OFL-01 · Hardware Offload and Virtualization

Decide what belongs on the card.

Learn to split work between host and SmartNIC, program a DPU, and deploy the accelerated workload on Kubernetes.

Advanced≈ 30 h 8 units4 labs
smartnicdpubluefieldipuovsp4fpga

You build: an offloaded service running on a Kubernetes cluster.

Promise

Decide what belongs on the card, program a SmartNIC or DPU, and deploy accelerated workloads on Kubernetes.

Prerequisites

PDP-01; DPK-01 recommended.

Units

1. Foundations ch 01–02

hardware acceleration basics.

2. SmartNIC and DPU architecture ch 03–05

architecture and the programming model.

3. Programming ch 06–10

models, the DPDK data plane on a SmartNIC.

4. Offload ch 11–16

hardware offload, SR-IOV, OVS offload, security offload.

5. Programmable pipelines ch 17–19

P4 pipelines and FPGA-based SmartNIC development. Also the unit where the Verilog bridge applies.

6. DPU platforms ch 20–24

BlueField DPUs and IPU programming.

7. Cloud native ch 25–28

smart NICs and Kubernetes, orchestration, reliability.

8. Case study and close ch 29–30

how cloud providers use them.

Labs

Each lab names its environment and a pass check. Labs are not marked complete on "it ran" — the pass check has to hold.

LabWhat you doEnvironment
OFL-01ach 14 Check whether OVS offload is activePass check: Offloaded flow count above zero hardware60 min
OFL-01bch 10 DPDK application on a SmartNICPass check: Packets counted at the NIC hardware120 min
OFL-01cch 19 Custom packet processing on an FPGA SmartNICPass check: Output matches the reference model hardware180 min
OFL-01dch 21 Run an application on a DPUPass check: Application runs with traffic offloaded hardware120 min

Capstone project · CAP-07

Offload Plan with Measured Gains · 3 weeks

Management asks whether a virtual switch should move to a SmartNIC or DPU.

Baseline the host, measure the offload on the same workload, decide, and state the workload where offload loses.

Deliverables: Measurement data, decision record, rollout plan.

Outcomes

  • I can decide which functions to offload, and show the measurement that justifies it.
  • I can check whether OVS offload is active.
  • I can explain the boundary between host and DPU.

Also in

How it runs

Work through the units in order. Each unit groups the chapters of the study guide with its share of the labs. You can start any time; there is no cohort date and nothing expires.

Labs run in a VM, a container, a simulator or on real hardware, and the card above names which. Where a lab needs hardware — an RDMA NIC, a programmable switch model, an FPGA — there is a simulator fallback so you are never blocked by equipment.

Questions

Do I get a certificate?

You get a completion record for the course. Path badges and project credentials are earned by passing the labs and the project review, not by attendance.

Can my team take this together?

Yes — and if you would rather have it delivered live, with the instructor in the room, this course also exists as a scheduled live cohort. See the live dates.

How long does it take?

≈ 30 h of study including the labs. Most engineers take it part-time over a few weeks.