JP2022506345A - ドット積計算機およびその演算方法 - Google Patents

ドット積計算機およびその演算方法 Download PDF

Info

Publication number
JP2022506345A
JP2022506345A JP2021523664A JP2021523664A JP2022506345A JP 2022506345 A JP2022506345 A JP 2022506345A JP 2021523664 A JP2021523664 A JP 2021523664A JP 2021523664 A JP2021523664 A JP 2021523664A JP 2022506345 A JP2022506345 A JP 2022506345A
Authority
JP
Japan
Prior art keywords
vector
value
product
mask
binary
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.)
Ceased
Application number
JP2021523664A
Other languages
English (en)
Japanese (ja)
Other versions
JP2022506345A5 (https=
Inventor
コナー、ファーガル
ベルナルド、デイヴィッド
ハンラハン、ニアル
Original Assignee
モビディウス リミテッド
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 モビディウス リミテッド filed Critical モビディウス リミテッド
Publication of JP2022506345A publication Critical patent/JP2022506345A/ja
Publication of JP2022506345A5 publication Critical patent/JP2022506345A5/ja
Ceased 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
    • 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
    • G06F7/52—Multiplying; Dividing
    • G06F7/523—Multiplying only
    • 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
    • G06F9/30003—Arrangements for executing specific machine instructions
    • G06F9/30007—Arrangements for executing specific machine instructions to perform operations on data operands
    • G06F9/30018—Bit or string 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
    • G06F9/30003—Arrangements for executing specific machine instructions
    • G06F9/30007—Arrangements for executing specific machine instructions to perform operations on data operands
    • G06F9/30036—Instructions to perform operations on packed data, e.g. vector, tile or matrix operations
    • G06F9/30038—Instructions to perform operations on packed data, e.g. vector, tile or matrix operations using a mask
    • 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
    • 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
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Mathematical Analysis (AREA)
  • Mathematical Optimization (AREA)
  • Pure & Applied Mathematics (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Computing Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Neurology (AREA)
  • Complex Calculations (AREA)
JP2021523664A 2018-11-08 2019-11-04 ドット積計算機およびその演算方法 Ceased JP2022506345A (ja)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US16/184,985 2018-11-08
US16/184,985 US10768895B2 (en) 2018-11-08 2018-11-08 Dot product calculators and methods of operating the same
PCT/EP2019/080136 WO2020094586A1 (en) 2018-11-08 2019-11-04 Dot product calculators and methods of operating the same

Publications (2)

Publication Number Publication Date
JP2022506345A true JP2022506345A (ja) 2022-01-17
JP2022506345A5 JP2022506345A5 (https=) 2022-10-20

Family

ID=68461801

Family Applications (1)

Application Number Title Priority Date Filing Date
JP2021523664A Ceased JP2022506345A (ja) 2018-11-08 2019-11-04 ドット積計算機およびその演算方法

Country Status (7)

Country Link
US (3) US10768895B2 (https=)
EP (1) EP3877839A1 (https=)
JP (1) JP2022506345A (https=)
KR (1) KR20210092751A (https=)
CN (1) CN113330421B (https=)
DE (1) DE112019005586T5 (https=)
WO (1) WO2020094586A1 (https=)

Families Citing this family (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11169809B2 (en) * 2017-03-31 2021-11-09 Intel Corporation Method and apparatus for converting scatter control elements to gather control elements used to sort vector data elements
US10409614B2 (en) 2017-04-24 2019-09-10 Intel Corporation Instructions having support for floating point and integer data types in the same register
US10474458B2 (en) 2017-04-28 2019-11-12 Intel Corporation Instructions and logic to perform floating-point and integer operations for machine learning
CN110770722B (zh) * 2017-06-29 2023-08-18 北京清影机器视觉技术有限公司 二维数据匹配方法、装置和逻辑电路
US10768895B2 (en) 2018-11-08 2020-09-08 Movidius Limited Dot product calculators and methods of operating the same
US12182035B2 (en) 2019-03-15 2024-12-31 Intel Corporation Systems and methods for cache optimization
US11934342B2 (en) 2019-03-15 2024-03-19 Intel Corporation Assistance for hardware prefetch in cache access
WO2020190807A1 (en) * 2019-03-15 2020-09-24 Intel Corporation Systolic disaggregation within a matrix accelerator architecture
PL3938914T3 (pl) 2019-03-15 2025-03-31 Intel Corporation Dynamiczna rekonfiguracja pamięci
US12131251B2 (en) * 2019-03-19 2024-10-29 Cirrus Logic Inc. Neurons for artificial neural networks
WO2020218157A1 (ja) * 2019-04-25 2020-10-29 国立大学法人静岡大学 予測システム、予測方法、および予測プログラム
US11741349B2 (en) * 2019-10-31 2023-08-29 Arm Limited Performing matrix-vector multiply operations for neural networks on electronic devices
US11861761B2 (en) 2019-11-15 2024-01-02 Intel Corporation Graphics processing unit processing and caching improvements
US11663746B2 (en) 2019-11-15 2023-05-30 Intel Corporation Systolic arithmetic on sparse data
US11500680B2 (en) * 2020-04-24 2022-11-15 Alibaba Group Holding Limited Systolic array-friendly data placement and control based on masked write
US20220405571A1 (en) * 2021-06-16 2022-12-22 Microsoft Technology Licensing, Llc Sparsifying narrow data formats for neural networks
US12321857B2 (en) 2021-06-24 2025-06-03 Intel Corporation Methods and apparatus to perform machine-learning model operations on sparse accelerators
US20230035474A1 (en) * 2021-07-20 2023-02-02 Gsi Technology Inc. Compiler for a parallel processor
US20230083270A1 (en) * 2021-09-14 2023-03-16 International Business Machines Corporation Mixed signal circuitry for bitwise multiplication with different accuracies
US11789646B2 (en) 2021-09-24 2023-10-17 Intel Corporation Methods, apparatus, and articles of manufacture to increase data reuse for multiply and accumulate (MAC) operations
US11669489B2 (en) * 2021-09-30 2023-06-06 International Business Machines Corporation Sparse systolic array design

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS62233884A (ja) * 1986-04-04 1987-10-14 Hitachi Ltd ベクトル・プロセツサ
JP2011511986A (ja) * 2008-02-11 2011-04-14 リニア アルジェブラ テクノロジーズ リミテッド プロセッサ
WO2018080624A1 (en) * 2016-10-27 2018-05-03 Google Llc Exploiting input data sparsity in neural network compute units

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080071851A1 (en) * 2006-09-20 2008-03-20 Ronen Zohar Instruction and logic for performing a dot-product operation
US20160358069A1 (en) * 2015-06-03 2016-12-08 Samsung Electronics Co., Ltd. Neural network suppression
US10223359B2 (en) * 2016-10-10 2019-03-05 The Directv Group, Inc. Determining recommended media programming from sparse consumption data
US10146738B2 (en) * 2016-12-31 2018-12-04 Intel Corporation Hardware accelerator architecture for processing very-sparse and hyper-sparse matrix data
US20180189675A1 (en) * 2016-12-31 2018-07-05 Intel Corporation Hardware accelerator architecture and template for web-scale k-means clustering
US10096134B2 (en) * 2017-02-01 2018-10-09 Nvidia Corporation Data compaction and memory bandwidth reduction for sparse neural networks
US10171084B2 (en) * 2017-04-24 2019-01-01 The Regents Of The University Of Michigan Sparse coding with Memristor networks
US20180330235A1 (en) * 2017-05-15 2018-11-15 National Taiwan University Apparatus and Method of Using Dual Indexing in Input Neurons and Corresponding Weights of Sparse Neural Network
TWI684141B (zh) 2017-10-12 2020-02-01 英屬開曼群島商意騰科技股份有限公司 人工神經元中以非零封包加速乘法運算的裝置及方法
KR102697300B1 (ko) * 2018-03-07 2024-08-23 삼성전자주식회사 전자 장치 및 머신 러닝 수행 방법
US10768895B2 (en) 2018-11-08 2020-09-08 Movidius Limited Dot product calculators and methods of operating the same

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS62233884A (ja) * 1986-04-04 1987-10-14 Hitachi Ltd ベクトル・プロセツサ
JP2011511986A (ja) * 2008-02-11 2011-04-14 リニア アルジェブラ テクノロジーズ リミテッド プロセッサ
WO2018080624A1 (en) * 2016-10-27 2018-05-03 Google Llc Exploiting input data sparsity in neural network compute units

Also Published As

Publication number Publication date
US20200387350A1 (en) 2020-12-10
US11023206B2 (en) 2021-06-01
US20210247961A1 (en) 2021-08-12
US11656845B2 (en) 2023-05-23
CN113330421A (zh) 2021-08-31
EP3877839A1 (en) 2021-09-15
US10768895B2 (en) 2020-09-08
CN113330421B (zh) 2024-01-16
WO2020094586A1 (en) 2020-05-14
US20200150926A1 (en) 2020-05-14
KR20210092751A (ko) 2021-07-26
DE112019005586T5 (de) 2021-12-16

Similar Documents

Publication Publication Date Title
JP2022506345A (ja) ドット積計算機およびその演算方法
CN111708511B (zh) 用于神经网络的数据压缩
CN108229648B (zh) 匹配存储器中数据位宽的卷积计算方法和装置、设备、介质
TW202207052A (zh) 用以解碼零值壓縮資料向量之方法、系統、製造物品及設備
US10268451B2 (en) Method and processing apparatus for performing arithmetic operation
JP6571752B2 (ja) ベクトルレジスタファイルにおいてデータインデックス方式アキュムレータを使用するベクトルプロセッサによるスカラ演算の並列化、関連する回路、方法およびコンピュータ可読媒体
US20220318604A1 (en) Sparse machine learning acceleration
EP4260174B1 (en) Data-type-aware clock-gating
CN111033462B (zh) 在基于处理器的系统中使用矩阵处理器提供高效浮点运算
EP2738675B1 (en) System and method for efficient resource management of a signal flow programmed digital signal processor code
WO2019215907A1 (ja) 演算処理装置
CN114254563A (zh) 数据处理方法及装置、电子设备、存储介质
CN116010300A (zh) 一种gpu缓存方法及装置、电子设备和存储介质
CN111931937B (zh) 图像处理模型的梯度更新方法、装置及系统
TW202333041A (zh) 執行浮點運算的系統及方法
CN109543835B (zh) 运算方法、装置及相关产品
US12468507B1 (en) Reducing power consumption in integrated circuits
EP3923132B1 (en) Device for performing multiply/accumulate operations
CN112699525B (zh) 一种瑞利信道仿真器的计算方法、设备
CN109558564B (zh) 运算方法、装置及相关产品
CN109543836B (zh) 运算方法、装置及相关产品
CN120197660A (zh) 一种面向脑电信号处理的边缘推理神经网络协处理器电路
CN115809043A (zh) 一种乘法器及其相关产品和方法
CN119339023A (zh) 基于自适应稀疏编码引导的3d场景隐式重建方法及装置

Legal Events

Date Code Title Description
A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20221012

A621 Written request for application examination

Free format text: JAPANESE INTERMEDIATE CODE: A621

Effective date: 20221012

A977 Report on retrieval

Free format text: JAPANESE INTERMEDIATE CODE: A971007

Effective date: 20230726

A131 Notification of reasons for refusal

Free format text: JAPANESE INTERMEDIATE CODE: A131

Effective date: 20230808

A521 Request for written amendment filed

Free format text: JAPANESE INTERMEDIATE CODE: A523

Effective date: 20231026

A01 Written decision to grant a patent or to grant a registration (utility model)

Free format text: JAPANESE INTERMEDIATE CODE: A01

Effective date: 20240123

A045 Written measure of dismissal of application [lapsed due to lack of payment]

Free format text: JAPANESE INTERMEDIATE CODE: A045

Effective date: 20240528