc/apt/trusted.gpg.d/GPG-KEY-Mellanox.pub
        

            

            
<bf> $ echo "deb [signed-by=/etc/apt/trusted.gpg.d/GPG-KEY-Mellanox.pub] $DOCA_REPO ./" > /etc/apt/sources.list.d/doca.list
        

            

            
<bf> $ apt update
        

            

            
<bf> $ apt install mlxbf-bootimages-signed
        

            

            
<bf> $ apt install mlxbf-scripts
<bf> $ bfrec
        

            

            
<bf> $ apt install mlnx-fw-updater-signed
<bf> $ sudo /opt/mellanox/mlnx-fw-updater/mlnx_fw_updater.pl --force-fw-update
        

            

            
<bf> $ apt-get remove doca* mlnx-ofed* kernel-mft* -y
        

            

            
<bf> $ apt-get install doca-runtime doca-devel -y
        

            

            
<bf> $ apt upgrade
        

            

            
<bf> $ yum -y remove mlxbf-bootimages*
<bf> $ yum makecache
        

            

            
<bf> $ export DOCA_REPO="https://linux.mellanox.com/public/repo/doca/2.8.0/rhel8.6/dpu-arm64/"
        

            

            
echo "[doca] 
name=DOCA Online Repo 
baseurl=$DOCA_REPO 
enabled=1 
gpgcheck=0 
priority=10 
cost=10" > /etc/yum.repos.d/doca.repo
        

            

            
<bf> $ yum makecache
        

            

            
<bf> $ yum install mlxbf-bootimages-signed mlxbf-bfscripts
        

            

            
<bf> $ bfrec
        

            

            
<bf> $ yum install mlnx-fw-updater-signed
<bf> $ sudo /opt/mellanox/mlnx-fw-updater/mlnx_fw_updater.pl --force-fw-update
        

            

            
<bf> $ yum remove doca*  mlnx-ofed* kernel-mft* -y
        

            

            
<bf> $ yum remove strongswan-bf strongswan-swanctl
<bf> $ yum remove strongswan-bf strongswan-swanctl libreswan
        

            

            
<bf> $ yum -y install doca-runtime doca-devel
        

            

            
<bf> $ yum upgrade --nobest
        

1. Restart the driver. Run:

   Copy

   Copied!

               
   
               
   host# sudo /etc/init.d/openibd restart
   Unloading HCA driver:                                      [  OK  ]
   Loading HCA driver and Access Layer:                       [  OK  ]
           

2. Configure the physical function (PF) interfaces.

   Copy

   Copied!

               
   
               
   host# sudo ifconfig <interface-1> <network-1/mask> up
   host# sudo ifconfig <interface-2> <network-2/mask> up
           

   For example:

   Copy

   Copied!

               
   
               
   host# sudo ifconfig p2p1 192.168.200.32/24 up
   host# sudo ifconfig p2p2 192.168.201.32/24 up
           

   Pings between the source and destination should now be operational.

Users wishing to build their own customized BlueField OS image can use the BFB build environment. Please refer to the bfb-build project in this GitHub webpage for more information.

For full instructions about setting up a development environment, refer to the NVIDIA DOCA Developer Guide.

Installing CUDA on NVIDIA Converged Accelerator

NVIDIA® CUDA® is a parallel computing platform and programming model developed by NVIDIA for general computing GPUs.

This section details the necessary steps to set up CUDA on your environment. This section assumes that a BFB image has already been installed on your environment.

To install CUDA on your converged accelerator:

1. Download and install the latest NVIDIA Data Center GPU driver.

2. Download and install CUDA

   Note

   The CUDA version tested to work with DOCA SDK is 11.8.0.

Configuring Operation Mode

There are two modes that the NVIDIA Converged Accelerator may operate in:

• Standard mode (default) – the BlueField and the GPU operate separately

• BlueField-X mode – the GPU is exposed to BlueField and is no longer visible on the host

To verify which mode the system is operating in, run:

            

            
host# sudo mst start
host# sudo mlxconfig -d <device-id> q PCI_DOWNSTREAM_PORT_OWNER[4]
        

• Standard mode output:

  Copy

  Copied!

              
  
              
  Device #1:
  […]
  Configurations:                              Next Boot
           PCI_DOWNSTREAM_PORT_OWNER[4]        DEVICE_DEFAULT(0)
          

• BlueField-X mode output:

  Copy

  Copied!

              
  
              
  Device #1:
  […]
  Configurations:                              Next Boot
           PCI_DOWNSTREAM_PORT_OWNER[4]        EMBEDDED_CPU(15)
          

To configure BlueField-X mode, run:

            

            
host# mlxconfig -d <device-id> s PCI_DOWNSTREAM_PORT_OWNER[4]=0xF
        

To configure standard mode, run:

            

            
host# mlxconfig -d <device-id> s PCI_DOWNSTREAM_PORT_OWNER[4]=0x0
        

Power cycle is required for configuration to take effect. For power cycle the host run:

            

            
host# ipmitool power cycle
        

Downloading and Installing CUDA Toolkit and Driver

This section details the necessary steps to set up CUDA on your environment. It assumes that a BFB image has already been installed on your environment.

1. Install CUDA by visiting the CUDA Toolkit Downloads webpage.

   Note

   Select the Linux distribution and version relevant for your environment.

   Note

   This section shows the native compilation option either on x86 or aarch64 hosts.

2. Test that the driver installation completed successfully. Run:

   Copy

   Copied!

               
   
               
   dpu# nvidia-smi
    
   Tue Apr  5 13:37:59 2022       
   +-----------------------------------------------------------------------------+
   | NVIDIA-SMI 510.47.03    Driver Version: 510.47.03    CUDA Version: 11.8     |
   |-------------------------------+----------------------+----------------------+
   | GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
   | Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
   |                               |                      |               MIG M. |
   |===============================+======================+======================|
   |   0  NVIDIA BF A10       Off  | 00000000:06:00.0 Off |                    0 |
   |  0%   43C    P0    N/A / 225W |      0MiB / 23028MiB |      0%      Default |
   |                               |                      |                  N/A |
   +-------------------------------+----------------------+----------------------+
   +-----------------------------------------------------------------------------+
   | Processes:                                                                  |
   |  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
   |        ID   ID                                                   Usage      |
   |=============================================================================|
   |  No running processes found                                                 |
   +-----------------------------------------------------------------------------+
           

3. Verify that the installation completed successfully.

   1. Download CUDA samples repo. Run:

      Copy

      Copied!

                  
      
                  
      dpu# git clone https://github.com/NVIDIA/cuda-samples.git
              

   2. Build and run vectorAdd CUDA sample. Run:

      Copy

      Copied!

                  
      
                  
      dpu# cd cuda-samples/Samples/0_Introduction/vectorAdd
      dpu# make
      dpu# ./vectorAdd
              

   Note

   If the vectorAdd sample works as expected, it should output "Test Passed".

   Note

   If it seems that the GPU is slow or stuck, stop execution and run:

   Copy

   Copied!

               
   
               
   dpu# sudo setpci -v -d ::0302 800.L=201 # CPL_VC0 = 32
           

GPUDirect RDMA

For information on GPUDirect RMDA and more, refer to DOCA GPUNetIO documentation.

Installing Rivermax on BlueField

NVIDIA Rivermax offers a unique IP-based solution for any media and data streaming use case.

This section provides the steps to install Rivermax assuming that a BFB image has already been installed on your environment.

Downloading Rivermax Driver

1. Navigate to the NVIDIA Rivermax SDK product page.

2. Register to be able to download the driver package using the JOIN button at the top of the page.

3. D ownload the appropriate driver package according to your BFB under the "Linux" subsection. For example, for Ubuntu 22.04 BFB, download rivermax_ubuntu2204_<version>.tar.gz.

Installing Rivermax Driver

1. Copy the .tgz file to BlueField:

   Copy

   Copied!

               
   
               
   host# sudo scp -r rivermax_ubuntu2204_<version>.tar.gz ubuntu@192.168.100.2:/tmp/
           

2. Extract the Rivermax file:

   Copy

   Copied!

               
   
               
   dpu# sudo tar xzf rivermax_ubuntu2204_<version>.tar.gz
           

3. Install the Rivermax driver package:

   Copy

   Copied!

               
   
               
   dpu# cd <rivermax-version>/Ubuntu.22.04/deb-dist/aarch64/
   dpu# sudo dpkg -i rivermax_<version>.deb
           

Installing Rivermax Libraries from DOCA

Rivermax libraries are compatibles with DOCA components and can be found inside the doca-dpu-repo.

1. Unpack the doca-dpu-repo:

   Copy

   Copied!

               
   
               
   dpu# sudo dpkg -i doca-dpu-repo-ubuntu2204-local_<version>_arm64.deb
           

2. Run apt update:

   Copy

   Copied!

               
   
               
   dpu# sudo apt-get update
           

3. Install the Rivermax libraries:

   Copy

   Copied!

               
   
               
   dpu# sudo apt install doca-rmax-libs
   dpu# sudo apt install libdoca-rmax-libs-dev
           

For additional details and guidelines, please visit the NVIDIA Rivermax SDK product page.