Table of Contents
Advertisement
Feature
BlueField-3 IC
Overlay Networks
RDMA and RDMA over Converged
InfiniBand/Ethernet (RoCE)
Quality of Service (QoS)
Storage Acceleration
NVMe-oF
SR-IOV
High-Performance Accelerations
NVIDIA BlueField-3 DPU User Guide
Description
The NVIDIA BlueField-3 DPU integrates x8 / x16 Armv8.2+ A78 Hercules cores (64-bit) is interconnected by a coherent
mesh network, one DRAM controller, an RDMA intelligent network adapter supporting up to 400Gb/s, an embedded PCIe
switch with endpoint and root complex functionality, and up to 32 lanes of PCIe Gen 5.0.
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. NVIDIA DPU effectively addresses this by providing advanced NVGRE and VXLAN hardware offloading engines that
encapsulate and de-capsulate the overlay protocol.
NVIDIA DPU, utilizing IBTA RDMA (Remote Data Memory Access) and RoCE (RDMA over Converged InfiniBand/Ethernet)
technology, delivers low-latency and high-performance over InfiniBand/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.
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: NVMe over Fabric offloads for the target machine
•
BlueField-3 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 NVIDIA
BlueField-3 Arm cores. On the storage initiator side, NVIDIA BlueField-3 DPU 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.
Non-volatile 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. NVIDIA
BlueField-3 DPU may operate as a co-processor offloading specific storage tasks from the host using its powerful NVMe
over Fabrics Offload accelerator.
NVIDIA DPU SR-IOV technology provides dedicated adapter resources and guaranteed isolation and protection for virtual
machines (VM) within the server.
•
Tag Matching and Rendezvous Offloads
•
Adaptive Routing on Reliable Transport
•
Burst Buffer Offloads for Background Checkpointing
| 15
Advertisement
Table of Contents
