Introduction

Cards

1x BlueField-2 DPU

Accessories

1x tall bracket (shipped assembled on the card).

For MBF2H332A-AECOT, MBF2H332A-AEEOT, MBF2H332A-AENOT, MBF2M355A-VECOT, MBF2M355A-VESOT only:

1x short bracket is included in the box (not assembled).

For other cards: Short brackets should be ordered separately.

PCI Express (PCIe)

Uses PCIe Gen 4.0 (16GT/s) through an x8/x16 edge connector. Gen 1.1, 2.0, and 3.0 compatible.

Up to 200 Gigabit Ethernet

BlueField-2 DPU complies with the following IEEE 802.3 standards: 200GbE / 100GbE / 50GbE / 40GbE / 25GbE / 10GbE

Onboard Memory

• Quad SPI NOR FLASH - includes 256Mbit for firmware image

• UVPS EEPROM - includes 1Mbit

• FRU EEPROM - stores the parameters and personality of the DPU. The EEPROM capacity is 128Kbit. FRU I2C address is (0x50) and is accessible through the PCIe SMBus.

• eMMC - x8 NAND flash (memory size might vary on different DPUs) for Arm boot, OS, and disk space

• DDR4 SDRAM - 8GB/16GB/32GB @3200MT/s single-channel DDR4 SDRAM memory. Solder down on-board. 64bit + 8bit ECC.

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

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), significantly reducing 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.

Storage Acceleration

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.

• NVMe over Fabric offloads for the target machine

• T10-DIF Signature Handover

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 using the BlueField-2 Arm cores. On the storage initiator side, BlueField-2 DPU can prove an efficient solution for hyper-converged systems to enable the host CPU to focus on computing while all the storage interface is handled through the Arm cores.

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.

SR-IOV

DPU SR-IOV technology provides dedicated adapter resources and guaranteed isolation and protection for virtual machines (VM) within the server.

GPU Direct

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. The DPU uses high-speed DMA transfers to copy data between P2P devices resulting in more efficient system applications.

Crypto

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 is enabled.

Security Accelerators

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 Layer 4 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.

BMC

Some DPUs incorporate local NIC BMC (Baseboard Management Controller) hardware on the board. The BMC SoC (system on a chip) can utilize either shared or dedicated NICs for remote access. The BMC node enables remote power cycling, board environment monitoring, BlueField-2 chip temperature monitoring, board power, and consumption monitoring, and individual interface resets. The BMC also supports the ability to push a bootstream to BlueField-2. Having a trusted onboard BMC that is fully isolated from the host server ensures the highest security for the DPU boards.

Enabled in MBF2H516C-CECOT, MBF2H516C-CESOT, MBF2M516C-CECOT, MBF2M516C-CESOT, MBF2H536C-CECOT, MBF2H536C-CESOT, MBF2H512C-AECOT, MBF2H512C-AESOT, MBF2H512C-AEUOT, MBF2H532C-AECOT, MBF2H532C-AESOT.

PPS IN/OUT

NVIDIA offers a full IEEE 1588v2 PTP software solution, as well as time-sensitive related features called “5T”. NVIDIA PTP and 5T software solutions, are designed to meet the most demanding PTP profiles. BlueField-2 incorporates an integrated Hardware Clock (PHC) that allows BlueField-2 to achieve sub-20u Sec accuracy and offers many timings-related functions such as time-triggered scheduling or time-based SND accelerations. The PTP part supports the subordinate clock, master clock, and boundary clock.

BlueField-2 PTP solution allows you to run any PTP stack on your host and on the DPU Arm.

The MMCX on the board allows customers to connect an RF cable without occupying space on the external bracket.

Enabled in MBF2H516C-CECOT, MBF2H516C-CESOT, MBF2M516C-CECOT, MBF2M516C-CESOT, MBF2H536C-CECOT, MBF2H536C-CESOT, MBF2H512C-AECOT, MBF2H512C-AESOT, MBF2H512C-AEUOT, MBF2H532C-AECOT, MBF2H532C-AESOT.