This is the User Manual for NVIDIA® BlueField®-2 BF2500 DPU Controller. This document provides details of the product interfaces, specifications, required software and firmware for operating the board, and a step-by-step plan of how to bring up the BlueField-2 BF2500 DPU Controller.
|Main-board PCI Express slot|
x16 Gen 4.0 slot.
|System Power Supply||Minimum 75W or greater system power supply for all cards.|
These PCIe Gen 4.0 x16 DPU controllers require additional 75W through a supplementary 6-pin ATX power supply connector.
NOTE: The connector is not included in the package. It should be part of system wiring or it can be ordered separately as a system accessory.
|Operating System||BlueField-2 DPU is shipped with Ubuntu – a Linux commercial operating system – which includes the NVIDIA OFED stack (MLNX_OFED), and is capable of running all customer-based Linux applications seamlessly. BlueField-2 DPU also supports CentOS and has an out-of-band 1GbE management interface. For more information, please refer to the DOCA SDK documentation or NVIDIA BlueField-2 Software User Manual.|
For detailed information, see Specifications.
Before installing your new system, unpack it and check against the below tables that all the parts have been sent. Check the parts for visible damage that may have occurred during shipping.
If anything is damaged or missing, contact your reseller.
|Cards||1x BlueField-2 DPU Controller card with an assembled tall bracket|
The accessories kit should be ordered separately. Earlier controller versions require the kit OPN MBF20-DKIT, while newer versions require kit OPN MBF25-DKIT.
|MBF20-DKIT||1x USB 2.0 Type A to mini-USB Type B cable|
|1x USB 2.0 Type A to 30pin Flat Socket|
These DPU controllers, you need a 6-pin ATX power supply connector cable to activate the card. The cable is not included in the package. For further details, please refer to External PCIe Power Supply Connector.
BlueField-2 BlueField-2 BF2500 DPU Controller features the second generation BlueField-2 data processing Unit (DPU) – an innovative and high-performance programmable networking engine. The DPU integrates an array of eight powerful 64-bit Arm v8 A72 cores interconnected by a coherent mesh with a DDR4 memory controller and a dual-port Ethernet network controller. Providing unmatched scalability and efficiency, NVIDIA BF2500 DPU Controller is the ideal adapter to accelerate the most demanding workloads in data center, cloud, service provider and storage environments.
The BlueField BF2500 DPU Controller should be installed only in a JBOF and JBOD Systems as it functions as a PCIe root-complex (RC) initiating PCIe bus operations. Installing it in a regular host system may damage the card.
Ideal Solution for JBOF and JBOD Systems
NVIDIA BlueField-2 DPU is a highly integrated and efficient controller, optimized for NVMe storage systems, Network Functions Virtualization (NFV), Cloud and Machine Learning workloads. BlueField-2 integrates all the discrete components of a storage system appliance into a single chip, including Arm core CPUs, PCIe switch and a network controller, making it the premier solution for building Just-a-Bunch-Of-Flash (JBOF) systems, All-Flash-Array and storage appliances for NVMe over Fabrics. With an integrated NVMe-oF offload accelerator, the BF2500 DPU Controller has a superior performance advantage over existing JBOF systems, significantly reducing storage transaction latency, while increasing IOPs (I/O operations per second).
Features and Benefits
This section describes hardware features and capabilities.
It is recommended to upgrade your BlueField product to the latest software and firmware versions available in order to enjoy the latest features and bug fixes.
Please refer to the software release notes for feature availability.
|PCI Express (PCIe)||Uses PCIe Gen 4.0 (16GT/s) through an x16 edge connector, compatible with Gen 3.0, 2.0 and 1.1.|
|Up to 200 Gigabit Ethernet|
|BlueField-2 DPU||The BlueField-2 DPU integrates eight 64-bit Armv8 A72 cores interconnected by a coherent mesh network, one DRAM controller, an RDMA intelligent network adapter supporting up to 200Gb/s, an embedded PCIe switch with endpoint and root complex functionality, and up to 16 lanes of PCIe Gen 4.0.|
|Overlay Networks||In order to better scale their networks, data center operators often create overlay networks that carry traffic from individual virtual machines over logical tunnels in encapsulated formats such as NVGRE and VXLAN. While this solves network scalability issues, it hides the TCP packet from the hardware offloading engines, placing higher loads on the host CPU. DPU effectively addresses this by providing advanced NVGRE and VXLAN hardware offloading engines that encapsulate and de-capsulate the overlay protocol.|
|RDMA and RDMA over Converged Ethernet (RoCE)||DPU, utilizing IBTA RDMA (Remote Data Memory Access) and RoCE (RDMA over Converged Ethernet) technology, delivers low-latency and high-performance over Ethernet networks. Leveraging data center bridging (DCB) capabilities as well as advanced congestion control hardware mechanisms, RoCE provides efficient low-latency RDMA services over Layer 2 and Layer 3 networks.|
|NVIDIA PeerDirect||NVIDIA PeerDirect communication provides high-efficiency RDMA access by eliminating unnecessary internal data copies between components on the PCIe bus (for example, from GPU to CPU), and therefore significantly reduces application run time. DPU advanced acceleration technology enables higher cluster efficiency and scalability to tens of thousands of nodes.|
|Quality of Service (QoS)||Support for port-based Quality of Service enabling various application requirements for latency and SLA.|
A consolidated compute and storage network achieves significant cost-performance advantages over multi-fabric networks. Standard block and file access protocols can leverage RDMA for high-performance storage access.
BlueField-2 DPU may operate as a co-processor offloading specific storage tasks from the host, isolating part of the storage media from the host, or enabling abstraction of software-defined storage logic
|NVMe-oF||Nonvolatile Memory Express (NVMe) over Fabrics is a protocol for communicating block storage IO requests over RDMA to transfer data between a host computer and a target solid-state storage device or system over a network. BlueField-2 DPU may operate as a co-processor offloading specific storage tasks from the host using its powerful NVMe over Fabrics Offload accelerator.|
DPU SR-IOV technology provides dedicated adapter resources and guaranteed isolation and protection for virtual machines (VM) within the server.
The latest advancement in GPU-GPU communications is GPUDirect RDMA. This new technology provides a direct P2P (Peer-to-Peer) data path between the GPU Memory directly to/from the HCA devices. This provides a significant decrease in GPU-GPU communication latency and completely offloads the CPU, removing it from all GPU-GPU communications across the network. DPU uses high-speed DMA transfers to copy data between P2P devices resulting in more efficient system applications
The BlueField-2 DPU crypto enabled versions include a BlueField-2 IC which supports accelerated cryptographic operations. In addition to specialized instructions for bulk cryptographic processing in the Arm cores, an offload hardware engine accelerates public-key cryptography and random number generation are enabled.
A consolidated compute and network solution based on DPU achieves significant advantages over a centralized security server solution. Standard encryption protocols and security applications can leverage BlueField-2 compute capabilities and network offloads for security application solutions such as Layer4 Stateful Firewall.
|Out-of-Band Management||The BlueField-2 DPU incorporates a 1GbE RJ45 out-of-band port that allows the network operator to establish trust boundaries in accessing the management function to apply it to network resources. It can also be used to ensure management connectivity (including the ability to determine the status of any network component) independent of the status of other in-band network components.|