NVIDIA Bluefield 1 - (DBox DPU)

NVIDIA SKU #

OPN #

Data Rate

Network Interface

Ports

PCIe

Technology

Crypto

MBF1M606A-ESNAT

2x100GbE/EDR100

QSFP28

Dual

PCIe 4.0 x16

VPI

Disabled

Feature

Description

PCI Express (PCIe)^a

Uses the following PCIe connectors:

• PCIe Gen 3.0 (8GT/s) and Gen 4.0 (16GT/s) through an x16 edge connector. Gen 1.1 and 2.0 compatible

• Two PCIe Gen 3.0 (8GT/s) CABLINE-CA II PLUS connectors - available in MBF1M656A-CSNAT, MBF1M636A-CSNAT and MBF1M626A-CSNAT

Up to 100 Gigabit Ethernet

• 100GbE/ 50GbE / 25GbE

• IEEE 802.3bj, 802.3bm 100 Gigabit Ethernet

• IEEE 802.3by, Ethernet Consortium25, 50 Gigabit Ethernet, supporting all FEC modes

• IEEE 802.3az Energy Efficient Ethernet

• IEEE 802.3ap based auto-negotiation and KR startup

• Proprietary Ethernet protocols (50GBASE-R4)

• IEEE 802.3ad, 802.1AX Link Aggregation

• IEEE 802.1Q, 802.1P VLAN tags and priority

• IEEE 802.1Qau (QCN)

• Congestion Notification

• IEEE 802.1Qaz (ETS)

• IEEE 802.1Qbb (PFC)

• IEEE 802.1Qbg

• IEEE 1588v2

• Jumbo frame support (9.6KB)

On-board Memory

• Two DDR4 SODIMM sockets - size is 16GB each (MBF1M636A-CSNAT and MBF1M616A-CSNAT)

• Two DDR4 SODIMM sockets - size is 8GB each (MBF1M656A-CSNAT and MBF1M646A-CSNAT)

• 2x 16GB eMMC NAND flash memory for software

• SPI Flash for NIC firmware

• SPI Flash for CPLD firmware

• EEPROM - Size 128Kbit

BlueField SoC

The BlueField-2 SoC 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 3.0/4.0.

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. BlueField BF1600 Controller Card effectively addresses this by providing advanced NVGRE and VXLAN hardware offloading engines that encapsulate and decapsulate the overlay protocol.

RDMA and RDMA over Converged Ethernet (RoCE)

The BlueField BF1600 Controller Cards, utilizing IBTA RDMA (Remote Data Memory Access) and RoCE (RDMA over Converged Ethernet) technology, deliver 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®

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. BlueField BF1600 Controller Card 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 SmartNIC 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 SmartNIC can prove an efficient solution for hyper-converged systems to enable the host CPU to focus
on compute while all the storage interface is handled through the Arm cores.

High-Performance Accelerations

• Tag Matching and Rendezvous Offloads

• Adaptive Routing on Reliable Transport

• Burst Buffer Offloads for Background Checkpointing

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 NVIDIA 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. BlueField BF1600 Controller Card uses high-speed DMA transfers to copy data between P2P devices, resulting in more efficient system applications.

Security Accelerators

A consolidated compute and network solution based on BlueField Controller Card achieves significant advantages over a centralized security server solution. Standard encryption protocols and security applications can leverage BlueField compute capabilities and network offloads for security application solutions such as:

• Connection Tracking

• Stateful firewall