d-MATRIX was granted a patent for chiplet switching in AI systems

{
  "signal_id": "11802d75-8b7e-5fbc-a2b1-eec756573ca4",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-09-30T17:17:34+00:00",
  "company": {
    "name": "d-Matrix",
    "domain": "d-matrix.ai"
  },
  "data": {
    "cpc": [
      {
        "code": "G06F 13/4027",
        "label": "Electric digital data processing"
      },
      {
        "code": "G06F 13/4022",
        "label": "Electric digital data processing"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Artificial Intelligence",
      "Engineering"
    ],
    "detail": "In September 2026 d-MATRIX patented a reconfigurable interconnect for linking chip packages in AI accelerators, including PCIe-based data-center hardware.",
    "summary": "d-MATRIX was granted a patent for chiplet switching in AI systems",
    "event_at": "2026-09-29",
    "inventors": [
      {
        "name": "Nithesh Kurella",
        "status": "resolved",
        "is_primary": true,
        "linkedin_url": "https://www.linkedin.com/in/nithesh-kurella-aa027663"
      },
      {
        "name": "Akhil Arunkumar",
        "status": "unresolved",
        "is_primary": false
      },
      {
        "name": "Jayaprakash Balachandran",
        "status": "unresolved",
        "is_primary": false
      },
      {
        "name": "Aayush Ankit",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/aayushankit"
      }
    ],
    "tech_area": "software / computing",
    "event_kind": "grant_date",
    "grant_date": "2026-09-29",
    "source_url": "https://patents.google.com/patent/US12748715",
    "cpc_primary": {
      "code": "G06F 13/4027",
      "label": "Electric digital data processing"
    },
    "patent_title": "Digital switch between chiplet devices for handling transformer workloads",
    "patent_number": "US12748715",
    "uspto_assignee": "d-MATRIX CORPORATION",
    "patent_abstract": "An active bridge module is present between substrates of an apparatus that accelerates AI computation workload. In response to an input, the active bridge module is configured to dynamically configure links between packages on the different substrates (e.g., PCIe cards). The active bridge module may comprise a network of digital switches. In certain embodiments, the active bridge module employs optical conversion with links comprising optical waveguides and/or optical cables. For a certain input, links can be dynamically established between packages on either of the adjacent PCIe boards (e.g., accommodating TP-4 tensor parallelism). For a different input to the module, links can be dynamically established between individual packages on each of the PCIe boards (e.g., accommodating TP-2 tensor parallelism). Embodiments are not limited to implementing parallelism of any particular degree, and can scale generally to implement parallel processing utilizing numbers of package(s) and/or their supporting substrate(s) that are greater than two.",
    "precision_class": "structural",
    "invention_explanation": "A bridge between chip packages that switches their connections as needed, with optional optical links to move transformer-workload data efficiently.",
    "technologies_mentioned": [
      "chiplets",
      "AI accelerators",
      "digital switching",
      "optical interconnects"
    ]
  }
}

curl https://signals.autobound.ai/v1/signals/11802d75-8b7e-5fbc-a2b1-eec756573ca4 \
  -H "X-API-KEY: $AUTOBOUND_API_KEY"

curl -X POST https://signals.autobound.ai/v1/companies/enrich \
  -H "X-API-KEY: $AUTOBOUND_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"domain":"d-matrix.ai","limit":20}'