TWI815407B - 用於促進一計算環境內之處理的電腦程式產品、電腦系統及電腦實施方法 - Google Patents

用於促進一計算環境內之處理的電腦程式產品、電腦系統及電腦實施方法 Download PDF

Info

Publication number
TWI815407B
TWI815407B TW111115169A TW111115169A TWI815407B TW I815407 B TWI815407 B TW I815407B TW 111115169 A TW111115169 A TW 111115169A TW 111115169 A TW111115169 A TW 111115169A TW I815407 B TWI815407 B TW I815407B
Authority
TW
Taiwan
Prior art keywords
function
tensor
designated area
processing
data
Prior art date
Application number
TW111115169A
Other languages
English (en)
Chinese (zh)
Other versions
TW202301110A (zh
Inventor
賽門 衛蕭普特
安東尼 薩波里多
提摩西 史洛歌
Original Assignee
美商萬國商業機器公司
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 美商萬國商業機器公司 filed Critical 美商萬國商業機器公司
Publication of TW202301110A publication Critical patent/TW202301110A/zh
Application granted granted Critical
Publication of TWI815407B publication Critical patent/TWI815407B/zh

Links

Classifications

    • 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
    • G06F9/4812—Task transfer initiation or dispatching by interrupt, e.g. masked
    • 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
    • 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
    • G06F9/30072—Arrangements for executing specific machine instructions to perform conditional operations, e.g. using predicates or guards
    • 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
    • G06F9/30098—Register arrangements
    • G06F9/3012—Organisation of register space, e.g. banked or distributed register file
    • G06F9/3013—Organisation of register space, e.g. banked or distributed register file according to data content, e.g. floating-point registers, address registers
    • 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
    • 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
    • G06N3/0464—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
    • G06N3/08—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
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/048—Activation functions

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)
  • Molecular Biology (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Data Mining & Analysis (AREA)
  • Mathematical Physics (AREA)
  • Computational Linguistics (AREA)
  • Artificial Intelligence (AREA)
  • Neurology (AREA)
  • Executing Machine-Instructions (AREA)
  • Testing And Monitoring For Control Systems (AREA)
  • Particle Accelerators (AREA)
  • Control Of Transmission Device (AREA)
  • Stored Programmes (AREA)
  • Debugging And Monitoring (AREA)
  • Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
  • Image Analysis (AREA)
TW111115169A 2021-06-17 2022-04-21 用於促進一計算環境內之處理的電腦程式產品、電腦系統及電腦實施方法 TWI815407B (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US17/350,365 2021-06-17
US17/350,365 US11693692B2 (en) 2021-06-17 2021-06-17 Program event recording storage alteration processing for a neural network accelerator instruction

Publications (2)

Publication Number Publication Date
TW202301110A TW202301110A (zh) 2023-01-01
TWI815407B true TWI815407B (zh) 2023-09-11

Family

ID=84490421

Family Applications (1)

Application Number Title Priority Date Filing Date
TW111115169A TWI815407B (zh) 2021-06-17 2022-04-21 用於促進一計算環境內之處理的電腦程式產品、電腦系統及電腦實施方法

Country Status (7)

Country Link
US (2) US11693692B2 (enExample)
JP (1) JP7750990B2 (enExample)
CN (1) CN117441172A (enExample)
DE (1) DE112022002300T5 (enExample)
GB (1) GB2622349A (enExample)
TW (1) TWI815407B (enExample)
WO (1) WO2022263997A1 (enExample)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11693692B2 (en) 2021-06-17 2023-07-04 International Business Machines Corporation Program event recording storage alteration processing for a neural network accelerator instruction
US12495005B1 (en) * 2024-03-22 2025-12-09 Chelsio Communications, Inc. Programmable processing of network protocol packets

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170103304A1 (en) * 2015-10-08 2017-04-13 Via Alliance Semiconductor Co., Ltd. Neural network unit with plurality of selectable output functions
CN111126583A (zh) * 2019-12-23 2020-05-08 中国电子科技集团公司第五十八研究所 一种通用神经网络加速器
CN111353595A (zh) * 2018-12-20 2020-06-30 上海寒武纪信息科技有限公司 运算方法、装置及相关产品

Family Cites Families (74)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
FR2061803A5 (enExample) * 1969-03-21 1971-06-25 Labo Cent Telecommunicat
JPS6349846A (ja) * 1986-08-20 1988-03-02 Canon Inc 演算処理装置
US5761105A (en) 1995-09-26 1998-06-02 Advanced Micro Devices, Inc. Reservation station including addressable constant store for a floating point processing unit
JPH10171770A (ja) * 1996-12-06 1998-06-26 Meidensha Corp マルチプロセッサシステム
JP2004252729A (ja) * 2003-02-20 2004-09-09 Konica Minolta Holdings Inc 割り込み支援回路装置及びマイクロコンピュータ並びに割り込み支援方法
US8291003B2 (en) 2008-09-09 2012-10-16 International Business Machines Corporation Supporting multiple formats in a floating point processor
US9286130B2 (en) 2012-08-27 2016-03-15 International Business Machines Corporation Optimizing virtual machine deployment time by temporarily allocating more processing resources during the initial deployment time of the virtual machine
US10623386B1 (en) 2012-09-26 2020-04-14 Pure Storage, Inc. Secret sharing data protection in a storage system
US10061824B2 (en) 2015-01-30 2018-08-28 Splunk Inc. Cell-based table manipulation of event data
US9747546B2 (en) 2015-05-21 2017-08-29 Google Inc. Neural network processor
US10460230B2 (en) 2015-06-04 2019-10-29 Samsung Electronics Co., Ltd. Reducing computations in a neural network
US9710401B2 (en) 2015-06-26 2017-07-18 Intel Corporation Processors, methods, systems, and instructions to support live migration of protected containers
US10728169B1 (en) 2015-06-26 2020-07-28 Amazon Technologies, Inc. Instance upgrade migration
US9940101B2 (en) 2015-08-25 2018-04-10 Samsung Electronics Co., Ltd. Tininess prediction and handler engine for smooth handling of numeric underflow
US10726328B2 (en) 2015-10-09 2020-07-28 Altera Corporation Method and apparatus for designing and implementing a convolution neural net accelerator
US10552370B2 (en) 2015-10-08 2020-02-04 Via Alliance Semiconductor Co., Ltd. Neural network unit with output buffer feedback for performing recurrent neural network computations
US9569277B1 (en) 2016-01-29 2017-02-14 International Business Machines Corporation Rebalancing virtual resources for virtual machines based on multiple resource capacities
US10778707B1 (en) 2016-05-12 2020-09-15 Amazon Technologies, Inc. Outlier detection for streaming data using locality sensitive hashing
US10891538B2 (en) 2016-08-11 2021-01-12 Nvidia Corporation Sparse convolutional neural network accelerator
US10810484B2 (en) 2016-08-12 2020-10-20 Xilinx, Inc. Hardware accelerator for compressed GRU on FPGA
US10802992B2 (en) 2016-08-12 2020-10-13 Xilinx Technology Beijing Limited Combining CPU and special accelerator for implementing an artificial neural network
US9959498B1 (en) 2016-10-27 2018-05-01 Google Llc Neural network instruction set architecture
US10175980B2 (en) 2016-10-27 2019-01-08 Google Llc Neural network compute tile
US10949736B2 (en) 2016-11-03 2021-03-16 Intel Corporation Flexible neural network accelerator and methods therefor
US10120680B2 (en) 2016-12-30 2018-11-06 Intel Corporation Systems, apparatuses, and methods for arithmetic recurrence
CN107016175B (zh) 2017-03-23 2018-08-31 中国科学院计算技术研究所 适用神经网络处理器的自动化设计方法、装置及优化方法
CN118134744A (zh) 2017-04-07 2024-06-04 英特尔公司 用于多处理器平台上的深度学习网络执行流水线的方法和装置
WO2018193352A1 (en) 2017-04-17 2018-10-25 Cerebras Systems Inc. Dataflow triggered tasks for accelerated deep learning
CN107704922B (zh) 2017-04-19 2020-12-08 赛灵思公司 人工神经网络处理装置
US12154028B2 (en) 2017-05-05 2024-11-26 Intel Corporation Fine-grain compute communication execution for deep learning frameworks via hardware accelerated point-to-point primitives
US10338925B2 (en) 2017-05-24 2019-07-02 Microsoft Technology Licensing, Llc Tensor register files
US11216437B2 (en) 2017-08-14 2022-01-04 Sisense Ltd. System and method for representing query elements in an artificial neural network
US10642835B2 (en) 2017-08-14 2020-05-05 Sisense Ltd. System and method for increasing accuracy of approximating query results using neural networks
US10558599B2 (en) 2017-09-12 2020-02-11 Nxp Usa, Inc. Method and apparatus for loading a matrix into an accelerator
CN109543826A (zh) 2017-09-21 2019-03-29 杭州海康威视数字技术股份有限公司 一种基于深度神经网络的激活量量化方法及装置
KR102610820B1 (ko) 2017-09-27 2023-12-06 삼성전자주식회사 뉴럴 네트워크 시스템 및 뉴럴 네트워크 시스템의 동작방법
GB2568087B (en) 2017-11-03 2022-07-20 Imagination Tech Ltd Activation functions for deep neural networks
US11373088B2 (en) 2017-12-30 2022-06-28 Intel Corporation Machine learning accelerator mechanism
MX2020007385A (es) 2018-01-10 2020-11-24 Lynjohnston Llc Sistemas y metodos de inyector compacto.
US10832137B2 (en) 2018-01-30 2020-11-10 D5Ai Llc Merging multiple nodal networks
WO2019157599A1 (en) 2018-02-16 2019-08-22 The Governing Council Of The University Of Toronto Neural network accelerator
US10552199B2 (en) 2018-02-26 2020-02-04 Nutanix, Inc. System and method for binary throttling for live migration of virtual machines
US20200074293A1 (en) 2018-08-29 2020-03-05 DinoplusAI Holdings Limited Computing Device for Multiple Activation Functions in Neural Networks
US20190340499A1 (en) 2018-05-04 2019-11-07 Microsoft Technology Licensing, Llc Quantization for dnn accelerators
US10656913B2 (en) 2018-06-05 2020-05-19 International Business Machines Corporation Enhanced low precision binary floating-point formatting
US10620951B2 (en) 2018-06-22 2020-04-14 Intel Corporation Matrix multiplication acceleration of sparse matrices using column folding and squeezing
US10832139B2 (en) 2018-06-22 2020-11-10 Moffett Technologies Co. Limited Neural network acceleration and embedding compression systems and methods with activation sparsification
US10908906B2 (en) 2018-06-29 2021-02-02 Intel Corporation Apparatus and method for a tensor permutation engine
CN109146072B (zh) 2018-08-01 2021-03-23 上海天数智芯半导体有限公司 基于卷积神经网络加速器的数据重用方法
US10885277B2 (en) 2018-08-02 2021-01-05 Google Llc On-device neural networks for natural language understanding
US10817042B2 (en) 2018-09-27 2020-10-27 Intel Corporation Power savings for neural network architecture with zero activations during inference
US11676003B2 (en) 2018-12-18 2023-06-13 Microsoft Technology Licensing, Llc Training neural network accelerators using mixed precision data formats
US10699465B1 (en) 2018-12-28 2020-06-30 Intel Corporation Cluster of scalar engines to accelerate intersection in leaf node
US20200218985A1 (en) 2019-01-03 2020-07-09 Alibaba Group Holding Limited System and method for synthetic-model-based benchmarking of ai hardware
US11645358B2 (en) 2019-01-29 2023-05-09 Hewlett Packard Enterprise Development Lp Generation of executable files corresponding to neural network models
WO2020163171A1 (en) * 2019-02-07 2020-08-13 quadric.io, Inc. Systems and methods for implementing a random access augmented machine perception and dense algorithm integrated circuit
US12165038B2 (en) 2019-02-14 2024-12-10 Microsoft Technology Licensing, Llc Adjusting activation compression for neural network training
US11442700B2 (en) 2019-03-29 2022-09-13 Stmicroelectronics S.R.L. Hardware accelerator method, system and device
US10789402B1 (en) 2019-05-01 2020-09-29 Xilinx, Inc. Compiler and hardware abstraction layer architecture for a neural network accelerator
US11366771B2 (en) 2019-05-02 2022-06-21 EMC IP Holding Company LLC Host device with multi-path layer configured for detection and resolution of initiator-related conditions
US11790250B2 (en) 2019-05-09 2023-10-17 Intel Corporation Using computational cost and instantaneous load analysis for intelligent deployment of neural networks on multiple hardware executors
CN110197260B (zh) 2019-06-06 2020-10-02 百度在线网络技术（北京）有限公司 一种数据处理方法及装置
TWI701612B (zh) 2019-06-19 2020-08-11 創鑫智慧股份有限公司 用於神經網路中激勵函數的電路系統及其處理方法
US11714572B2 (en) 2019-06-19 2023-08-01 Pure Storage, Inc. Optimized data resiliency in a modular storage system
US11568238B2 (en) 2019-06-28 2023-01-31 Amazon Technologies, Inc. Dynamic processing element array expansion
US11907827B2 (en) 2019-06-28 2024-02-20 Intel Corporation Schedule-aware tensor distribution module
US11630770B2 (en) 2019-07-11 2023-04-18 Meta Platforms Technologies, Llc Systems and methods for reading and writing sparse data in a neural network accelerator
US11727267B2 (en) 2019-08-30 2023-08-15 Intel Corporation Artificial neural network with trainable activation functions and fractional derivative values
US11567555B2 (en) 2019-08-30 2023-01-31 Intel Corporation Software assisted power management
CN110766135A (zh) 2019-10-15 2020-02-07 北京芯启科技有限公司 一种对任意深度神经网络优化其运行功能时所需存储的方法
US11797188B2 (en) 2019-12-12 2023-10-24 Sk Hynix Nand Product Solutions Corp. Solid state drive with multiplexed internal channel access during program data transfers
US11513818B1 (en) * 2020-09-30 2022-11-29 Cadence Design Systems, Inc. Method, product, and system for integrating a hardware accelerator with an extensible processor
JP2022144805A (ja) * 2021-03-19 2022-10-03 富士通株式会社 機械学習プログラム、機械学習方法、及び、計算機
US11693692B2 (en) * 2021-06-17 2023-07-04 International Business Machines Corporation Program event recording storage alteration processing for a neural network accelerator instruction

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170103304A1 (en) * 2015-10-08 2017-04-13 Via Alliance Semiconductor Co., Ltd. Neural network unit with plurality of selectable output functions
CN111353595A (zh) * 2018-12-20 2020-06-30 上海寒武纪信息科技有限公司 运算方法、装置及相关产品
CN111126583A (zh) * 2019-12-23 2020-05-08 中国电子科技集团公司第五十八研究所 一种通用神经网络加速器

Also Published As

Publication number Publication date
CN117441172A (zh) 2024-01-23
GB202400226D0 (en) 2024-02-21
DE112022002300T5 (de) 2024-02-22
US12008395B2 (en) 2024-06-11
US11693692B2 (en) 2023-07-04
WO2022263997A1 (en) 2022-12-22
JP7750990B2 (ja) 2025-10-07
TW202301110A (zh) 2023-01-01
JP2024523790A (ja) 2024-07-02
US20230273810A1 (en) 2023-08-31
US20220405120A1 (en) 2022-12-22
GB2622349A (en) 2024-03-13

Similar Documents

Publication Publication Date Title
TWI840790B (zh) 用於促進一運算環境內之處理的電腦程式產品、電腦系統及電腦實施方法
TWI859529B (zh) 電腦程式產品、電腦系統及電腦實施方法
TWI833205B (zh) 用於遞歸神經網路中使用之串連輸入/輸出張量
TWI813258B (zh) 重新格式化張量以提供子張量
TWI807767B (zh) 神經網路處理輔助指令
CN117396847A (zh) 采用隐含的舍入模式的向/从所选择的数据类型的数据转换
TWI815407B (zh) 用於促進一計算環境內之處理的電腦程式產品、電腦系統及電腦實施方法
TWI832214B (zh) 用於促進一運算環境內之處理的電腦程式產品、電腦系統及電腦實施方法
TWI885258B (zh) 遞歸神經網路單元啟動以執行一單一引動中之複數個運算
TWI818518B (zh) 用於促進一運算環境內之處理的電腦程式產品、電腦系統及電腦實施方法
TWI804285B (zh) 查詢模型相依資訊之指令
TWI840785B (zh) 用於在指令執行期間偵測之無效值之例外摘要
HK40099076A (zh) 具有不同操作参数验证的执行多个操作的单个功能
HK40099080A (zh) 神经网络处理辅助指令
HK40099077A (zh) 重新格式化张量以提供子张量
HK40099082A (zh) 用於在单次调用中执行多个操作的循环神经网络神经元激活