JP2025514088A - 処理要素のアレイを含む畳み込みエンジンを使用して実行される行列乗算 - Google Patents

処理要素のアレイを含む畳み込みエンジンを使用して実行される行列乗算 Download PDF

Info

Publication number
JP2025514088A
JP2025514088A JP2024562065A JP2024562065A JP2025514088A JP 2025514088 A JP2025514088 A JP 2025514088A JP 2024562065 A JP2024562065 A JP 2024562065A JP 2024562065 A JP2024562065 A JP 2024562065A JP 2025514088 A JP2025514088 A JP 2025514088A
Authority
JP
Japan
Prior art keywords
matrix
processor
processing elements
processing
multiplication
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
JP2024562065A
Other languages
English (en)
Japanese (ja)
Other versions
JP2025514088A5 (https=
Inventor
サチデフ，ガガンディープ
サッソーネ，ピーター
タヌミハルジョ，ジェレミー
Original Assignee
テスラ，インコーポレイテッド
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by テスラ，インコーポレイテッド filed Critical テスラ，インコーポレイテッド
Publication of JP2025514088A publication Critical patent/JP2025514088A/ja
Publication of JP2025514088A5 publication Critical patent/JP2025514088A5/ja
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/15—Correlation function computation including computation of convolution operations
    • G06F17/153—Multidimensional correlation or convolution
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F7/00—Methods or arrangements for processing data by operating upon the order or content of the data handled
    • G06F7/38—Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation
    • G06F7/48—Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation using non-contact-making devices, e.g. tube, solid state device; using unspecified devices
    • G06F7/544—Methods or arrangements for performing computations using exclusively denominational number representation, e.g. using binary, ternary, decimal representation using non-contact-making devices, e.g. tube, solid state device; using unspecified devices for evaluating functions by calculation
    • G06F7/5443—Sum of products

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Theoretical Computer Science (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Algebra (AREA)
  • Software Systems (AREA)
  • Databases & Information Systems (AREA)
  • Complex Calculations (AREA)
JP2024562065A 2022-04-29 2023-04-27 処理要素のアレイを含む畳み込みエンジンを使用して実行される行列乗算 Pending JP2025514088A (ja)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US202263336586P 2022-04-29 2022-04-29
US63/336,586 2022-04-29
PCT/US2023/020213 WO2023212203A1 (en) 2022-04-29 2023-04-27 Matrix multiplication performed using convolution engine which includes array of processing elements

Publications (2)

Publication Number Publication Date
JP2025514088A true JP2025514088A (ja) 2025-05-02
JP2025514088A5 JP2025514088A5 (https=) 2026-04-30

Family

ID=86469086

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2024562065A Pending JP2025514088A (ja) 2022-04-29 2023-04-27 処理要素のアレイを含む畳み込みエンジンを使用して実行される行列乗算

Country Status (6)

Country Link
US (1) US20250284767A1 (https=)
EP (1) EP4515426A1 (https=)
JP (1) JP2025514088A (https=)
KR (1) KR20250002449A (https=)
CN (1) CN119278445A (https=)
WO (1) WO2023212203A1 (https=)

Family Cites Families (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11157287B2 (en) 2017-07-24 2021-10-26 Tesla, Inc. Computational array microprocessor system with variable latency memory access
US11157441B2 (en) 2017-07-24 2021-10-26 Tesla, Inc. Computational array microprocessor system using non-consecutive data formatting
US11409692B2 (en) 2017-07-24 2022-08-09 Tesla, Inc. Vector computational unit
US11256977B2 (en) * 2017-12-29 2022-02-22 Facebook, Inc. Lowering hardware for neural networks
EP3674982A1 (en) * 2018-12-27 2020-07-01 IMEC vzw Hardware accelerator architecture for convolutional neural network

Also Published As

Publication number Publication date
US20250284767A1 (en) 2025-09-11
WO2023212203A1 (en) 2023-11-02
CN119278445A (zh) 2025-01-07
KR20250002449A (ko) 2025-01-07
EP4515426A1 (en) 2025-03-05

Similar Documents

Publication Publication Date Title
US12174910B2 (en) Methods and systems for implementing a convolution transpose layer of a neural network
US11698773B2 (en) Accelerated mathematical engine
JP7271820B2 (ja) 行列乗算アクセラレータ（ｍｍａ）を用いる基本計算原始関数の実装
TW202123093A (zh) 實行卷積運算的系統及方法
KR20200081044A (ko) 뉴럴 네트워크의 컨볼루션 연산을 처리하는 방법 및 장치
US11899741B2 (en) Memory device and method
EP3093757B1 (en) Multi-dimensional sliding window operation for a vector processor
EP3690757B1 (en) Method and apparatus with convolution neural network processing
JP2025514088A (ja) 処理要素のアレイを含む畳み込みエンジンを使用して実行される行列乗算
EP4425419A1 (en) Methods and systems for performing a sparse submanifold convolution on a gpu
JP2025507845A (ja) 最大プーリングを含む畳み込みニューラルネットワーク処理のための効率的な積和演算ユニット
CN113554092A (zh) 基于R2Net的水下鱼类目标检测方法、装置及存储介质
GB2598918A (en) Downscaler and method of downscaling
US20240160692A1 (en) Implementing a scatter function on a neural network accelerator
US20250307206A1 (en) Efficient selection of single instruction multiple data operations for neural processing units

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20260421

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20260421