[go: up one dir, main page]

PL3671439T3 - Optymalizacje obliczeniowe dla sieci neuronowych - Google Patents

Optymalizacje obliczeniowe dla sieci neuronowych

Info

Publication number
PL3671439T3
PL3671439T3 PL20155873.1T PL20155873T PL3671439T3 PL 3671439 T3 PL3671439 T3 PL 3671439T3 PL 20155873 T PL20155873 T PL 20155873T PL 3671439 T3 PL3671439 T3 PL 3671439T3
Authority
PL
Poland
Prior art keywords
neural networks
optimizations
compute
compute optimizations
neural
Prior art date
Application number
PL20155873.1T
Other languages
English (en)
Inventor
Kevin Nealis
Anbang YAO
Xiaoming Chen
Elmoustapha OULD-AHMED-VALL
Sara S. Baghsorkhi
Eriko Nurvitadhi
Balaji Vembu
Nicolas C. Galoppo Von Borries
Rajkishore Barik
Tsung-Han Lin
Kamal SINHA
Original Assignee
Intel Corporation
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 Intel Corporation filed Critical Intel Corporation
Publication of PL3671439T3 publication Critical patent/PL3671439T3/pl

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F5/00—Methods or arrangements for data conversion without changing the order or content of the data handled
    • G06F5/01—Methods or arrangements for data conversion without changing the order or content of the data handled for shifting, e.g. justifying, scaling, normalising
    • G06F5/015—Methods or arrangements for data conversion without changing the order or content of the data handled for shifting, e.g. justifying, scaling, normalising having at least two separately controlled shifting levels, e.g. using shifting matrices
    • 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
    • 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
    • G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/30003—Arrangements for executing specific machine instructions
    • G06F9/30007—Arrangements for executing specific machine instructions to perform operations on data operands
    • G06F9/3001—Arithmetic instructions
    • 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
    • G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/38—Concurrent instruction execution, e.g. pipeline or look ahead
    • G06F9/3836—Instruction issuing, e.g. dynamic instruction scheduling or out of order instruction execution
    • G06F9/3851—Instruction issuing, e.g. dynamic instruction scheduling or out of order instruction execution from multiple instruction streams, e.g. multistreaming
    • 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
    • G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/38—Concurrent instruction execution, e.g. pipeline or look ahead
    • G06F9/3885—Concurrent instruction execution, e.g. pipeline or look ahead using a plurality of independent parallel functional units
    • G06F9/3887—Concurrent instruction execution, e.g. pipeline or look ahead using a plurality of independent parallel functional units controlled by a single instruction for multiple data lanes [SIMD]
    • 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
    • G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/38—Concurrent instruction execution, e.g. pipeline or look ahead
    • G06F9/3885—Concurrent instruction execution, e.g. pipeline or look ahead using a plurality of independent parallel functional units
    • G06F9/3888—Concurrent instruction execution, e.g. pipeline or look ahead using a plurality of independent parallel functional units controlled by a single instruction for multiple threads [SIMT] in parallel
    • 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
    • G06F9/30—Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/38—Concurrent instruction execution, e.g. pipeline or look ahead
    • G06F9/3885—Concurrent instruction execution, e.g. pipeline or look ahead using a plurality of independent parallel functional units
    • G06F9/3893—Concurrent instruction execution, e.g. pipeline or look ahead using a plurality of independent parallel functional units controlled in tandem, e.g. multiplier-accumulator
    • 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
    • G06N3/044—Recurrent networks, e.g. Hopfield 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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
    • 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
    • G06N3/045—Combinations of 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
    • G06N3/04—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
    • G06N3/0495—Quantised networks; Sparse networks; Compressed 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
    • G06N3/06—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
    • G06N3/08—Learning methods
    • G06N3/084—Backpropagation, e.g. using gradient descent
    • 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
    • G06N3/0895—Weakly supervised learning, e.g. semi-supervised or self-supervised learning
    • 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
    • G06N3/09—Supervised learning
    • 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
    • G06N3/098—Distributed learning, e.g. federated learning
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G06T1/20—Processor architectures; Processor configuration, e.g. pipelining
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2207/00—Indexing scheme relating to methods or arrangements for processing data by operating upon the order or content of the data handled
    • G06F2207/38—Indexing scheme relating to groups G06F7/38 - G06F7/575
    • G06F2207/48—Indexing scheme relating to groups G06F7/48 - G06F7/575
    • G06F2207/4802—Special implementations
    • G06F2207/4818—Threshold devices
    • G06F2207/4824—Neural networks

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Health & Medical Sciences (AREA)
  • Computing Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Mathematical Physics (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computational Mathematics (AREA)
  • Neurology (AREA)
  • Multimedia (AREA)
  • Image Processing (AREA)
  • Image Generation (AREA)
PL20155873.1T 2017-04-24 2018-03-23 Optymalizacje obliczeniowe dla sieci neuronowych PL3671439T3 (pl)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
US15/494,710 US10410098B2 (en) 2017-04-24 2017-04-24 Compute optimizations for neural networks

Publications (1)

Publication Number Publication Date
PL3671439T3 true PL3671439T3 (pl) 2024-07-29

Family

ID=61768108

Family Applications (1)

Application Number Title Priority Date Filing Date
PL20155873.1T PL3671439T3 (pl) 2017-04-24 2018-03-23 Optymalizacje obliczeniowe dla sieci neuronowych

Country Status (5)

Country Link
US (4) US10410098B2 (pl)
EP (2) EP3396535B1 (pl)
CN (1) CN108734285B (pl)
ES (1) ES2982454T3 (pl)
PL (1) PL3671439T3 (pl)

Families Citing this family (117)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10445894B2 (en) * 2016-05-11 2019-10-15 Mitutoyo Corporation Non-contact 3D measuring system
US11551067B2 (en) * 2017-04-06 2023-01-10 Shanghai Cambricon Information Technology Co., Ltd Neural network processor and neural network computation method
US10410098B2 (en) 2017-04-24 2019-09-10 Intel Corporation Compute optimizations for neural networks
CN109284827A (zh) * 2017-07-19 2019-01-29 阿里巴巴集团控股有限公司 神经网络计算方法、设备、处理器及计算机可读存储介质
CN109525407B (zh) * 2017-09-18 2020-05-26 中国科学院声学研究所 一种同层无交集全覆盖嵌套容器生成方法及可读存储介质
EP3660628B1 (en) * 2017-10-20 2023-12-06 Shanghai Cambricon Information Technology Co., Ltd Dynamic voltage frequency scaling device and method
US10657439B2 (en) * 2017-10-24 2020-05-19 Shanghai Cambricon Information Technology Co., Ltd Processing method and device, operation method and device
US10802489B1 (en) 2017-12-29 2020-10-13 Apex Artificial Intelligence Industries, Inc. Apparatus and method for monitoring and controlling of a neural network using another neural network implemented on one or more solid-state chips
US11488002B2 (en) * 2018-02-15 2022-11-01 Atlazo, Inc. Binary neural network accelerator engine methods and systems
US11514306B1 (en) * 2018-03-14 2022-11-29 Meta Platforms, Inc. Static memory allocation in neural networks
CN110296763B (zh) * 2018-03-23 2021-04-30 江森自控科技公司 使用循环网络进行温度传感器校准
US10621489B2 (en) * 2018-03-30 2020-04-14 International Business Machines Corporation Massively parallel neural inference computing elements
US11210586B1 (en) 2018-04-20 2021-12-28 Perceive Corporation Weight value decoder of neural network inference circuit
US11481612B1 (en) 2018-04-20 2022-10-25 Perceive Corporation Storage of input values across multiple cores of neural network inference circuit
US12093696B1 (en) 2018-04-20 2024-09-17 Perceive Corporation Bus for transporting output values of a neural network layer to cores specified by configuration data
US11222257B1 (en) 2018-04-20 2022-01-11 Perceive Corporation Non-dot product computations on neural network inference circuit
US11586910B1 (en) 2018-04-20 2023-02-21 Perceive Corporation Write cache for neural network inference circuit
US11568227B1 (en) 2018-04-20 2023-01-31 Perceive Corporation Neural network inference circuit read controller with multiple operational modes
US11783167B1 (en) 2018-04-20 2023-10-10 Perceive Corporation Data transfer for non-dot product computations on neural network inference circuit
US11049013B1 (en) 2018-04-20 2021-06-29 Perceive Corporation Encoding of weight values stored on neural network inference circuit
US11341397B1 (en) 2018-04-20 2022-05-24 Perceive Corporation Computation of neural network node
US10977338B1 (en) 2018-04-20 2021-04-13 Perceive Corporation Reduced-area circuit for dot product computation
US12033058B1 (en) * 2018-05-24 2024-07-09 Apple Inc. Iterative neural network training using quality assurance neural network
US12099912B2 (en) 2018-06-22 2024-09-24 Samsung Electronics Co., Ltd. Neural processor
CN112840353B (zh) * 2018-11-01 2023-12-29 赫尔实验室有限公司 自动生成图像并在训练中输入图像的系统、方法和介质
CN111178492B (zh) * 2018-11-09 2020-12-11 安徽寒武纪信息科技有限公司 计算装置及相关产品、执行人工神经网络模型的计算方法
CN111198673B (zh) * 2018-11-19 2022-07-12 北京智谱微科技有限责任公司 字长调整方法、装置、设备及存储介质
US12045725B1 (en) 2018-12-05 2024-07-23 Perceive Corporation Batch normalization for replicated layers of neural network
US12136039B1 (en) 2018-12-05 2024-11-05 Perceive Corporation Optimizing global sparsity for neural network
US11847567B1 (en) 2018-12-05 2023-12-19 Perceive Corporation Loss-aware replication of neural network layers
US11995533B1 (en) 2018-12-05 2024-05-28 Perceive Corporation Executing replicated neural network layers on inference circuit
CN109740733B (zh) * 2018-12-27 2021-07-06 深圳云天励飞技术有限公司 深度学习网络模型优化方法、装置及相关设备
KR102877638B1 (ko) 2019-01-09 2025-10-27 삼성전자주식회사 뉴럴 네트워크 양자화를 위한 방법 및 장치
US11347297B1 (en) 2019-01-23 2022-05-31 Perceive Corporation Neural network inference circuit employing dynamic memory sleep
KR102233174B1 (ko) * 2019-01-28 2021-03-29 포항공과대학교 산학협력단 신경망 가속기 및 그것의 동작 방법
CN109800877B (zh) * 2019-02-20 2022-12-30 腾讯科技（深圳）有限公司 神经网络的参数调整方法、装置及设备
US11074100B2 (en) * 2019-02-27 2021-07-27 Micron Technology, Inc. Arithmetic and logical operations in a multi-user network
KR102674475B1 (ko) * 2019-03-15 2024-06-12 한국전자통신연구원 복수의 뉴럴 네트워크들을 실행하기 위한 전자 장치
US12254526B2 (en) * 2019-03-15 2025-03-18 Intel Corporation On chip dense memory for temporal buffering
US11194585B2 (en) * 2019-03-25 2021-12-07 Flex Logix Technologies, Inc. Multiplier-accumulator circuitry having processing pipelines and methods of operating same
CN111767078B (zh) * 2019-04-02 2024-08-06 上海寒武纪信息科技有限公司 数据运行方法、装置和相关产品
US11671111B2 (en) 2019-04-17 2023-06-06 Samsung Electronics Co., Ltd. Hardware channel-parallel data compression/decompression
US11211944B2 (en) 2019-04-17 2021-12-28 Samsung Electronics Co., Ltd. Mixed-precision compression with random access
KR102263694B1 (ko) * 2019-04-26 2021-06-10 울산과학기술원 확률컴퓨팅 회로의 정확도를 높이기 위한 장치
US11880760B2 (en) 2019-05-01 2024-01-23 Samsung Electronics Co., Ltd. Mixed-precision NPU tile with depth-wise convolution
US12182577B2 (en) 2019-05-01 2024-12-31 Samsung Electronics Co., Ltd. Neural-processing unit tile for shuffling queued nibbles for multiplication with non-zero weight nibbles
US11256624B2 (en) 2019-05-28 2022-02-22 Micron Technology, Inc. Intelligent content migration with borrowed memory
US12436804B2 (en) * 2019-05-28 2025-10-07 Micron Technology, Inc. Memory as a service for artificial neural network (ANN) applications
KR102774094B1 (ko) * 2019-06-05 2025-03-04 삼성전자주식회사 전자 장치 및 그의 연산 수행 방법
US11669585B2 (en) * 2019-06-25 2023-06-06 Apple Inc. Optimizing binary convolutional neural networks
US12353846B2 (en) * 2019-07-09 2025-07-08 MemryX Matrix data reuse techniques in multiply and accumulate units of processing system
CN112329909B (zh) * 2019-08-05 2022-10-21 杭州海康威视数字技术股份有限公司 生成神经网络模型的方法、装置及存储介质
DE102019211829A1 (de) * 2019-08-07 2021-02-11 Robert Bosch Gmbh Recheneinheit, Verfahren und Computerprogramm zur Multiplikation
US11195095B2 (en) * 2019-08-08 2021-12-07 Neuralmagic Inc. System and method of accelerating execution of a neural network
JP7632286B2 (ja) * 2019-08-26 2025-02-19 ソニーグループ株式会社 情報処理装置、情報処理システム及び情報処理方法
US10872295B1 (en) * 2019-09-19 2020-12-22 Hong Kong Applied Science and Technology Institute Company, Limited Residual quantization of bit-shift weights in an artificial neural network
CN111492369B (zh) * 2019-09-19 2023-12-12 香港应用科技研究院有限公司 人工神经网络中移位权重的残差量化
CN110689114B (zh) * 2019-09-24 2023-07-18 Oppo广东移动通信有限公司 网络节点处理方法、装置、存储介质及电子设备
KR102726377B1 (ko) * 2019-10-23 2024-11-05 한국전자통신연구원 이진 신경망 생성 방법 및 장치
US20210125063A1 (en) * 2019-10-23 2021-04-29 Electronics And Telecommunications Research Institute Apparatus and method for generating binary neural network
US11941511B1 (en) 2019-11-11 2024-03-26 Perceive Corporation Storing of intermediate computed values for subsequent use in a machine trained network
KR102737377B1 (ko) * 2019-11-12 2024-12-03 한국전자통신연구원 다중 생체정보 기반 사용자 인증 장치 및 방법
US12039430B2 (en) * 2019-11-15 2024-07-16 Samsung Electronics Co., Ltd. Electronic device and method for inference binary and ternary neural networks
CN110942154B (zh) * 2019-11-22 2021-07-06 深圳前海微众银行股份有限公司 基于联邦学习的数据处理方法、装置、设备及存储介质
US10691133B1 (en) * 2019-11-26 2020-06-23 Apex Artificial Intelligence Industries, Inc. Adaptive and interchangeable neural networks
US11367290B2 (en) 2019-11-26 2022-06-21 Apex Artificial Intelligence Industries, Inc. Group of neural networks ensuring integrity
US11366434B2 (en) 2019-11-26 2022-06-21 Apex Artificial Intelligence Industries, Inc. Adaptive and interchangeable neural networks
US10956807B1 (en) 2019-11-26 2021-03-23 Apex Artificial Intelligence Industries, Inc. Adaptive and interchangeable neural networks utilizing predicting information
US12081646B2 (en) 2019-11-26 2024-09-03 Apex Ai Industries, Llc Adaptively controlling groups of automated machines
US11119772B2 (en) 2019-12-06 2021-09-14 International Business Machines Corporation Check pointing of accumulator register results in a microprocessor
US12112141B2 (en) 2019-12-12 2024-10-08 Samsung Electronics Co., Ltd. Accelerating 2D convolutional layer mapping on a dot product architecture
WO2021126203A1 (en) * 2019-12-19 2021-06-24 Google Llc Processing sequential inputs using neural network accelerators
CN111190716B (zh) * 2019-12-31 2022-06-03 清华大学 基于中断的神经网络加速器多任务调度方法
US11580388B2 (en) 2020-01-03 2023-02-14 Microsoft Technology Licensing, Llc Distributed processing architecture
US11076210B1 (en) * 2020-01-03 2021-07-27 Microsoft Technology Licensing, Llc Distributed processing architecture
US11847451B2 (en) 2020-01-07 2023-12-19 SK Hynix Inc. Processing-in-memory (PIM) device for implementing a quantization scheme
TWI868210B (zh) 2020-01-07 2025-01-01 韓商愛思開海力士有限公司 記憶體中處理（ｐｉｍ）系統
KR102334011B1 (ko) * 2020-02-10 2021-12-01 고려대학교 산학협력단 무선 통신 시스템에서 머신 러닝 기반 제한된 피드백 방법 및 장치
US20210303975A1 (en) * 2020-03-25 2021-09-30 Arm Limited Compression and decompression of weight values
CN111507952A (zh) * 2020-04-13 2020-08-07 上海泗科智能科技有限公司 一种嵌入式端的糖尿病性视网膜病变筛查解决方法
JP6896306B1 (ja) 2020-04-13 2021-06-30 ＬｅａｐＭｉｎｄ株式会社 ニューラルネットワーク回路、エッジデバイスおよびニューラルネットワーク演算方法
US11809908B2 (en) 2020-07-07 2023-11-07 SambaNova Systems, Inc. Runtime virtualization of reconfigurable data flow resources
US11848980B2 (en) * 2020-07-09 2023-12-19 Boray Data Technology Co. Ltd. Distributed pipeline configuration in a distributed computing system
KR102871496B1 (ko) * 2020-07-17 2025-10-14 삼성전자주식회사 뉴럴 네트워크 장치 및 그의 동작 방법
FR3113158B1 (fr) * 2020-08-03 2024-04-05 Commissariat Energie Atomique Architecture de calcul systolique pour la mise en œuvre de réseaux de neurones artificiels traitant plusieurs types de convolutions
US20220067513A1 (en) * 2020-08-28 2022-03-03 Nvidia Corp. Efficient softmax computation
US11099854B1 (en) * 2020-10-15 2021-08-24 Gigantor Technologies Inc. Pipelined operations in neural networks
US11256981B1 (en) * 2020-10-15 2022-02-22 Gigantor Technologies Inc. Unbounded parallel implementation of deep neural networks
US11550545B2 (en) * 2020-11-06 2023-01-10 SK Hynix Inc. Low-power, low-memory multiply and accumulate (MAC) unit
US12124939B1 (en) 2020-11-24 2024-10-22 Perceive Corporation Generation of machine-trained network instructions
US11237880B1 (en) * 2020-12-18 2022-02-01 SambaNova Systems, Inc. Dataflow all-reduce for reconfigurable processor systems
US11182221B1 (en) 2020-12-18 2021-11-23 SambaNova Systems, Inc. Inter-node buffer-based streaming for reconfigurable processor-as-a-service (RPaaS)
US11392740B2 (en) 2020-12-18 2022-07-19 SambaNova Systems, Inc. Dataflow function offload to reconfigurable processors
US20220197595A1 (en) * 2020-12-21 2022-06-23 Intel Corporation Efficient multiply and accumulate instruction when an operand is equal to or near a power of two
WO2022150009A1 (en) * 2021-01-08 2022-07-14 Agency For Science, Technology And Research GENERATING AN OUTPUT FOR A RECTIFIED LINEAR UNIT (ReLU)-ACTIVATED NEURON OF A NEURAL NETWORK
KR20220114228A (ko) 2021-02-08 2022-08-17 삼성전자주식회사 프로세서, 프로세서의 동작 방법 및 이를 포함한 전자 장치
US11782760B2 (en) 2021-02-25 2023-10-10 SambaNova Systems, Inc. Time-multiplexed use of reconfigurable hardware
US11200096B1 (en) 2021-03-26 2021-12-14 SambaNova Systems, Inc. Resource allocation for reconfigurable processors
CN112925741B (zh) * 2021-03-29 2023-01-24 上海西井信息科技有限公司 异构计算方法和系统
JP7681348B2 (ja) * 2021-04-15 2025-05-22 ジャイガンター・テクノロジーズ・インコーポレイテッド ニューラルネットワークにおけるパイプライン動作
US12159214B1 (en) 2021-04-23 2024-12-03 Perceive Corporation Buffering of neural network inputs and outputs
WO2022235517A2 (en) * 2021-05-05 2022-11-10 Uniquify, Inc. Implementations and methods for processing neural network in semiconductor hardware
US20240196058A1 (en) * 2021-05-05 2024-06-13 Uniquify, Inc. Systems and methods involving artificial intelligence and cloud technology for edge and server soc
US20240202509A1 (en) * 2021-05-05 2024-06-20 Uniquify, Inc. Implementations and methods for processing neural network in semiconductor hardware
US12443407B2 (en) * 2021-06-30 2025-10-14 Advanced Micro Devices, Inc. Accelerated processing device and method of sharing data for machine learning
WO2023287653A1 (en) * 2021-07-12 2023-01-19 Gigantor Technologies Inc. Pipelined operations in neural networks
US20230129750A1 (en) * 2021-10-27 2023-04-27 International Business Machines Corporation Performing a floating-point multiply-add operation in a computer implemented environment
KR20230068823A (ko) 2021-11-11 2023-05-18 삼성전자주식회사 인공 신경망 모델을 구동하기 위한 연산 방법 및 연산 장치
CN114330751A (zh) * 2021-12-31 2022-04-12 国家超级计算无锡中心 数据并行中优化dropout的方法
US12159140B2 (en) * 2022-04-28 2024-12-03 Qualcomm Incorporated Instruction set architecture for neural network quantization and packing
CN116011512B (zh) * 2022-11-28 2025-08-29 昆山市工业技术研究院有限责任公司 一种面向神经网络的高精度低功耗近似移位乘法器
CN115775021A (zh) * 2022-12-02 2023-03-10 北京灵汐科技有限公司 神经网络的信息统计的方法、众核系统、计算机可读介质
US12380041B2 (en) 2023-01-19 2025-08-05 SambaNova Systems, Inc. Method and apparatus for data transfer between accessible memories of multiple processors in a heterogeneous processing system using two memory to memory transfer operations
US12210468B2 (en) 2023-01-19 2025-01-28 SambaNova Systems, Inc. Data transfer between accessible memories of multiple processors incorporated in coarse-grained reconfigurable (CGR) architecture within heterogeneous processing system using one memory to memory transfer operation
US12229057B2 (en) 2023-01-19 2025-02-18 SambaNova Systems, Inc. Method and apparatus for selecting data access method in a heterogeneous processing system with multiple processors
US20250004762A1 (en) * 2023-06-29 2025-01-02 Texas Instruments Incorporated Binary convolution instructions for binary neural network computations
CN116956989A (zh) * 2023-07-31 2023-10-27 安谋科技（中国）有限公司 神经网络模型中归一化算子的量化方法、装置、电子设备

Family Cites Families (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE4228767A1 (de) * 1991-08-28 1993-03-04 Toshiba Kawasaki Kk Multiplizierschaltung
US7873812B1 (en) 2004-04-05 2011-01-18 Tibet MIMAR Method and system for efficient matrix multiplication in a SIMD processor architecture
US9712185B2 (en) * 2012-05-19 2017-07-18 Olsen Ip Reserve, Llc System and method for improved fractional binary to fractional residue converter and multipler
US20160026912A1 (en) * 2014-07-22 2016-01-28 Intel Corporation Weight-shifting mechanism for convolutional neural networks
US10223333B2 (en) 2014-08-29 2019-03-05 Nvidia Corporation Performing multi-convolution operations in a parallel processing system
US11049006B2 (en) 2014-09-12 2021-06-29 Microsoft Technology Licensing, Llc Computing system for training neural networks
US9747910B2 (en) * 2014-09-26 2017-08-29 Qualcomm Incorporated Switching between predictive and non-predictive quantization techniques in a higher order ambisonics (HOA) framework
US10776690B2 (en) * 2015-10-08 2020-09-15 Via Alliance Semiconductor Co., Ltd. Neural network unit with plurality of selectable output functions
US11029949B2 (en) * 2015-10-08 2021-06-08 Shanghai Zhaoxin Semiconductor Co., Ltd. Neural network unit
US10997496B2 (en) 2016-08-11 2021-05-04 Nvidia Corporation Sparse convolutional neural network accelerator
US10891538B2 (en) 2016-08-11 2021-01-12 Nvidia Corporation Sparse convolutional neural network accelerator
US10410098B2 (en) * 2017-04-24 2019-09-10 Intel Corporation Compute optimizations for neural networks

Also Published As

Publication number Publication date
CN108734285B (zh) 2025-05-27
EP3671439A1 (en) 2020-06-24
EP3396535B1 (en) 2020-04-22
US11074072B2 (en) 2021-07-27
EP3671439B1 (en) 2024-04-10
EP3396535A1 (en) 2018-10-31
US20210373886A1 (en) 2021-12-02
US20230359461A1 (en) 2023-11-09
CN108734285A (zh) 2018-11-02
US10410098B2 (en) 2019-09-10
US20190332903A1 (en) 2019-10-31
ES2982454T3 (es) 2024-10-16
US11693658B2 (en) 2023-07-04
US12430131B2 (en) 2025-09-30
US20180307950A1 (en) 2018-10-25

Similar Documents

Publication Publication Date Title
PL3671439T3 (pl) Optymalizacje obliczeniowe dla sieci neuronowych
GB201917181D0 (en) No details
GB201917180D0 (en) No details
GB201917178D0 (en) No details
GB2555936B (en) Neural network compute tile
GB202017924D0 (en) No details
GB201910775D0 (en) No Details
GB2556459B (en) Neural networks for speaker verification
ZA201801308B (en) Channel access configuration
EP3274928A4 (en) Optimizing neural networks for risk assessment
HUE054320T2 (hu) Kockázaton alapuló, tartományon belül tartást célzó szabályozás
GB201501869D0 (en) Hinge
GB201512278D0 (en) Hybrid neural network
AU201714804S (en) Micro-exfoliation roller
GB201918422D0 (en) No details
SG11201803488VA (en) Hinge
GB201817893D0 (en) Predicting physological parameters
PL3298224T3 (pl) Zawias o małych rozmiarach
GB2535637B (en) Continuous hinge
GB201609986D0 (en) Streamed communications
GB201702386D0 (en) System for streaming
GB201908106D0 (en) No details
GB201918330D0 (en) No details
GB201905867D0 (en) No details
ZA201800978B (en) Baffle structure for channel