Skip to main content
ArmPatent grant

Arm was granted a patent for a flexible matrix-multiplication accelerator.

Source: Autobound Signal API · 92 signals tracked for Arm · updated

Get Arm's live signals in Claude or ChatGPT, or by API

AskWhat changed at Arm this week? Use Autobound signals for arm.com.

What happened

In November 2026 Arm patented a processor design for efficient AI and data-processing calculations across hardware such as smartphones, servers, and embedded systems.

Source

patents.google.comNov 17, 2026

US patent US12801689

Matrix multiply accelerator for variable bitwidth operands

Abstract

A processor, computer based method and apparatus for performing matrix multiplication are provided. The processor obtains a first bitslice vector comprising m elements, obtains a second bitslice vector comprising n elements, provides at least one element of the first bitslice vector as a first input to a single bit dot product unit, provides at least one element of the second bit-slice vector as a second input to the single-bit dot product unit, and obtains, from the single-bit dot product unit, an output comprising at least a partial dot product of the first and second bitslice vectors.

patents.google.com/patent/US12801689Read the full source

Extracted by Autobound

From the Signal API record
Signal
Patent grant

What this signalsA new patent often shows where a company is putting its R&D budget.

Grant date
Nov 17, 2026
Tech area
software / computing
Patent number
US12801689

The full record

From the Signal API record

People

  • Zhi-Gang LiuInventor
  • Paul Nicholas WhatmoughInventor
  • Matthew MattinaInventor
  • John Fremont Brown, IIIInventor

Details

Primary CPC class
G06F 17/16 (Electric digital data processing)
USPTO assignee
Arm Limited
What the invention does
A hardware engine breaks numbers into individual bit layers and combines them with one-bit dot products, supporting calculations with different number precisions.

Topics and mentions

Inventors

  • Zhi-Gang Liu
  • Paul Nicholas Whatmough
  • Matthew Mattina
  • John Fremont Brown
  • III

Tags

  • Intellectual Property
  • Research & Development
  • Artificial Intelligence
  • Engineering

Technologies named

  • matrix multiplication
  • AI accelerators
  • bit-slice processing
  • processor architecture

Extraction

Detected
Nov 18, 2026
signal_type
patents-company
signal_subtype
patentGrant

Use this data

Get every patent signal for Arm and the companies you sell to, in the tools you already use.

  1. Ask Claude about it

    Connect Autobound to Claude, Claude Code or Cursor with MCP. Then ask: “What changed at Arm this week?”

  2. Send it to your own tools

    The Signal API returns patent signals for any list of companies as JSON, for your CRM, warehouse or app.

  3. Try it free

    Sign up and spend your free credits on the companies you sell to.

    Start Free1,000 free credits

The API returns more than this page shows

This page shows a preview. The full patents-company record in the Signal API and MCP can also have these 8 fields. Some fields are empty for some signals.

Company

  • linkedin_urlValue in the API
  • industriesValue in the API
  • employee_count_lowValue in the API
  • employee_count_highValue in the API
  • revenueValue in the API
  • descriptionValue in the API

Signal

  • signal_nameValue in the API
  • associationValue in the API
Show the full JSONThe record on this page and the API request

GET /v1/signals/11a24b13-badf-5f45-91c1-bdca0cebc770 returns this record as JSON. POST /v1/companies/enrich returns every signal for arm.com.

{
  "signal_id": "11a24b13-badf-5f45-91c1-bdca0cebc770",
  "signal_type": "patents-company",
  "signal_subtype": "patentGrant",
  "detected_at": "2026-11-18T15:31:56+00:00",
  "company": {
    "name": "Arm",
    "domain": "arm.com"
  },
  "data": {
    "cpc": [
      {
        "code": "G06F 17/16",
        "label": "Electric digital data processing"
      },
      {
        "code": "G06F 5/01",
        "label": "Electric digital data processing"
      },
      {
        "code": "G06F 7/501",
        "label": "Electric digital data processing"
      },
      {
        "code": "G06F 7/523",
        "label": "Electric digital data processing"
      },
      {
        "code": "G06F 7/5443",
        "label": "Electric digital data processing"
      }
    ],
    "tags": [
      "Intellectual Property",
      "Research & Development",
      "Artificial Intelligence",
      "Engineering"
    ],
    "detail": "In November 2026 Arm patented a processor design for efficient AI and data-processing calculations across hardware such as smartphones, servers, and embedded systems.",
    "summary": "Arm was granted a patent for a flexible matrix-multiplication accelerator.",
    "event_at": "2026-11-17",
    "inventors": [
      {
        "name": "Zhi-Gang Liu",
        "status": "unresolved",
        "is_primary": true
      },
      {
        "name": "Paul Nicholas Whatmough",
        "status": "unresolved",
        "is_primary": false
      },
      {
        "name": "Matthew Mattina",
        "status": "resolved",
        "is_primary": false,
        "linkedin_url": "https://www.linkedin.com/in/matthewmattina"
      },
      {
        "name": "John Fremont Brown, III",
        "status": "unresolved",
        "is_primary": false
      }
    ],
    "tech_area": "software / computing",
    "event_kind": "grant_date",
    "grant_date": "2026-11-17",
    "source_url": "https://patents.google.com/patent/US12801689",
    "cpc_primary": {
      "code": "G06F 17/16",
      "label": "Electric digital data processing"
    },
    "patent_title": "Matrix multiply accelerator for variable bitwidth operands",
    "patent_number": "US12801689",
    "uspto_assignee": "Arm Limited",
    "patent_abstract": "A processor, computer based method and apparatus for performing matrix multiplication are provided. The processor obtains a first bitslice vector comprising m elements, obtains a second bitslice vector comprising n elements, provides at least one element of the first bitslice vector as a first input to a single bit dot product unit, provides at least one element of the second bit-slice vector as a second input to the single-bit dot product unit, and obtains, from the single-bit dot product unit, an output comprising at least a partial dot product of the first and second bitslice vectors.",
    "precision_class": "structural",
    "invention_explanation": "A hardware engine breaks numbers into individual bit layers and combines them with one-bit dot products, supporting calculations with different number precisions.",
    "technologies_mentioned": [
      "matrix multiplication",
      "AI accelerators",
      "bit-slice processing",
      "processor architecture"
    ]
  }
}

Long text fields are shortened on this page.

Looking up one signal by its id is free. Enrich costs 2 credits per signal returned; a call with no results is free.