Tenstorrent was granted a patent for predicting memory dependencies.

{
  "signal_id": "0fd40029-3c8a-5b69-acfe-e7451c8ecbb1",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-09-15T03:16:33+00:00",
  "company": {
    "name": "Tenstorrent",
    "domain": "tenstorrent.com"
  },
  "data": {
    "cpc": [
      {
        "code": "G06F 12/0223",
        "label": "Electric digital data processing"
      },
      {
        "code": "G06F 9/3834",
        "label": "Electric digital data processing"
      },
      {
        "code": "G06F 9/3838",
        "label": "Electric digital data processing"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Engineering",
      "Software"
    ],
    "detail": "In September 2026 Tenstorrent patented a processor technique for coordinating loads and stores in out-of-order computing, used in high-performance processors and computing systems.",
    "summary": "Tenstorrent was granted a patent for predicting memory dependencies.",
    "event_at": "2026-09-08",
    "inventors": [
      {
        "name": "Reshma C Jumani",
        "status": "resolved",
        "is_primary": true,
        "linkedin_url": "https://www.linkedin.com/in/reshma-jumani-6a28589"
      },
      {
        "name": "Miles Robert Dooley",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/milesdooley"
      },
      {
        "name": "Deepak Panwar",
        "status": "unresolved",
        "is_primary": false
      },
      {
        "name": "Luke Yen",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/lukeyence"
      },
      {
        "name": "Apurv Ravindra Narkhede",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/apurv-narkhede"
      },
      {
        "name": "Alexander C. Rucker",
        "status": "unresolved",
        "is_primary": false
      }
    ],
    "tech_area": "software / computing",
    "event_kind": "grant_date",
    "grant_date": "2026-09-08",
    "source_url": "https://patents.google.com/patent/US12730744",
    "cpc_primary": {
      "code": "G06F 12/0223",
      "label": "Electric digital data processing"
    },
    "patent_title": "Window-based memory dependency predictor",
    "patent_number": "US12730744",
    "uspto_assignee": "Tenstorrent USA, Inc.",
    "patent_abstract": "Methods and systems for out-of-order processing are disclosed herein. A disclosed method for out-of-order instruction processing includes identifying a first load instruction for processing, determining, based on the first load instruction, whether a store instruction window has been established for the first load instruction, confirming, when the store instruction window has been established, that one or more store instructions, within the store instruction window, that the first load instruction is dependent upon have been executed, and executing the first load instruction after execution of the one or more store instructions has been confirmed.",
    "precision_class": "structural",
    "invention_explanation": "A predictor tracks nearby store instructions so a processor can decide whether a load depends on earlier data before executing it.",
    "technologies_mentioned": [
      "processor architecture",
      "out-of-order execution",
      "memory dependency prediction",
      "load/store processing"
    ]
  }
}

curl https://signals.autobound.ai/v1/signals/0fd40029-3c8a-5b69-acfe-e7451c8ecbb1 \
  -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":"tenstorrent.com","limit":20}'