DE102017121887A1 - Ausführen von Kerndurchschreiten in Hardware - Google Patents

Ausführen von Kerndurchschreiten in Hardware Download PDF

Info

Publication number
DE102017121887A1
DE102017121887A1 DE102017121887.4A DE102017121887A DE102017121887A1 DE 102017121887 A1 DE102017121887 A1 DE 102017121887A1 DE 102017121887 A DE102017121887 A DE 102017121887A DE 102017121887 A1 DE102017121887 A1 DE 102017121887A1
Authority
DE
Germany
Prior art keywords
neural network
tensor
convolution layer
layer
hardware circuit
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.)
Withdrawn
Application number
DE102017121887.4A
Other languages
German (de)
English (en)
Inventor
Reginald Clifford Young
William John Gulland
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Google LLC
Original Assignee
Google LLC
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 Google LLC filed Critical Google LLC
Publication of DE102017121887A1 publication Critical patent/DE102017121887A1/de
Withdrawn legal-status Critical Current

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
    • G06N3/08—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
    • G06N3/06—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
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Biomedical Technology (AREA)
  • Biophysics (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Evolutionary Computation (AREA)
  • General Health & Medical Sciences (AREA)
  • Molecular Biology (AREA)
  • Computational Linguistics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Artificial Intelligence (AREA)
  • Neurology (AREA)
  • Complex Calculations (AREA)
  • Image Analysis (AREA)
  • Feedback Control In General (AREA)
  • Amplifiers (AREA)
  • Reduction Or Emphasis Of Bandwidth Of Signals (AREA)
DE102017121887.4A 2016-11-10 2017-09-21 Ausführen von Kerndurchschreiten in Hardware Withdrawn DE102017121887A1 (de)

Applications Claiming Priority (4)

Application Number Priority Date Filing Date Title
US15/348,199 US10733505B2 (en) 2016-11-10 2016-11-10 Performing kernel striding in hardware
US15/348,199 2016-11-10
US15/467,382 US9721203B1 (en) 2016-11-10 2017-03-23 Performing kernel striding in hardware
US15/467,382 2017-03-23

Publications (1)

Publication Number Publication Date
DE102017121887A1 true DE102017121887A1 (de) 2018-05-17

Family

ID=59382805

Family Applications (2)

Application Number Title Priority Date Filing Date
DE102017121887.4A Withdrawn DE102017121887A1 (de) 2016-11-10 2017-09-21 Ausführen von Kerndurchschreiten in Hardware
DE202017105729.1U Active DE202017105729U1 (de) 2016-11-10 2017-09-21 Kerndurchschreiten in Hardware

Family Applications After (1)

Application Number Title Priority Date Filing Date
DE202017105729.1U Active DE202017105729U1 (de) 2016-11-10 2017-09-21 Kerndurchschreiten in Hardware

Country Status (12)

Country Link
US (3) US10733505B2 (enExample)
EP (2) EP4336411A3 (enExample)
JP (2) JP6987860B2 (enExample)
KR (2) KR102512936B1 (enExample)
CN (2) CN108073983B (enExample)
DE (2) DE102017121887A1 (enExample)
DK (1) DK3539059T3 (enExample)
FI (1) FI3539059T3 (enExample)
GB (2) GB2556670B (enExample)
IE (1) IE20170205A1 (enExample)
SG (2) SG10201804284XA (enExample)
WO (1) WO2018089079A1 (enExample)

Families Citing this family (86)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
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
US10360163B2 (en) 2016-10-27 2019-07-23 Google Llc Exploiting input data sparsity in neural network compute units
US10733505B2 (en) * 2016-11-10 2020-08-04 Google Llc Performing kernel striding in hardware
TWI634490B (zh) * 2016-11-14 2018-09-01 美商耐能股份有限公司 卷積運算裝置及卷積運算方法
US10198401B2 (en) * 2016-12-30 2019-02-05 Intel Corporation Max pooling in a matrix processing architecture
TWI607389B (zh) * 2017-02-10 2017-12-01 耐能股份有限公司 卷積神經網路的池化運算裝置及方法
US11132599B2 (en) 2017-02-28 2021-09-28 Microsoft Technology Licensing, Llc Multi-function unit for programmable hardware nodes for neural network processing
US10346944B2 (en) 2017-04-09 2019-07-09 Intel Corporation Machine learning sparse computation mechanism
US10643297B2 (en) * 2017-05-05 2020-05-05 Intel Corporation Dynamic precision management for integer deep learning primitives
CN119151768A (zh) 2017-05-05 2024-12-17 英特尔公司 用于整数深度学习原语的动态精度管理
US10776694B2 (en) * 2017-05-16 2020-09-15 Samsung Electronics Co., Ltd. Optimized neural network input stride method and apparatus
US11360934B1 (en) 2017-09-15 2022-06-14 Groq, Inc. Tensor streaming processor architecture
US11243880B1 (en) 2017-09-15 2022-02-08 Groq, Inc. Processor architecture
US11868804B1 (en) 2019-11-18 2024-01-09 Groq, Inc. Processor instruction dispatch configuration
US11170307B1 (en) 2017-09-21 2021-11-09 Groq, Inc. Predictive model compiler for generating a statically scheduled binary with known resource constraints
KR102442055B1 (ko) * 2017-09-26 2022-09-13 삼성전자주식회사 전자 장치 및 그 제어 방법
EP3480748B1 (en) 2017-11-06 2025-10-08 Imagination Technologies Limited Neural network hardware
CN108108811B (zh) * 2017-12-18 2021-07-30 南京地平线机器人技术有限公司 神经网络中的卷积计算方法和电子设备
CN108133270B (zh) * 2018-01-12 2020-08-04 清华大学 卷积神经网络加速方法及装置
US11461579B2 (en) 2018-02-08 2022-10-04 Western Digital Technologies, Inc. Configurable neural network engine for convolutional filter sizes
US11494620B2 (en) 2018-02-08 2022-11-08 Western Digital Technologies, Inc. Systolic neural network engine capable of backpropagation
US11475306B2 (en) 2018-03-22 2022-10-18 Amazon Technologies, Inc. Processing for multiple input data sets
EP4542446A3 (en) * 2018-03-22 2025-07-02 Amazon Technologies, Inc. Processing for multiple input data sets
US10621489B2 (en) 2018-03-30 2020-04-14 International Business Machines Corporation Massively parallel neural inference computing elements
US12182686B2 (en) 2018-04-30 2024-12-31 International Business Machines Corporation Neural hardware accelerator for parallel and distributed tensor computations
US11783174B2 (en) 2018-05-04 2023-10-10 Apple Inc. Splitting of input data for processing in neural network processor
CN108764182B (zh) * 2018-06-01 2020-12-08 阿依瓦（北京）技术有限公司 一种优化的用于人工智能的加速方法和装置
US12099912B2 (en) 2018-06-22 2024-09-24 Samsung Electronics Co., Ltd. Neural processor
CN109036460B (zh) * 2018-08-28 2020-01-07 百度在线网络技术（北京）有限公司 基于多模型神经网络的语音处理方法和装置
EP3617953A1 (en) * 2018-08-30 2020-03-04 Koninklijke Philips N.V. An adaptable neural network
CN109190758B (zh) * 2018-09-04 2021-06-15 地平线(上海)人工智能技术有限公司 用于展开卷积神经网络的张量数据的方法和装置
US11455370B2 (en) * 2018-11-19 2022-09-27 Groq, Inc. Flattened input stream generation for convolution with expanded kernel
US12340300B1 (en) 2018-09-14 2025-06-24 Groq, Inc. Streaming processor architecture
CN110969247B (zh) * 2018-09-30 2024-04-09 北京地平线信息技术有限公司 基于神经网络的张量处理方法、装置和电子设备
CN112771546A (zh) * 2018-09-30 2021-05-07 华为技术有限公司 运算加速器和压缩方法
DE102018217090A1 (de) * 2018-10-05 2020-04-09 Robert Bosch Gmbh Verfahren, künstliches neuronales Netz, Vorrichtung, Computerprogramm und maschinenlesbares Speichermedium zur semantischen Segmentierung von Bilddaten
CN109376843B (zh) * 2018-10-12 2021-01-08 山东师范大学 基于fpga的脑电信号快速分类方法、实现方法及装置
US11636325B2 (en) 2018-10-24 2023-04-25 Macronix International Co., Ltd. In-memory data pooling for machine learning
JP7315317B2 (ja) 2018-11-09 2023-07-26 株式会社Preferred Networks プロセッサおよびプロセッサのデータ転送方法
US11562229B2 (en) * 2018-11-30 2023-01-24 Macronix International Co., Ltd. Convolution accelerator using in-memory computation
US11934480B2 (en) 2018-12-18 2024-03-19 Macronix International Co., Ltd. NAND block architecture for in-memory multiply-and-accumulate operations
US20200202198A1 (en) * 2018-12-21 2020-06-25 Waymo Llc Neural network processor
CN109919321A (zh) * 2019-02-01 2019-06-21 京微齐力(北京)科技有限公司 单元具有本地累加功能的人工智能模块及系统芯片
US11556764B2 (en) * 2019-03-01 2023-01-17 Microsoft Technology Licensing, Llc Deriving a concordant software neural network layer from a quantized firmware neural network layer
US11783176B2 (en) 2019-03-25 2023-10-10 Western Digital Technologies, Inc. Enhanced storage device memory architecture for machine learning
US10929058B2 (en) 2019-03-25 2021-02-23 Western Digital Technologies, Inc. Enhanced memory device architecture for machine learning
US12456045B2 (en) * 2019-03-30 2025-10-28 Microsoft Technology Licensing, Llc Embedded learning for response prediction in content item relevance
US11671111B2 (en) 2019-04-17 2023-06-06 Samsung Electronics Co., Ltd. Hardware channel-parallel data compression/decompression
CN110135580B (zh) * 2019-04-26 2021-03-26 华中科技大学 一种卷积网络全整型量化方法及其应用方法
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
US11880760B2 (en) 2019-05-01 2024-01-23 Samsung Electronics Co., Ltd. Mixed-precision NPU tile with depth-wise convolution
KR102373802B1 (ko) * 2019-06-12 2022-03-16 주식회사 사피온코리아 신경망 연산 효율 증대를 위한 신경망 가속기 및 그의 동작 방법
US11487998B2 (en) * 2019-06-17 2022-11-01 Qualcomm Incorporated Depth-first convolution in deep neural networks
US11308396B2 (en) * 2019-06-27 2022-04-19 Amazon Technologies, Inc. Neural network layer-by-layer debugging
US12190225B2 (en) * 2019-06-27 2025-01-07 Advanced Micro Devices, Inc. Composable neural network kernels
US11379555B2 (en) * 2019-06-28 2022-07-05 Amazon Technologies, Inc. Dilated convolution using systolic array
US10997116B2 (en) * 2019-08-06 2021-05-04 Microsoft Technology Licensing, Llc Tensor-based hardware accelerator including a scalar-processing unit
US11449739B2 (en) * 2019-08-22 2022-09-20 Google Llc General padding support for convolution on systolic arrays
US11768911B2 (en) * 2019-09-24 2023-09-26 Alibaba Group Holding Limited Method and apparatus for execution of neural network
US12229657B2 (en) 2019-10-08 2025-02-18 Apple Inc. Multi-mode planar engine for neural processor
TWI774067B (zh) * 2019-10-18 2022-08-11 旺宏電子股份有限公司 記憶體裝置及其記憶體內計算方法
JP7462140B2 (ja) * 2019-10-29 2024-04-05 国立大学法人 熊本大学 ニューラルネットワーク回路及びニューラルネットワーク演算方法
CN110852424B (zh) * 2019-11-15 2023-07-25 广东工业大学 一种对抗生成网络的处理方法和装置
US20230004810A1 (en) * 2019-12-06 2023-01-05 Nec Corporation Parameter optimization device, parameter optimization method, and parameter optimization program
CN111027683A (zh) * 2019-12-09 2020-04-17 Oppo广东移动通信有限公司 数据处理方法、装置、存储介质及电子设备
US12112141B2 (en) 2019-12-12 2024-10-08 Samsung Electronics Co., Ltd. Accelerating 2D convolutional layer mapping on a dot product architecture
US12346812B2 (en) * 2020-02-07 2025-07-01 The Regents Of The University Of California Query optimization for deep convolutional neural network inferences
US11507831B2 (en) * 2020-02-24 2022-11-22 Stmicroelectronics International N.V. Pooling unit for deep learning acceleration
EP4115346A4 (en) * 2020-03-10 2024-03-20 Aip Semi, Inc. Hardware architecture for processing data in neural network
US11604975B2 (en) 2020-04-09 2023-03-14 Apple Inc. Ternary mode of planar engine for neural processor
US11507817B2 (en) 2020-04-17 2022-11-22 Samsung Electronics Co., Ltd. System and method for performing computations for deep neural networks
US11488066B2 (en) * 2020-04-21 2022-11-01 SiMa Technologies, Inc. Efficient convolution of multi-channel input samples with multiple kernels
CN115836299B (zh) * 2020-05-27 2025-10-24 深圳引望智能技术有限公司 使用卷积神经网络（cnn）来处理包括由用于测量距离的2d或3d传感器提供的空间信息的扫描的数据流
JP6931252B1 (ja) * 2020-08-07 2021-09-01 ＬｅａｐＭｉｎｄ株式会社 ニューラルネットワーク回路およびニューラルネットワーク回路の制御方法
KR102430837B1 (ko) * 2020-08-24 2022-08-09 울산과학기술원 기계학습 모델에 포함된 복수의 레이어들을 분할하고, 분할한 레이어들을 수행하는 프로세서를 결정하는 방법 및 상기 방법을 수행하는 장치
CN112070067B (zh) * 2020-10-12 2023-11-21 乐普（北京）医疗器械股份有限公司 一种光体积描计信号的散点图分类方法和装置
KR20220078819A (ko) * 2020-12-04 2022-06-13 삼성전자주식회사 딥러닝 연산 수행 방법 및 장치
JP7413249B2 (ja) * 2020-12-25 2024-01-15 日立Astemo株式会社 情報処理装置、情報処理方法
CN115496190A (zh) * 2021-06-18 2022-12-20 南京大学 一种面向卷积神经网络训练的高效可重构硬件加速器
KR102361249B1 (ko) * 2021-08-02 2022-02-14 오픈엣지테크놀로지 주식회사 브로드캐스팅 멀티플라이 최적화 방법 및 이를 이용한 하드웨어 가속기, 이를 이용한 컴퓨팅 장치
US20230042773A1 (en) * 2021-08-09 2023-02-09 Industry-Academic Cooperation Foundation, Yonsei University Neural network computing device and control method thereof
US12299597B2 (en) 2021-08-27 2025-05-13 Macronix International Co., Ltd. Reconfigurable AI system
JP7788364B2 (ja) 2022-11-16 2025-12-18 ルネサスエレクトロニクス株式会社 画像処理装置及び画像処理方法
US12321603B2 (en) 2023-02-22 2025-06-03 Macronix International Co., Ltd. High bandwidth non-volatile memory for AI inference system
US12417170B2 (en) 2023-05-10 2025-09-16 Macronix International Co., Ltd. Computing system and method of operation thereof

Family Cites Families (31)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6505224B1 (en) 1999-09-29 2003-01-07 Sun Microsystems, Inc. System and computer-implemented method for performing multi-stage fast Walsh transform
US7107304B2 (en) 2001-11-30 2006-09-12 Apple Computer, Inc. Single-channel convolution in a vector processing computer system
US7653675B2 (en) 2005-08-08 2010-01-26 Freescale Semiconductor, Inc. Convolution operation in a multi-mode wireless processing system
JP5075861B2 (ja) 2009-03-16 2012-11-21 株式会社東芝 画像処理装置及び画像処理方法
US8583896B2 (en) * 2009-11-13 2013-11-12 Nec Laboratories America, Inc. Massively parallel processing core with plural chains of processing elements and respective smart memory storing select data received from each chain
US8458635B2 (en) 2009-12-04 2013-06-04 Synopsys, Inc. Convolution computation for many-core processor architectures
US9811775B2 (en) 2012-12-24 2017-11-07 Google Inc. Parallelizing neural networks during training
US9858220B2 (en) * 2014-03-17 2018-01-02 Purdue Research Foundation Computing architecture with concurrent programmable data co-processor
IL231862A (en) * 2014-04-01 2015-04-30 Superfish Ltd Image representation using a neural network
US20150311050A1 (en) * 2014-04-28 2015-10-29 Thermo Finnigan Llc Method for Determining a Spectrum from Time-Varying Data
CN104035751B (zh) * 2014-06-20 2016-10-12 深圳市腾讯计算机系统有限公司 基于多图形处理器的数据并行处理方法及装置
US20160026912A1 (en) * 2014-07-22 2016-01-28 Intel Corporation Weight-shifting mechanism for convolutional neural networks
FR3025344B1 (fr) * 2014-08-28 2017-11-24 Commissariat Energie Atomique Reseau de neurones convolutionnels
US10223333B2 (en) 2014-08-29 2019-03-05 Nvidia Corporation Performing multi-convolution operations in a parallel processing system
EP3035204B1 (en) 2014-12-19 2018-08-15 Intel Corporation Storage device and method for performing convolution operations
US9418458B2 (en) 2015-01-05 2016-08-16 Superfish Ltd. Graph image representation from convolutional neural networks
JP6360802B2 (ja) * 2015-02-20 2018-07-18 株式会社デンソーアイティーラボラトリ ニューラルネットワーク処理装置、ニューラルネットワーク処理方法、検出装置、検出方法、および、車両
US10762894B2 (en) * 2015-03-27 2020-09-01 Google Llc Convolutional neural networks
CN104915322B (zh) * 2015-06-09 2018-05-01 中国人民解放军国防科学技术大学 一种卷积神经网络硬件加速方法
US9734567B2 (en) * 2015-06-24 2017-08-15 Samsung Electronics Co., Ltd. Label-free non-reference image quality assessment via deep neural network
CN105488565A (zh) * 2015-11-17 2016-04-13 中国科学院计算技术研究所 加速深度神经网络算法的加速芯片的运算装置及方法
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
CN105589938A (zh) * 2015-12-13 2016-05-18 公安部第三研究所 基于fpga的图像检索系统及检索方法
US10460231B2 (en) * 2015-12-29 2019-10-29 Samsung Electronics Co., Ltd. Method and apparatus of neural network based image signal processor
CN105681628B (zh) * 2016-01-05 2018-12-07 西安交通大学 一种卷积网络运算单元及可重构卷积神经网络处理器和实现图像去噪处理的方法
CN105678379B (zh) * 2016-01-12 2020-08-07 腾讯科技（深圳）有限公司 一种cnn的处理方法和装置
CN205621018U (zh) * 2016-02-26 2016-10-05 陈进民 手机细胞/卷积神经网络加速器
US10706348B2 (en) 2016-07-13 2020-07-07 Google Llc Superpixel methods for convolutional neural networks
US10402697B2 (en) * 2016-08-01 2019-09-03 Nvidia Corporation Fusing multilayer and multimodal deep neural networks for video classification
US9779786B1 (en) * 2016-10-26 2017-10-03 Xilinx, Inc. Tensor operations and acceleration
US10733505B2 (en) * 2016-11-10 2020-08-04 Google Llc Performing kernel striding in hardware

Also Published As

Publication number Publication date
EP3539059A1 (en) 2019-09-18
EP3539059B1 (en) 2024-02-28
GB2583594A (en) 2020-11-04
WO2018089079A1 (en) 2018-05-17
JP6987860B2 (ja) 2022-01-05
US20200334536A1 (en) 2020-10-22
GB2583594B (en) 2021-07-28
DK3539059T3 (da) 2024-05-27
JP2019537139A (ja) 2019-12-19
US11816532B2 (en) 2023-11-14
IE20170205A1 (en) 2018-05-16
GB202008121D0 (en) 2020-07-15
US10733505B2 (en) 2020-08-04
EP4336411A2 (en) 2024-03-13
FI3539059T3 (fi) 2024-05-24
GB2556670A (en) 2018-06-06
GB2556670B (en) 2020-07-15
DE202017105729U1 (de) 2018-01-03
CN114897132A (zh) 2022-08-12
SG10201804284XA (en) 2018-07-30
JP2022037022A (ja) 2022-03-08
CN108073983A (zh) 2018-05-25
KR102512936B1 (ko) 2023-03-21
GB201715309D0 (en) 2017-11-08
US20180129936A1 (en) 2018-05-10
KR102385843B1 (ko) 2022-04-11
SG10201707700WA (en) 2018-06-28
KR20190084088A (ko) 2019-07-15
CN108073983B (zh) 2022-04-26
HK1254699A1 (zh) 2019-07-26
KR20220047680A (ko) 2022-04-18
EP4336411A3 (en) 2024-04-24
US9721203B1 (en) 2017-08-01
JP7394104B2 (ja) 2023-12-07

Similar Documents

Publication Publication Date Title
DE102017121887A1 (de) Ausführen von Kerndurchschreiten in Hardware
DE102017121257A1 (de) Ausführen von Mittelwert-Poolbildung in Hardware
DE102018105457A1 (de) Transponieren von Matrizen neuronaler Netze in Hardware
DE202016107436U1 (de) Neuronaler Netzwerkprozessor
DE112016002296T5 (de) Vektor-recheneinheit in einem neuronalen netzwerkprozessor
DE102017115519A1 (de) Superpixel-Verfahren für faltende neuronale Netze
DE102018105198A1 (de) Tiefenverkettung unter Verwendung einer Matrixberechnungseinheit
DE102020210965B4 (de) Neuronales graph-transformer-netz-kraftfeld für die vorhersage atomarer kräfte und energien bei moleküldynamiksimulationen
DE112016002292T5 (de) Stapel-verarbeitung in einem neuronalen netzwerkprozessor
DE102018100239B4 (de) Schleifen- und Bibliotheksfusion
DE112016002298T5 (de) Vorabruf von gewichten zur verwendung in einem neuronalen netzwerkprozessor
DE202016107443U1 (de) Berechnen von Faltungen mithilfe eines neuronalen Netzwerkprozessors
DE202016107446U1 (de) Rotation von Daten für Berechnungen in neuronalen Netzwerken
DE112018006189T5 (de) Robuste gradienten-gewichtskomprimierungsschemata für deep-learning-anwendungen
DE102020101187A1 (de) Winograd-transformationsfaltungsoperation für neuronale netze
DE102020105535A1 (de) Neuronale Netzwerkvorrichtung und Verfahren zum Quantisieren von Parametern eines neuronalen Netzwerks
DE112020003128T5 (de) Dilatierte faltung mit systolischem array
DE102019122818A1 (de) Neuronale Netzwerkvorrichtung für eine neuronale Netzwerkoperation, Verfahren zum Betreiben einer neuronalen Netzwerkvorrichtung und Anwendungsprozessor, der die neuronale Netzwerkvorrichtung beinhaltet
DE102018111905A1 (de) Domänenspezifische Sprache zur Erzeugung rekurrenter neuronaler Netzarchitekturen
DE202016008658U1 (de) Bildklassifikationsneuronalnetze
DE102019126719A1 (de) Energieeffiziente Speichersysteme und Verfahren
DE102021107510A1 (de) Training eines neuronalen netzwerks unter speicherbeschränkung
DE102021108622A1 (de) Neuronale netzvorrichtung , verfahren zum betrieb der neuronalen netzvorrichtung und anwendungsprozessor, der die neuronale netzvorrichtung umfasst
DE112020004231T5 (de) Ausführen von skalarproduktoperationen unter verwendung einer memristiven crossbar-anordnung
DE112019000676T5 (de) Zentraler scheduler und anweisungszuteiler für einen neuronalen inferenzprozessor

Legal Events

Date Code Title Description
R012 Request for examination validly filed
R081 Change of applicant/patentee

Owner name: GOOGLE LLC (N.D.GES.D.STAATES DELAWARE), MOUNT, US

Free format text: FORMER OWNER: GOOGLE INC., MOUNTAIN VIEW, CALIF., US

R120 Application withdrawn or ip right abandoned