{
 "id": "1.11",
 "slug": "2-5d-3d-advanced-packaging-cowos-s-l-r-soic",
 "url": "/parts/compute-silicon-and-packaging/2-5d-3d-advanced-packaging-cowos-s-l-r-soic",
 "name": "2.5D/3D advanced packaging",
 "qualifiers": "CoWoS-S/L/R, SoIC, EMIB/Foveros, I-Cube",
 "layer": {
  "id": 1,
  "name": "Compute silicon & packaging"
 },
 "parent_id": null,
 "children": [
  "1.11a"
 ],
 "summary": "The 2.5D/3D processes that combine a compute die, HBM memory stacks, and a substrate into one finished package — the step that turns silicon into a shippable AI accelerator.",
 "description_md": "Advanced packaging takes the finished die from the advanced-node foundry step, combines it with HBM memory stacks (see Layer 2) on an interposer or bridge (Interposers, silicon bridges, RDL), and mounts the result on a substrate (ABF / high-layer package substrates) — the step that actually produces a shippable AI accelerator rather than a bare die. It's the part of the chain that has repeatedly been the binding constraint on how many finished accelerators can reach the market, independent of how much wafer capacity exists upstream, because 2.5D/3D packaging capacity has historically been smaller and slower to add than logic wafer capacity.\nOne company's dominance in this specific process, as the taxonomy itself notes, has made packaging allocation as consequential to accelerator supply as foundry allocation, with a set of OSATs (see the child part below) picking up back-end and overflow work when primary capacity is full. For investors, the packaging step is arguably the single highest-conviction choke point in the whole compute-silicon chain: qualification cycles for a new packaging process are long, the process is capital-intensive to add capacity for, and demand for it has consistently run ahead of what's available.",
 "ai_delta": "Multi-die AI accelerator packages — a compute die plus HBM stacks — require advanced 2.5D/3D packaging that ordinary logic chips never needed, and packaging capacity has repeatedly been the first-order constraint on how many finished accelerators can ship.",
 "bottleneck_status": null,
 "scale_tiers": [
  "enterprise",
  "hyperscale_building",
  "ai_campus",
  "gw_class"
 ],
 "density_modes": [
  "any"
 ],
 "scale_notes": "Every merchant and custom AI accelerator needs advanced packaging; volume tracks total accelerator unit count across all tiers rather than any single facility's footprint.",
 "flow": [
  "compute"
 ],
 "companies": [
  {
   "company_id": "intel",
   "name": "Intel",
   "role": "manufacturer",
   "confidence": "inferred",
   "ownership_type": "public",
   "ticker": "INTC",
   "product_note": "Foundry",
   "note": null,
   "source_url": null
  },
  {
   "company_id": "samsung-electronics",
   "name": "Samsung Electronics",
   "role": "manufacturer",
   "confidence": "inferred",
   "ownership_type": "public",
   "ticker": "005930.KS",
   "product_note": null,
   "note": null,
   "source_url": null
  },
  {
   "company_id": "tsmc",
   "name": "TSMC",
   "role": "manufacturer",
   "confidence": "inferred",
   "ownership_type": "public",
   "ticker": "2330.TW",
   "product_note": null,
   "note": "dominant and the historical bottleneck",
   "source_url": null
  }
 ]
}