TWI699712B - 用於執行神經網路運算之方法及系統及相關非暫時性機器可讀儲存裝置 - Google Patents

用於執行神經網路運算之方法及系統及相關非暫時性機器可讀儲存裝置 Download PDF

Info

Publication number
TWI699712B
TWI699712B TW108119004A TW108119004A TWI699712B TW I699712 B TWI699712 B TW I699712B TW 108119004 A TW108119004 A TW 108119004A TW 108119004 A TW108119004 A TW 108119004A TW I699712 B TWI699712 B TW I699712B
Authority
TW
Taiwan
Prior art keywords
layer
neural network
super
layers
batch
Prior art date
Application number
TW108119004A
Other languages
English (en)
Chinese (zh)
Other versions
TW201937416A (zh
Inventor
禹同爀
Original Assignee
美商谷歌有限責任公司
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 美商谷歌有限責任公司 filed Critical 美商谷歌有限責任公司
Publication of TW201937416A publication Critical patent/TW201937416A/zh
Application granted granted Critical
Publication of TWI699712B publication Critical patent/TWI699712B/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
    • G06N3/063—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/042—Knowledge-based neural networks; Logical representations of neural networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/48—Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/48—Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5011—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
    • G06F9/5016—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals the resource being the memory
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0464—Convolutional networks [CNN, ConvNet]
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/0499—Feedforward networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/10—Interfaces, programming languages or software development kits, e.g. for simulating neural networks
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computing Systems (AREA)
  • Artificial Intelligence (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Strategic Management (AREA)
  • Neurology (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Marketing (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Tourism & Hospitality (AREA)
  • General Business, Economics & Management (AREA)
  • Educational Administration (AREA)
  • Design And Manufacture Of Integrated Circuits (AREA)
  • Image Analysis (AREA)
  • Semiconductor Memories (AREA)
  • Memory System (AREA)
TW108119004A 2017-05-19 2018-02-09 用於執行神經網路運算之方法及系統及相關非暫時性機器可讀儲存裝置 TWI699712B (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US15/599,559 2017-05-19
US15/599,559 US10019668B1 (en) 2017-05-19 2017-05-19 Scheduling neural network processing

Publications (2)

Publication Number Publication Date
TW201937416A TW201937416A (zh) 2019-09-16
TWI699712B true TWI699712B (zh) 2020-07-21

Family

ID=61157323

Family Applications (2)

Application Number Title Priority Date Filing Date
TW108119004A TWI699712B (zh) 2017-05-19 2018-02-09 用於執行神經網路運算之方法及系統及相關非暫時性機器可讀儲存裝置
TW107104603A TWI664587B (zh) 2017-05-19 2018-02-09 排程神經網路處理

Family Applications After (1)

Application Number Title Priority Date Filing Date
TW107104603A TWI664587B (zh) 2017-05-19 2018-02-09 排程神經網路處理

Country Status (7)

Country Link
US (4) US10019668B1 (cg-RX-API-DMAC7.html)
EP (1) EP3577605B1 (cg-RX-API-DMAC7.html)
JP (2) JP7025441B2 (cg-RX-API-DMAC7.html)
KR (1) KR102346636B1 (cg-RX-API-DMAC7.html)
CN (2) CN117291239A (cg-RX-API-DMAC7.html)
TW (2) TWI699712B (cg-RX-API-DMAC7.html)
WO (1) WO2018212799A1 (cg-RX-API-DMAC7.html)

Families Citing this family (93)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11437032B2 (en) 2017-09-29 2022-09-06 Shanghai Cambricon Information Technology Co., Ltd Image processing apparatus and method
US11164074B2 (en) 2018-02-08 2021-11-02 Western Digital Technologies, Inc. Multi-core systolic processor system for neural network processing
US11769042B2 (en) 2018-02-08 2023-09-26 Western Digital Technologies, Inc. Reconfigurable systolic neural network engine
US11507370B2 (en) 2018-02-13 2022-11-22 Cambricon (Xi'an) Semiconductor Co., Ltd. Method and device for dynamically adjusting decimal point positions in neural network computations
EP3651075B1 (en) 2018-02-13 2021-10-27 Shanghai Cambricon Information Technology Co., Ltd Computation device and method
US11630666B2 (en) 2018-02-13 2023-04-18 Shanghai Cambricon Information Technology Co., Ltd Computing device and method
CN110162162B (zh) 2018-02-14 2023-08-18 上海寒武纪信息科技有限公司 处理器的控制装置、方法及设备
US11475306B2 (en) 2018-03-22 2022-10-18 Amazon Technologies, Inc. Processing for multiple input data sets
JP6961640B2 (ja) * 2018-03-22 2021-11-05 南京地平▲線▼机▲器▼人技▲術▼有限公司 データ処理のシステムおよび方法
US11461631B2 (en) * 2018-03-22 2022-10-04 Amazon Technologies, Inc. Scheduling neural network computations based on memory capacity
CN109313673A (zh) * 2018-04-17 2019-02-05 深圳鲲云信息科技有限公司 网络模型的运行方法及相关产品
US11562213B2 (en) * 2018-04-17 2023-01-24 Intel Corporation Methods and arrangements to manage memory in cascaded neural networks
WO2019218896A1 (zh) 2018-05-18 2019-11-21 上海寒武纪信息科技有限公司 计算方法以及相关产品
US10970120B2 (en) 2018-06-26 2021-04-06 Advanced Micro Devices, Inc. Method and system for opportunistic load balancing in neural networks using metadata
JP7053891B2 (ja) 2018-06-27 2022-04-12 シャンハイ カンブリコン インフォメーション テクノロジー カンパニー リミテッド オンチップコードのブレークポイントによるデバッグ方法、オンチッププロセッサ及びブレークポイントによるチップデバッグシステム
CN110728364B (zh) 2018-07-17 2024-12-17 上海寒武纪信息科技有限公司 一种运算装置和运算方法
CN109117949A (zh) * 2018-08-01 2019-01-01 南京天数智芯科技有限公司 用于人工智能设备的灵活数据流处理器和处理方法
EP3757896B1 (en) * 2018-08-28 2023-01-11 Cambricon Technologies Corporation Limited Method and device for pre-processing data in a neural network
EP3844620B9 (en) * 2018-08-29 2025-03-19 Qualcomm Incorporated Method, apparatus, and system for an architecture for machine learning acceleration
CN110956252B (zh) * 2018-09-27 2025-09-16 第四范式(北京)技术有限公司 执行多个神经网络的计算的方法和计算装置
WO2020062392A1 (zh) 2018-09-28 2020-04-02 上海寒武纪信息科技有限公司 信号处理装置、信号处理方法及相关产品
US11263529B2 (en) * 2018-10-10 2022-03-01 Google Llc Modifying machine learning models to improve locality
CN111383637A (zh) 2018-12-28 2020-07-07 上海寒武纪信息科技有限公司 信号处理装置、信号处理方法及相关产品
JP7379821B2 (ja) * 2019-01-09 2023-11-15 日本電信電話株式会社 推論処理装置および推論処理方法
US12254400B2 (en) * 2019-01-10 2025-03-18 Mipsology SAS Optimizing artificial neural network computations based on automatic determination of a batch size
US11586929B2 (en) 2019-02-15 2023-02-21 Wipro Limited Method and system for optimizing memory requirement for training an artificial neural network model
CN111667046A (zh) * 2019-03-08 2020-09-15 富泰华工业(深圳)有限公司 深度学习加速方法及用户终端
US10929058B2 (en) 2019-03-25 2021-02-23 Western Digital Technologies, Inc. Enhanced memory device architecture for machine learning
US11783176B2 (en) 2019-03-25 2023-10-10 Western Digital Technologies, Inc. Enhanced storage device memory architecture for machine learning
US20200334522A1 (en) 2019-04-18 2020-10-22 Cambricon Technologies Corporation Limited Data processing method and related products
CN111831543B (zh) 2019-04-18 2024-07-16 中科寒武纪科技股份有限公司 一种数据处理方法及相关产品
US11175898B2 (en) * 2019-05-31 2021-11-16 Apple Inc. Compiling code for a machine learning model for execution on a specialized processor
US20220327405A1 (en) * 2019-06-05 2022-10-13 Nippon Telegraph And Telephone Corporation Inference Processing Apparatus and Inference Processing Method
CN112085193B (zh) 2019-06-12 2024-03-29 上海寒武纪信息科技有限公司 一种神经网络的量化参数确定方法及相关产品
US11676028B2 (en) 2019-06-12 2023-06-13 Shanghai Cambricon Information Technology Co., Ltd Neural network quantization parameter determination method and related products
CN114008636B (zh) * 2019-06-18 2025-01-17 高通股份有限公司 优化机器学习模型性能
US20220365782A1 (en) * 2019-07-03 2022-11-17 Huaxia General Processor Technologies Inc. Instructions for operating accelerator circuit
US11436019B2 (en) 2019-07-15 2022-09-06 Microsoft Technology Licensing, Llc Data parallelism in distributed training of artificial intelligence models
US11354579B2 (en) * 2019-07-15 2022-06-07 Microsoft Technology Licensing, Llc Dynamic multi-layer execution for artificial intelligence modeling
US11520592B2 (en) * 2019-07-15 2022-12-06 Microsoft Technology Licensing, Llc Executing large artificial intelligence models on memory-constrained devices
US12455762B2 (en) 2019-08-16 2025-10-28 Google Llc Explicit scheduling of on-chip operations
JP7146954B2 (ja) 2019-08-23 2022-10-04 安徽寒武紀信息科技有限公司 データ処理方法、装置、コンピュータデバイス、及び記憶媒体
WO2021036904A1 (zh) 2019-08-23 2021-03-04 安徽寒武纪信息科技有限公司 数据处理方法、装置、计算机设备和存储介质
US12165039B2 (en) 2019-08-23 2024-12-10 Anhui Cambricon Information Technology Co., Ltd. Neural network quantization data processing method, device, computer equipment and storage medium
CN112434781B (zh) 2019-08-26 2024-09-10 上海寒武纪信息科技有限公司 用于处理数据的方法、装置以及相关产品
EP4024280A4 (en) 2019-08-27 2022-11-16 Anhui Cambricon Information Technology Co., Ltd. DATA PROCESSING METHOD AND EQUIPMENT, COMPUTER EQUIPMENT AND STORAGE MEDIA
US11573828B2 (en) * 2019-09-16 2023-02-07 Nec Corporation Efficient and scalable enclave protection for machine learning programs
US11651209B1 (en) 2019-10-02 2023-05-16 Google Llc Accelerated embedding layer computations
DE102019127795A1 (de) * 2019-10-15 2021-04-15 Infineon Technologies Ag Schaltung und ein Verfahren zum Bestimmen einer Lage eines Magneten und Joystick
CN110515739B (zh) * 2019-10-23 2020-01-31 上海燧原智能科技有限公司 深度学习神经网络模型负载计算方法、装置、设备及介质
US12379933B2 (en) * 2019-10-25 2025-08-05 Samsung Electronics Co., Ltd. Ultra pipelined accelerator for machine learning inference
CN110796245B (zh) * 2019-10-25 2022-03-22 浪潮电子信息产业股份有限公司 卷积神经网络模型的计算方法及装置
CN112862085B (zh) * 2019-11-27 2023-08-22 杭州海康威视数字技术股份有限公司 存储空间优化方法及装置
EP4693101A3 (en) * 2019-12-18 2026-04-15 Google Llc Parameter caching for neural network accelerators
CN111338816B (zh) * 2020-02-18 2023-05-12 深圳鲲云信息科技有限公司 基于神经网络的指令交互方法、系统、设备及存储介质
CN113298843B (zh) 2020-02-24 2024-05-14 中科寒武纪科技股份有限公司 数据量化处理方法、装置、电子设备和存储介质
CN113408717B (zh) 2020-03-17 2025-09-09 安徽寒武纪信息科技有限公司 计算装置、方法、板卡和计算机可读存储介质
CN113408716B (zh) 2020-03-17 2025-06-24 安徽寒武纪信息科技有限公司 计算装置、方法、板卡和计算机可读存储介质
JP6834097B1 (ja) * 2020-05-15 2021-02-24 エッジコーティックス ピーティーイー. リミテッド 推論のニューラルネットワークアクセラレータのハードウェア固有分割
EP4148627A4 (en) * 2020-05-29 2023-06-28 Huawei Technologies Co., Ltd. Neural network scheduling method and apparatus
WO2021243489A1 (zh) * 2020-05-30 2021-12-09 华为技术有限公司 一种神经网络的数据处理方法及装置
KR102860886B1 (ko) * 2020-06-01 2025-09-18 삼성전자주식회사 스케줄러, 스케줄러의 동작 방법 및 이를 포함한 가속기 시스템
US11288097B2 (en) * 2020-06-12 2022-03-29 Disney Enterprises, Inc. Automated hardware resource optimization
US20220012635A1 (en) * 2020-06-18 2022-01-13 Texas Instruments Incorporated Analytic techniques for improved super tiling machine learning processing
JP7719106B2 (ja) * 2020-07-02 2025-08-05 インターデイジタル パテント ホールディングス インコーポレイテッド トポロジフレンドリ表現を用いたグラフ条件付きオートエンコーダ(gcae)のための方法、装置、及びシステム
KR102726172B1 (ko) * 2020-08-21 2024-11-05 주식회사 딥엑스 신경망 프로세싱 유닛을 포함하는 전자 장치
KR102299084B1 (ko) * 2020-08-24 2021-09-07 오픈엣지테크놀로지 주식회사 하드웨어 가속기의 출력 데이터를 메모리에 저장하는 방법, 하드웨어 가속기의 입력 데이터를 메모리로부터 읽는 방법, 및 이를 위한 하드웨어 가속기
KR102384587B1 (ko) * 2020-08-25 2022-04-08 오픈엣지테크놀로지 주식회사 하드웨어 가속기의 출력 데이터를 압축하는 방법, 하드웨어 가속기로의 입력 데이터를 디코딩하는 방법, 및 이를 위한 하드웨어 가속기
KR102942129B1 (ko) * 2020-08-27 2026-03-23 에스케이하이닉스 주식회사 가속 장치, 데이터 저장 장치, 데이터 처리 시스템 및 가속 장치의 동작방법
KR102883346B1 (ko) * 2020-09-09 2025-11-07 삼성전자주식회사 호스트 프로세서 및 가속기의 동작 방법 및 이들을 포함한 전자 장치
CN116324812A (zh) * 2020-12-02 2023-06-23 阿里巴巴集团控股有限公司 神经网络近记忆处理
KR20220078290A (ko) * 2020-12-03 2022-06-10 삼성전자주식회사 뉴럴 네트워크 연산 스케줄링 방법 및 장치
US11734072B2 (en) * 2020-12-31 2023-08-22 Nuvolo Technologies Corporation Stream-based job processing
US12645910B2 (en) 2021-01-15 2026-06-02 Google Llc Neural architecture scaling for hardware accelerators
TWI900601B (zh) * 2021-01-15 2025-10-11 美商谷歌有限責任公司 用於硬體加速器之神經架構縮放之電腦實施方法、系統及非暫時性電腦可讀儲存媒體
KR102951346B1 (ko) 2021-03-03 2026-04-10 삼성전자주식회사 이종 하드웨어 타입의 가속기들을 포함한 전자 장치
US11511772B2 (en) 2021-04-30 2022-11-29 Deepx Co., Ltd. NPU implemented for artificial neural networks to process fusion of heterogeneous data received from heterogeneous sensors
KR102506613B1 (ko) * 2021-04-30 2023-03-06 주식회사 딥엑스 이종의 센서로 제공되는 이종의 데이터를 처리하기 위한 퓨전-인공신경망을 위해 구현되는 npu
EP4099609A1 (en) * 2021-06-04 2022-12-07 Zama SAS Computational network conversion for fully homomorphic evaluation
DE112021007213T5 (de) * 2021-06-18 2024-01-04 Nvidia Corporation Neuronale Netzauswertung
WO2023284347A1 (zh) * 2021-07-16 2023-01-19 华为云计算技术有限公司 任务执行方法及装置
US12450478B2 (en) * 2021-09-10 2025-10-21 Maxim Integrated Products, Inc. Dynamic data-dependent neural network processing systems and methods
EP4371035A1 (en) * 2021-09-17 2024-05-22 Google Llc Performing segmented inference operations of a machine learning model
US11657260B2 (en) * 2021-10-26 2023-05-23 Edgecortix Pte. Ltd. Neural network hardware accelerator data parallelism
TWI802070B (zh) * 2021-11-03 2023-05-11 大陸商星宸科技股份有限公司 積體電路及其配置方法
US20230153583A1 (en) * 2021-11-15 2023-05-18 Xilinx, Inc. Compilation of neural networks into subgraphs for processing by multiple compute circuits
US11442775B1 (en) * 2021-12-03 2022-09-13 FriendliAI Inc. Dynamic batching for inference system for transformer-based generation tasks
US11514370B1 (en) 2021-12-03 2022-11-29 FriendliAI Inc. Selective batching for inference system for transformer-based generation tasks
WO2023106723A1 (ko) * 2021-12-08 2023-06-15 주식회사 딥엑스 영상 융합을 위한 신경 프로세싱 유닛 및 인공신경망 시스템
KR102651559B1 (ko) * 2021-12-08 2024-03-26 주식회사 딥엑스 영상 융합을 위한 신경 프로세싱 유닛 및 인공신경망 시스템
KR20240102798A (ko) 2022-12-26 2024-07-03 리벨리온 주식회사 뉴럴 프로세서 및 이의 명령어 페치 방법
KR102548582B1 (ko) * 2022-12-26 2023-06-29 리벨리온 주식회사 뉴럴 프로세서 및 이의 명령어 페치 방법
US20240256285A1 (en) * 2023-01-31 2024-08-01 Microsoft Technology Licensing, Llc Parallelizing multi-phase kernels with cross-phase dependency on heterogenous hardware

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW201525742A (zh) * 2013-10-24 2015-07-01 Solido Design Automation Inc 用於處理及環境變化之快速巢狀迴路電路驗證之方法及系統以及分層電路
US20160335119A1 (en) * 2015-05-12 2016-11-17 minds.ai inc Batch-based neural network system
WO2017075346A1 (en) * 2015-10-28 2017-05-04 Google Inc. Modifying computational graphs

Family Cites Families (31)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US7089185B2 (en) 2002-06-27 2006-08-08 Intel Corporation Embedded multi-layer coupled hidden Markov model
US7171043B2 (en) 2002-10-11 2007-01-30 Intel Corporation Image recognition using hidden markov models and coupled hidden markov models
US7203368B2 (en) 2003-01-06 2007-04-10 Intel Corporation Embedded bayesian network for pattern recognition
KR100486735B1 (ko) 2003-02-28 2005-05-03 삼성전자주식회사 최적구획 분류신경망 구성방법과 최적구획 분류신경망을이용한 자동 레이블링방법 및 장치
US7639727B1 (en) * 2004-10-05 2009-12-29 Cingular Wireless Ii, L.L.C. System and method for selecting wireless signal bandwidth based on signal strength measurements provided by wireless receivers
TWI525558B (zh) * 2011-01-17 2016-03-11 Univ Nat Taipei Technology Resilient high - speed hardware reverse transfer and feedback type neural network system
US8462018B1 (en) * 2011-05-26 2013-06-11 Rockwell Collins, Inc. Systems and method for controlling the simultaneous display of multi-level classified information on the same surface of an aircraft display unit
US8725658B2 (en) * 2011-09-21 2014-05-13 Brain Corporation Elementary network description for efficient memory management in neuromorphic systems
US8914315B2 (en) * 2012-01-27 2014-12-16 International Business Machines Corporation Multi-compartment neuron suitable for implementation in a distributed hardware model by reducing communication bandwidth
US9477925B2 (en) 2012-11-20 2016-10-25 Microsoft Technology Licensing, Llc Deep neural networks training for speech and pattern recognition
US10095917B2 (en) 2013-11-04 2018-10-09 Facebook, Inc. Systems and methods for facial representation
US20160026912A1 (en) * 2014-07-22 2016-01-28 Intel Corporation Weight-shifting mechanism for convolutional neural networks
EP3035204B1 (en) * 2014-12-19 2018-08-15 Intel Corporation Storage device and method for performing convolution operations
US10083395B2 (en) * 2015-05-21 2018-09-25 Google Llc Batch processing in a neural network processor
US10438117B1 (en) * 2015-05-21 2019-10-08 Google Llc Computing convolutions using a neural network processor
US10049322B2 (en) * 2015-05-21 2018-08-14 Google Llc Prefetching weights for use in a neural network processor
US9747546B2 (en) * 2015-05-21 2017-08-29 Google Inc. Neural network processor
CN107690663B (zh) * 2015-06-05 2022-04-12 渊慧科技有限公司 白化神经网络层
US10387770B2 (en) 2015-06-10 2019-08-20 Samsung Electronics Co., Ltd. Spiking neural network with reduced memory access and reduced in-network bandwidth consumption
EP3104309B1 (en) * 2015-06-10 2020-04-01 Samsung Electronics Co., Ltd. Spiking neural network with reduced memory access and reduced in-network bandwidth consumption
US9582726B2 (en) * 2015-06-24 2017-02-28 Qualcomm Incorporated Systems and methods for image processing in a deep convolution network
US10452971B2 (en) 2015-06-29 2019-10-22 Microsoft Technology Licensing, Llc Deep neural network partitioning on servers
CN106599989B (zh) * 2015-10-08 2019-04-09 上海兆芯集成电路有限公司 神经网络单元和神经处理单元阵列
US20170154262A1 (en) * 2015-11-30 2017-06-01 Google Inc. Resizing neural networks
CN105426517B (zh) * 2015-12-02 2020-02-18 上海越峰信息科技有限公司 一种具有图像处理功能的智能存储设备
US10482380B2 (en) * 2015-12-30 2019-11-19 Amazon Technologies, Inc. Conditional parallel processing in fully-connected neural networks
CN105719000B (zh) * 2016-01-21 2018-02-16 广西师范大学 一种神经元硬件装置及用这种装置模拟脉冲神经网络的方法
KR102459854B1 (ko) * 2016-05-26 2022-10-27 삼성전자주식회사 심층 신경망용 가속기
AU2016203619A1 (en) * 2016-05-31 2017-12-14 Canon Kabushiki Kaisha Layer-based operations scheduling to optimise memory for CNN applications
CN106250103A (zh) * 2016-08-04 2016-12-21 东南大学 一种卷积神经网络循环卷积计算数据重用的系统
US10922610B2 (en) * 2017-09-14 2021-02-16 Intel Corporation Synchronization scheduler of distributed neural network training

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW201525742A (zh) * 2013-10-24 2015-07-01 Solido Design Automation Inc 用於處理及環境變化之快速巢狀迴路電路驗證之方法及系統以及分層電路
US20160335119A1 (en) * 2015-05-12 2016-11-17 minds.ai inc Batch-based neural network system
WO2017075346A1 (en) * 2015-10-28 2017-05-04 Google Inc. Modifying computational graphs

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
Jeffrey Dean ET AL:"Large scale distributed deep networks",The 26th annual conference on Neural Information Processing Systems,6 December 2012,page 1- 9,URL:http://papers.nips.cc/paper/4687-large-scaledistributed-deep-networks.pdf *
Jeffrey Dean ET AL:"Large scale distributed deep networks",The 26th annual conference on Neural Information Processing Systems,6 December 2012,page 1- 9,URL:http://papers.nips.cc/paper/4687-large-scaledistributed-deep-networks.pdf。

Also Published As

Publication number Publication date
TW201937416A (zh) 2019-09-16
JP2020521195A (ja) 2020-07-16
US20180373976A1 (en) 2018-12-27
JP2022070955A (ja) 2022-05-13
US20220156557A1 (en) 2022-05-19
US10019668B1 (en) 2018-07-10
JP7025441B2 (ja) 2022-02-24
CN110447044A (zh) 2019-11-12
TW201901534A (zh) 2019-01-01
EP3577605B1 (en) 2024-12-18
CN117291239A (zh) 2023-12-26
US20250209302A1 (en) 2025-06-26
TWI664587B (zh) 2019-07-01
JP7439149B2 (ja) 2024-02-27
CN110447044B (zh) 2023-10-10
US12254394B2 (en) 2025-03-18
KR20190118635A (ko) 2019-10-18
KR102346636B1 (ko) 2022-01-03
WO2018212799A1 (en) 2018-11-22
EP3577605A1 (en) 2019-12-11
US11157794B2 (en) 2021-10-26

Similar Documents

Publication Publication Date Title
JP7439149B2 (ja) ニューラルネットワーク処理のスケジューリング
JP7792455B2 (ja) ニューラルネットワーク計算ユニットにおける入力データのスパース性の活用
Zhang et al. BoostGCN: A framework for optimizing GCN inference on FPGA
EP3480745B1 (en) Hardware implementation of convolution layer of deep neural network
US10740674B2 (en) Layer-based operations scheduling to optimise memory for CNN applications
CN107437110B (zh) 卷积神经网络的分块卷积优化方法及装置
KR102765048B1 (ko) 신경 네트워크 명령어 세트 아키텍처
JP2025516768A (ja) 機械学習ハードウェアアクセラレータにおけるデータスパース性の活用
WO2023278126A1 (en) Accelerated processing device and method of sharing data for machine learning
Erdem et al. Runtime design space exploration and mapping of DCNNs for the ultra-low-power Orlando SoC
JP7837470B2 (ja) ハードウェアアクセラレータにおけるメモリバンク競合の低減
Gimenes et al. AMPLE: Event-Driven Accelerator for Mixed-Precision Inference of Graph Neural Networks
Wang et al. Sh-gat: software-hardware co-design for accelerating graph attention networks on fpga
CN113159272A (zh) 一种用于处理神经网络的方法和系统
KR20210113762A (ko) 연산량에 따른 가변 데이터 동작 주파수 기반 인공지능 연산기 시스템
CN116029890B (zh) 一种神经网络增强的图形处理器流水线架构
BOESCH et al. Runtime Design Space Exploration and Mapping of DCNNs for the Ultra-Low-Power Orlando SoC
Wen et al. Dynamic co-operative intelligent memory
Zhao et al. Issm: An Incremental Space Search Method for Loop Unrolling Parameters in Fpga-Based Cnn Accelerators