AMD Pensando DPUs

View all models
Our Expertise
FAQ

IT teams need to keep networking, security and storage services from taking CPU resources away from applications. AMD Pensando DPUs move those infrastructure tasks off the host so shared platforms stay more responsive and easier to isolate and manage.

In data centres and distributed environments, they support low-overhead control of traffic, telemetry and segmentation around AI, virtualised and sensitive workloads. AMD Pensando Salina DPU’s helps preserve compute capacity, improve observability and reduce contention across growing infrastructure.

AMD Pensando DPU Quick Specs & Key Features

  • Infrastructure Offload: A data processing unit architecture moves software-defined networking, security, storage and telemetry services away from host CPUs, preserving application compute for AI, virtualised services and shared enterprise workloads so utilisation improves without adding CPU overhead.
  • Programmable Networking: Hardware-accelerated packet handling supports controlled traffic paths and changing service requirements, helping data centres and telecoms maintain predictable performance and lower latency in multi-tenant environments.
  • Tenant Isolation: Segmented infrastructure processing separates network and security functions between workloads, supporting stronger workload isolation for finance, healthcare and cloud platforms so shared systems are easier to secure and operate.
Read more
  • Telemetry Visibility: Integrated observability services collect infrastructure-level data without relying on host processors, giving platform teams clearer operational insight and faster troubleshooting with less monitoring overhead.
  • Storage Acceleration: Offloaded storage services reduce the amount of data-path work handled by the server CPU, improving efficiency for AI front-end and distributed storage traffic so more resources remain available for workloads.
  • Cloud Edge Deployment: The range is suited to compute-edge environments where networking, security and storage functions need to be isolated from applications, helping enterprise and cloud teams scale shared infrastructure more easily.

Find your ideal AMD Pensando DPU

Full technical specifications are available on each product page.

Model Popularity Host Interface Network Protocols Max Network Ports Maximum Port Speed DPU ARM Cores DPU On-Board Memory (GB) Security Features Virtualisation Support
AMD Pensando Salina DPU AMD Pensando Salina DPU — — — — — — — — — View
Steel City Consulting logo

Comparing multiple platforms? Our experts are available to help.

No commitment needed, no hard sells. Just straightforward technical guidance tailored to your infrastructure.

Talk to a Specialist
Request a quote

AMD Pensando DPU Deployment Scenarios and Industries

Data Centres

Data centre teams need to keep AI, storage and network traffic moving while preserving host CPU and GPU capacity for applications. AMD Pensando DPUs offload networking, security, storage and telemetry services, helping improve isolation, utilisation and control across shared infrastructure.

Telecoms

Telecoms operators run virtualised services that depend on high packet throughput, low jitter and predictable behaviour under load. AMD Pensando DPUs shift network and infrastructure functions away from server CPUs, supporting service consistency and programmable control without adding CPU overhead.

Finance

Finance teams need strong segmentation, encryption and visibility around sensitive workloads, with performance that stays predictable. AMD Pensando DPUs isolate networking and security services from application processing, helping protect compute resources and support resilient private-cloud environments.

Software Development

Platform teams supporting shared build, training and inference environments need flexible networking that does not consume developer compute. AMD Pensando DPUs offload infrastructure services and provide a more programmable layer for isolating tenants, managing shared clusters and preserving host capacity.

Healthcare

Healthcare IT teams must move clinical and research data securely while keeping systems available for day-to-day care. AMD Pensando DPUs offload networking, storage and security tasks, helping strengthen segmentation, improve observability and leave more server resources for applications.

AMD Pensando DPU Management and Licensing Options

Why Work With Steel City Consulting

We’re trusted by IT teams in enterprise environments, data centres and complex multi-vendor estates. Our consultants help you select, integrate and support AMD Pensando DPUs, with practical guidance across server compatibility, infrastructure offload, deployment and lifecycle planning.

  • Official multi-vendor partner Pricing, licensing and upgrade routes across leading infrastructure technology vendors.
  • Decades of IT expertise Hands-on consultancy across networking, compute, storage and security.
  • UK-wide support network Certified engineers and technicians for on-site projects, SLAs and break/fix cover.

AMD Pensando DPUs

Book a consultation with our specialists

Tell us about your server infrastructure, workloads and networking requirements. We’ll help you assess where DPU offload fits, review compatibility and integration needs, and identify the most suitable deployment route.

AMD Pensando DPU Procurement & Vendor Support

We help you assess where AMD Pensando DPUs fit within your environment, balancing infrastructure offload, server compatibility, integration, support and long-term deployment requirements.

Right-sized DPU selection

We help you match DPU capabilities to your server platform, workloads and infrastructure offload requirements, so the selected solution fits the role it needs to perform.

Vendor support & service planning

We help you define suitable warranties, support coverage and professional services around your deployment, operating model and ongoing infrastructure requirements.

Compatibility & integration planning

We help you assess server platforms, networking, security and storage requirements so the DPU integrates effectively with the wider infrastructure environment.

Deployment & lifecycle planning

We help you plan implementation, validation, ongoing support and future upgrades so the DPU remains aligned with your infrastructure as requirements change.

Need help selecting an AMD Pensando DPU?

Speak to our experts about selecting, integrating and supporting AMD Pensando DPUs within your data centre infrastructure.

Speak to a specialist today

Designing & Supporting AMD Pensando DPU Solutions

Backed by decades of expertise in the IT sector, our specialists support every stage of your deployment — from initial selection through to long-term lifecycle management.

Steel City Consulting logo
Book a specialist consultation

AMD Pensando DPU FAQ

Why do organisations deploy AMD Pensando Salina DPU instead of leaving infrastructure services on the server CPU?

Organisations deploy AMD Pensando Salina DPU to offload networking, security and storage services from the server CPU, preserving compute resources for applications and workloads.

By moving infrastructure processing away from the host, Salina reduces contention between business workloads and supporting services. This can improve resource efficiency and create clearer separation between application compute and infrastructure functions in demanding server environments.

Where does AMD Pensando Salina DPU fit within private cloud and virtualised infrastructure?

AMD Pensando Salina DPU fits private cloud and virtualised infrastructure where organisations want infrastructure services separated from application compute within the server environment.

It can handle networking, security, storage and management-related processing that would otherwise consume host resources. This makes it useful in growing private cloud environments where IT teams want greater operational separation while retaining control within their own data centre.

How should organisations choose between AMD Pensando Salina DPU and Pollara or Vulcano AI NICs?

Choose Salina DPU for server infrastructure offload, and Pollara or Vulcano AI NICs when the priority is high-performance connectivity across distributed AI clusters.

Salina handles networking, security, storage and telemetry functions at the server level. Pollara 400 and Vulcano 800 are designed for backend AI networking, where efficient communication between GPU systems is the priority.

Need a different solution?

If these options aren’t the right fit for your environment, we provide a wide portfolio of product series and solutions that may better suit your infrastructure. Explore below, or speak to our team and we’ll help you find the right match.

Ready to discuss your requirements?

Whether you know exactly what you need or you’re still evaluating options, our team is available for a no-obligation conversation.

Contact our experts today
A group discussing IT solutions
Can’t find what you’re looking for? We have more products available - just reach out to us directly! Found a better price elsewhere? Let us know - we’re happy to discuss price matching.