DK3568756T3 - Specialformålstræningschip til neuralt netværk - Google Patents
Specialformålstræningschip til neuralt netværk Download PDFInfo
- Publication number
- DK3568756T3 DK3568756T3 DK18735433.7T DK18735433T DK3568756T3 DK 3568756 T3 DK3568756 T3 DK 3568756T3 DK 18735433 T DK18735433 T DK 18735433T DK 3568756 T3 DK3568756 T3 DK 3568756T3
- Authority
- DK
- Denmark
- Prior art keywords
- neural network
- special purpose
- purpose training
- training chip
- chip
- Prior art date
Links
- 238000013528 artificial neural network Methods 0.000 title 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR 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; CALCULATING OR 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
- G06F9/30032—Movement instructions, e.g. MOVE, SHIFT, ROTATE, SHUFFLE
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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
- G06F9/30141—Implementation provisions of register files, e.g. ports
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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, look ahead
- G06F9/3885—Concurrent instruction execution, e.g. pipeline, look ahead using a plurality of independent parallel functional units
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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, look ahead
- G06F9/3885—Concurrent instruction execution, e.g. pipeline, look ahead using a plurality of independent parallel functional units
- G06F9/3887—Concurrent instruction execution, e.g. pipeline, look ahead using a plurality of independent parallel functional units controlled by a single instruction for multiple data lanes [SIMD]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR 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; CALCULATING OR 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; CALCULATING OR 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- Mathematical Optimization (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- Neurology (AREA)
- Databases & Information Systems (AREA)
- Algebra (AREA)
- Advance Control (AREA)
- Complex Calculations (AREA)
- Executing Machine-Instructions (AREA)
- Memory System Of A Hierarchy Structure (AREA)
- Computer Hardware Design (AREA)
- Nonlinear Science (AREA)
- Rehabilitation Tools (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US201762507771P | 2017-05-17 | 2017-05-17 | |
PCT/US2018/033215 WO2018213598A1 (en) | 2017-05-17 | 2018-05-17 | Special purpose neural network training chip |
Publications (1)
Publication Number | Publication Date |
---|---|
DK3568756T3 true DK3568756T3 (da) | 2022-09-19 |
Family
ID=62784215
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
DK18735433.7T DK3568756T3 (da) | 2017-05-17 | 2018-05-17 | Specialformålstræningschip til neuralt netværk |
Country Status (8)
Country | Link |
---|---|
US (2) | US11275992B2 (da) |
EP (3) | EP3568756B1 (da) |
JP (3) | JP6938661B2 (da) |
KR (4) | KR20240056801A (da) |
CN (2) | CN116644790A (da) |
DK (1) | DK3568756T3 (da) |
TW (3) | TWI769810B (da) |
WO (1) | WO2018213598A1 (da) |
Families Citing this family (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US10853070B1 (en) * | 2017-10-23 | 2020-12-01 | Habana Labs Ltd. | Processor suspension buffer and instruction queue |
US11645358B2 (en) * | 2019-01-29 | 2023-05-09 | Hewlett Packard Enterprise Development Lp | Generation of executable files corresponding to neural network models |
US10997116B2 (en) * | 2019-08-06 | 2021-05-04 | Microsoft Technology Licensing, Llc | Tensor-based hardware accelerator including a scalar-processing unit |
KR102496734B1 (ko) * | 2019-10-22 | 2023-02-06 | 에스앤즈 주식회사 | 분산환경 패킷 전송 기반의 스트리밍 데이터 딥러닝 처리 가속화 시스템 및 이를 이용한 멀티 로케이션 멀티 스트리밍 이상상태 탐지 시스템 |
CN111047036B (zh) * | 2019-12-09 | 2023-11-14 | Oppo广东移动通信有限公司 | 神经网络处理器、芯片和电子设备 |
US11054998B1 (en) * | 2019-12-12 | 2021-07-06 | Facebook, Inc. | High bandwidth memory system with distributed request broadcasting masters |
US11755683B2 (en) | 2019-12-23 | 2023-09-12 | Western Digital Technologies, Inc. | Flexible accelerator for sparse tensors (FAST) in machine learning |
US11797830B2 (en) | 2020-03-25 | 2023-10-24 | Western Digital Technologies, Inc. | Flexible accelerator for sparse tensors in convolutional neural networks |
US11462003B2 (en) | 2020-03-25 | 2022-10-04 | Western Digital Technologies, Inc. | Flexible accelerator for sparse tensors in convolutional neural networks |
US20210312266A1 (en) * | 2020-04-01 | 2021-10-07 | Microsoft Technology Licensing, Llc | Deep neural network accelerator with independent datapaths for simultaneous processing of different classes of operations |
CN113867788A (zh) * | 2020-06-30 | 2021-12-31 | 上海寒武纪信息科技有限公司 | 一种计算装置、芯片、板卡、电子设备和计算方法 |
CN112148453A (zh) * | 2020-09-29 | 2020-12-29 | 深圳致星科技有限公司 | 用于隐私计算的计算芯片及网络计算系统 |
CN112416433B (zh) * | 2020-11-24 | 2023-01-17 | 中科寒武纪科技股份有限公司 | 一种数据处理装置、数据处理方法及相关产品 |
EP4012623A1 (en) * | 2020-12-10 | 2022-06-15 | Toyota Jidosha Kabushiki Kaisha | Efficient and stable training of a neural network in compressed form |
WO2022133623A1 (en) * | 2020-12-24 | 2022-06-30 | Intel Corporation | Accelerated scale-out performance of deep learning training workload with embedding tables |
CN112860318A (zh) * | 2021-01-29 | 2021-05-28 | 成都商汤科技有限公司 | 一种数据传输方法、芯片、设备和存储介质 |
US11782871B2 (en) | 2021-04-27 | 2023-10-10 | Microchip Technology Inc. | Method and apparatus for desynchronizing execution in a vector processor |
TWI808000B (zh) * | 2022-09-20 | 2023-07-01 | 創鑫智慧股份有限公司 | 矩陣裝置及其操作方法 |
CN115713103B (zh) * | 2022-11-24 | 2023-08-18 | 辉羲智能科技(上海)有限公司 | 片上-片间互连的神经网络芯片联合性能预测方法及系统 |
TWI830669B (zh) * | 2023-02-22 | 2024-01-21 | 旺宏電子股份有限公司 | 編碼方法及編碼電路 |
Family Cites Families (23)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPS5841071B2 (ja) | 1981-10-13 | 1983-09-09 | 東北電子産業株式会社 | 生体誘導加熱装置 |
JPH04290155A (ja) | 1991-03-19 | 1992-10-14 | Fujitsu Ltd | 並列データ処理方式 |
CA2040903C (en) * | 1991-04-22 | 2003-10-07 | John G. Sutherland | Neural networks |
US5872988A (en) * | 1992-06-17 | 1999-02-16 | U.S. Philips Corporation | Parallel data processing device having a concatenated data path between elementary processors |
US5423051A (en) * | 1992-09-24 | 1995-06-06 | International Business Machines Corporation | Execution unit with an integrated vector operation capability |
AU2002338616A1 (en) * | 2001-02-06 | 2002-10-28 | Victor Demjanenko | Vector processor architecture and methods performed therein |
US7305540B1 (en) * | 2001-12-31 | 2007-12-04 | Apple Inc. | Method and apparatus for data processing |
US7219085B2 (en) * | 2003-12-09 | 2007-05-15 | Microsoft Corporation | System and method for accelerating and optimizing the processing of machine learning techniques using a graphics processing unit |
US8396582B2 (en) * | 2008-03-08 | 2013-03-12 | Tokyo Electron Limited | Method and apparatus for self-learning and self-improving a semiconductor manufacturing tool |
EP2798475A4 (en) * | 2011-12-30 | 2016-07-13 | Intel Corp | TRANSPOSED INSTRUCTION |
US9785565B2 (en) * | 2014-06-30 | 2017-10-10 | Microunity Systems Engineering, Inc. | System and methods for expandably wide processor instructions |
US9589443B2 (en) | 2014-09-02 | 2017-03-07 | At&T Intellectual Property I, L.P. | Method and apparatus for providing an emergency notification for an allergic reaction |
KR102277439B1 (ko) * | 2014-10-21 | 2021-07-14 | 삼성전자주식회사 | 재구성 가능 프로세서 및 그 동작 방법 |
US9965824B2 (en) | 2015-04-23 | 2018-05-08 | Google Llc | Architecture for high performance, power efficient, programmable image processing |
US9772852B2 (en) * | 2015-04-23 | 2017-09-26 | Google Inc. | Energy efficient processor core architecture for image processor |
US9747546B2 (en) * | 2015-05-21 | 2017-08-29 | Google Inc. | Neural network processor |
US10192162B2 (en) | 2015-05-21 | 2019-01-29 | Google Llc | Vector computation unit in a neural network processor |
US20160378465A1 (en) | 2015-06-23 | 2016-12-29 | Intel Corporation | Efficient sparse array handling in a processor |
GB2543554B (en) | 2015-10-22 | 2019-01-23 | Advanced Risc Mach Ltd | Handling exceptional conditions for vector arithmetic instruction |
US9904874B2 (en) * | 2015-11-05 | 2018-02-27 | Microsoft Technology Licensing, Llc | Hardware-efficient deep convolutional neural networks |
US9898441B2 (en) | 2016-02-05 | 2018-02-20 | Google Llc | Matrix processing apparatus |
WO2017146706A1 (en) * | 2016-02-25 | 2017-08-31 | Hewlett Packard Enterprise Development Lp | Performing complex multiply-accumulate operations |
EP3812900B1 (en) * | 2016-12-31 | 2023-11-29 | Intel Corporation | Systems, methods, and apparatuses for heterogeneous computing |
-
2018
- 2018-05-17 TW TW110117076A patent/TWI769810B/zh active
- 2018-05-17 KR KR1020247013765A patent/KR20240056801A/ko active Application Filing
- 2018-05-17 TW TW111120440A patent/TWI812254B/zh active
- 2018-05-17 TW TW107116869A patent/TWI728247B/zh active
- 2018-05-17 CN CN202310655432.5A patent/CN116644790A/zh active Pending
- 2018-05-17 KR KR1020197026557A patent/KR102312264B1/ko active IP Right Grant
- 2018-05-17 WO PCT/US2018/033215 patent/WO2018213598A1/en unknown
- 2018-05-17 EP EP18735433.7A patent/EP3568756B1/en active Active
- 2018-05-17 KR KR1020227045015A patent/KR102661910B1/ko active IP Right Grant
- 2018-05-17 JP JP2019549507A patent/JP6938661B2/ja active Active
- 2018-05-17 US US15/983,056 patent/US11275992B2/en active Active
- 2018-05-17 CN CN201880018006.8A patent/CN110622134B/zh active Active
- 2018-05-17 KR KR1020217031994A patent/KR102481428B1/ko active IP Right Grant
- 2018-05-17 EP EP22171943.8A patent/EP4083789B1/en active Active
- 2018-05-17 EP EP24163748.7A patent/EP4361832A2/en active Pending
- 2018-05-17 DK DK18735433.7T patent/DK3568756T3/da active
-
2021
- 2021-09-01 JP JP2021142529A patent/JP7314217B2/ja active Active
-
2022
- 2022-03-14 US US17/694,598 patent/US20220261622A1/en active Pending
-
2023
- 2023-07-12 JP JP2023114361A patent/JP2023145517A/ja active Pending
Also Published As
Publication number | Publication date |
---|---|
EP4083789A1 (en) | 2022-11-02 |
US20180336456A1 (en) | 2018-11-22 |
JP2023145517A (ja) | 2023-10-11 |
KR102481428B1 (ko) | 2022-12-23 |
KR20240056801A (ko) | 2024-04-30 |
TW202311939A (zh) | 2023-03-16 |
TWI769810B (zh) | 2022-07-01 |
KR102312264B1 (ko) | 2021-10-12 |
JP6938661B2 (ja) | 2021-09-22 |
TW202132978A (zh) | 2021-09-01 |
TW201908965A (zh) | 2019-03-01 |
KR20210123435A (ko) | 2021-10-13 |
KR102661910B1 (ko) | 2024-04-26 |
EP3568756B1 (en) | 2022-07-06 |
EP4361832A2 (en) | 2024-05-01 |
JP7314217B2 (ja) | 2023-07-25 |
TWI812254B (zh) | 2023-08-11 |
US11275992B2 (en) | 2022-03-15 |
EP4083789B1 (en) | 2024-05-15 |
TWI728247B (zh) | 2021-05-21 |
EP3568756A1 (en) | 2019-11-20 |
JP2022003532A (ja) | 2022-01-11 |
WO2018213598A1 (en) | 2018-11-22 |
CN110622134A (zh) | 2019-12-27 |
CN110622134B (zh) | 2023-06-27 |
CN116644790A (zh) | 2023-08-25 |
KR20190111132A (ko) | 2019-10-01 |
JP2020519981A (ja) | 2020-07-02 |
KR20230003443A (ko) | 2023-01-05 |
US20220261622A1 (en) | 2022-08-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
DK3568756T3 (da) | Specialformålstræningschip til neuralt netværk | |
DK3731771T3 (da) | V462033dk00 | |
DK3114540T3 (da) | Neuralt netværk og fremgangsmåder til træning af neuralt netværk | |
DE202018003363U8 (de) | Handgelenkssphygmomanometer | |
MA41950A (fr) | Dispositif de neuromodulation | |
CL2018000524S1 (es) | Golilla | |
DK3351526T3 (da) | Diisopentylterephthalat | |
DK3680364T3 (da) | Elektrolyseindretning | |
DK3568655T3 (da) | Rekuperator | |
DK3571580T5 (da) | Load-logical-and-shift-guarded-instruktion | |
DK3612237T3 (da) | Genterapi | |
IT201700027605A1 (it) | Apparato fotovoltaico. | |
DK3568506T3 (da) | Offeranode | |
DK3576686T3 (da) | Brokbind | |
FR3054629B1 (fr) | Dispositif antivibratoire hydraulique | |
FR3054628B1 (fr) | Dispositif antivibratoire hydraulique | |
DK3676276T3 (da) | Spirothietannukleosider | |
DK3621705T3 (da) | Træningsapparat | |
DK3576718T3 (da) | Pastil | |
FI11557U1 (fi) | Liikuntaväline | |
DK3510051T3 (da) | Carboxylalkylchitosan | |
DK3714101T3 (da) | Sporskifte | |
DK3395159T3 (da) | Ballepresse | |
DK3426014T3 (da) | Fordelingsmaskine | |
GB2578024B (en) | Animal bridge |