2.10 DPUs in the data center

NCA-AIIO · AI Infrastructure (40% of the exam) · Official objective: “Explain the purpose and benefits of a DPU in a datacenter”

What a DPU is and how BlueField and DOCA offload, accelerate and isolate infrastructure work.

Key points

  1. Offload means moving work from one processor to another. NVIDIA says DOCA and BlueField let developers build services that offload, accelerate and isolate data center workloads. BlueField decouples data center infrastructure from business applications. Its acceleration engines cover functions such as open virtual switch (OVS) packet processing.

    What NVIDIA says (5)

    “The NVIDIA DOCA™ Framework enables rapidly creating and managing applications and services on top of the BlueField networking platform, leveraging industry-standard APIs.”

    — NVIDIA DOCA Overview

    “by harnessing the power of NVIDIA's BlueField data-processing units (DPUs) and SuperNICs”

    — NVIDIA DOCA Overview

    “BlueField-3 DPUs offload, accelerate, and isolate software-defined networking, storage, security, and management functions, significantly enhancing data center performance, efficiency, and security.”

    — NVIDIA BlueField-3 Networking Platform User Guide: Introduction

    “By decoupling data center infrastructure from business applications, BlueField-3 creates a secure, zero-trust data center infrastructure”

    — NVIDIA BlueField-3 Networking Platform User Guide: Introduction

    “Data packet parsing, matching and manipulation to implement an open virtual switch (OVS)”

    — What Is a DPU? (NVIDIA Blog)

  2. A DPU (data processing unit) is a processor built to move and process data in the data center. NVIDIA describes it as a system on a chip (SoC) with an Arm-based multi-core CPU, a high-performance network interface, and programmable acceleration engines. NVIDIA calls the DPU the third pillar of computing, next to CPUs and GPUs. NVIDIA's DPU family is BlueField.

    What NVIDIA says (4)

    “The BlueField-3 platforms integrate x8 / x16 Armv8.2+ A78 Hercules cores (64-bit)”

    — NVIDIA BlueField-3 Networking Platform User Guide: Introduction

    “A DPU is a system on a chip, or SoC, that combines: An industry-standard, high-performance, software-programmable, multi-core CPU, typically based on the widely used Arm architecture, tightly coupled to the other SoC components.”

    — What Is a DPU? (NVIDIA Blog)

    “BlueField-3 DPUs offload, accelerate, and isolate software-defined networking, storage, security, and management functions, significantly enhancing data center performance, efficiency, and security.”

    — NVIDIA BlueField-3 Networking Platform User Guide: Introduction

    “Specialists in moving data in data centers, DPUs, or data processing units, are a new class of programmable processor and will join CPUs and GPUs as one of the three pillars of computing.”

    — What Is a DPU? (NVIDIA Blog)

  3. An SDK (software development kit) is a set of libraries and tools for building software. BlueField is programmed through NVIDIA DOCA. DOCA contains a runtime and a development environment (the SDK). DOCA services are containerized DOCA programs that can be deployed from NVIDIA's NGC catalog directly to BlueField.

    What NVIDIA says (3)

    “all fully programmable through the NVIDIA DOCA™ software framework”

    — NVIDIA BlueField-3 Networking Platform User Guide: Introduction

    “DOCA contains a runtime and development environment, including libraries and drivers for device management and programmability”

    — NVIDIA DOCA Overview

    “DOCA services are accessible as part of NVIDIA's container catalog (NGC) from which they can be easily deployed directly to BlueField”

    — NVIDIA DOCA Overview

  4. A data path is the route network packets take through a system. NVIDIA lists capabilities a DPU's data-path accelerators need, including RDMA transport acceleration for Zero Touch RoCE and GPUDirect accelerators that bypass the CPU and feed networked data directly to GPUs.

    What NVIDIA says (2)

    “the BlueField-3 SuperNIC provides best-in-class remote direct-memory access over converged Ethernet (RoCE) network connectivity between GPU servers”

    — NVIDIA BlueField-3 Networking Platform User Guide: Introduction

    “RDMA data transport acceleration for Zero Touch RoCE GPUDirect accelerators to bypass the CPU and feed networked data directly to GPUs”

    — What Is a DPU? (NVIDIA Blog)

Key terms

Try it

Sample question

Host CPUs are busy with virtual switching, encryption and storage traffic, leaving less CPU for the application. What does a BlueField DPU do here?

Show the answer

Answer: Offloads, accelerates and isolates these infrastructure services on the DPU, freeing host resources.

Offload means moving work from one processor to another. NVIDIA says DOCA and BlueField let developers build services that offload, accelerate and isolate data center workloads. BlueField decouples data center infrastructure from business applications. Its acceleration engines cover functions such as open virtual switch (OVS) packet processing.

What NVIDIA says (5)

“The NVIDIA DOCA™ Framework enables rapidly creating and managing applications and services on top of the BlueField networking platform, leveraging industry-standard APIs.”

— NVIDIA DOCA Overview

“by harnessing the power of NVIDIA's BlueField data-processing units (DPUs) and SuperNICs”

— NVIDIA DOCA Overview

“BlueField-3 DPUs offload, accelerate, and isolate software-defined networking, storage, security, and management functions, significantly enhancing data center performance, efficiency, and security.”

— NVIDIA BlueField-3 Networking Platform User Guide: Introduction

“By decoupling data center infrastructure from business applications, BlueField-3 creates a secure, zero-trust data center infrastructure”

— NVIDIA BlueField-3 Networking Platform User Guide: Introduction

“Data packet parsing, matching and manipulation to implement an open virtual switch (OVS)”

— What Is a DPU? (NVIDIA Blog)

Practice 2.10 (4 questions) Full AI Infrastructure guide

← 2.9 High-speed network options · 3.1 Data center management and monitoring →