{
 "id": "1.07",
 "slug": "dpus",
 "url": "/parts/compute-silicon-and-packaging/dpus",
 "name": "DPUs",
 "qualifiers": null,
 "layer": {
  "id": 1,
  "name": "Compute silicon & packaging"
 },
 "parent_id": null,
 "children": [],
 "summary": "Data Processing Units that offload networking, storage, and security functions from the host CPU onto a dedicated, programmable chip.",
 "description_md": "A DPU takes infrastructure work — packet processing, storage virtualization, security functions — off the server CPU (Server CPUs) so those CPU cycles can go to orchestrating GPUs and other workload instead. It typically shares the board with the NIC or SuperNIC (NICs / SuperNICs) and, in some designs, is combined with it on a single card. Adoption is not universal: it's a design choice tied to a given server architecture and hyperscaler infrastructure stack rather than a component every AI server needs.\nFor investors, DPU exposure is concentrated in a small number of vendors, including at least one hyperscaler that has built its own in-house rather than buying merchant silicon, which caps the addressable market for the merchant suppliers at whichever fleets choose to buy rather than build. The category is worth tracking less for standalone unit growth and more as a signal of which server architectures a given hyperscaler or OEM has standardized on, since DPU attach is usually decided at the platform level rather than per order.",
 "ai_delta": "Offloading networking, storage, and security work from the host CPU matters more as GPU-dense AI servers push CPU cycles toward scarcity, since every cycle not spent on infrastructure work is a cycle available for orchestrating accelerators.",
 "bottleneck_status": null,
 "scale_tiers": [
  "enterprise",
  "hyperscale_building",
  "ai_campus",
  "gw_class"
 ],
 "density_modes": [
  "any"
 ],
 "scale_notes": "Attach rate depends on server architecture and hyperscaler infrastructure choices rather than facility size; not universal even in gigawatt-class fleets.",
 "flow": [
  "compute"
 ],
 "companies": [
  {
   "company_id": "amd",
   "name": "AMD",
   "role": "manufacturer",
   "confidence": "inferred",
   "ownership_type": "public",
   "ticker": "AMD",
   "product_note": "Pensando",
   "note": null,
   "source_url": null
  },
  {
   "company_id": "intel",
   "name": "Intel",
   "role": "manufacturer",
   "confidence": "inferred",
   "ownership_type": "public",
   "ticker": "INTC",
   "product_note": "IPU",
   "note": null,
   "source_url": null
  },
  {
   "company_id": "marvell",
   "name": "Marvell",
   "role": "manufacturer",
   "confidence": "inferred",
   "ownership_type": "public",
   "ticker": "MRVL",
   "product_note": "OCTEON",
   "note": null,
   "source_url": null
  },
  {
   "company_id": "microsoft",
   "name": "Microsoft",
   "role": "in_house",
   "confidence": "inferred",
   "ownership_type": "public",
   "ticker": "MSFT",
   "product_note": null,
   "note": "in-house",
   "source_url": null
  },
  {
   "company_id": "nvidia",
   "name": "Nvidia",
   "role": "manufacturer",
   "confidence": "inferred",
   "ownership_type": "public",
   "ticker": "NVDA",
   "product_note": "BlueField",
   "note": null,
   "source_url": null
  }
 ]
}