CN111247775B - 用于消息传递计算系统的存储器映射接口 - Google Patents

用于消息传递计算系统的存储器映射接口 Download PDF

Info

Publication number
CN111247775B
CN111247775B CN201880067730.XA CN201880067730A CN111247775B CN 111247775 B CN111247775 B CN 111247775B CN 201880067730 A CN201880067730 A CN 201880067730A CN 111247775 B CN111247775 B CN 111247775B
Authority
CN
China
Prior art keywords
address
interface
neural network
write
data
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.)
Active
Application number
CN201880067730.XA
Other languages
English (en)
Chinese (zh)
Other versions
CN111247775A (zh
Inventor
A·S·卡斯迪
F·阿考佩安
J·V·阿尔苏尔
M·V·德宝乐
P·梅罗拉
D·莫德哈
J·萨瓦达
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.)
International Business Machines Corp
Original Assignee
International Business Machines Corp
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 International Business Machines Corp filed Critical International Business Machines Corp
Publication of CN111247775A publication Critical patent/CN111247775A/zh
Application granted granted Critical
Publication of CN111247775B publication Critical patent/CN111247775B/zh
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00—Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02—Addressing or allocation; Relocation
    • G06F12/06—Addressing a physical block of locations, e.g. base addressing, module addressing, memory dedication
    • G06F12/0615—Address space extension
    • G06F12/063—Address space extension for I/O modules, e.g. memory mapped I/O
    • 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
    • G06F12/00—Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02—Addressing or allocation; Relocation
    • G06F12/08—Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
    • G06F12/10—Address translation
    • G06F12/1027—Address translation using associative or pseudo-associative address translation means, e.g. translation look-aside buffer [TLB]
    • 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
    • G06N3/0495—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
    • G06N3/10—Interfaces, programming languages or software development kits, e.g. for simulating neural networks
    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11C—STATIC STORES
    • G11C7/00—Arrangements for writing information into, or reading information out from, a digital store
    • G11C7/10—Input/output [I/O] data interface arrangements, e.g. I/O data control circuits, I/O data buffers
    • G11C7/1051—Data output circuits, e.g. read-out amplifiers, data output buffers, data output registers, data output level conversion circuits
    • G11C7/1057—Data output buffers, e.g. comprising level conversion circuits, circuits for adapting load
    • 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
    • G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
    • G—PHYSICS
    • G11—INFORMATION STORAGE
    • G11C—STATIC STORES
    • G11C11/00—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor
    • G11C11/54—Digital stores characterised by the use of particular electric or magnetic storage elements; Storage elements therefor using elements simulating biological cells, e.g. neuron

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)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Evolutionary Computation (AREA)
  • Molecular Biology (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Artificial Intelligence (AREA)
  • Neurology (AREA)
  • Data Exchanges In Wide-Area Networks (AREA)
  • Multi Processors (AREA)
  • Advance Control (AREA)
  • Information Transfer Systems (AREA)
  • Computer And Data Communications (AREA)
CN201880067730.XA 2017-10-20 2018-10-12 用于消息传递计算系统的存储器映射接口 Active CN111247775B (zh)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US15/789,472 US10452540B2 (en) 2017-10-20 2017-10-20 Memory-mapped interface for message passing computing systems
US15/789,472 2017-10-20
PCT/IB2018/057922 WO2019077455A1 (en) 2017-10-20 2018-10-12 MAPPED MEMORY INTERFACE FOR MESSAGE PASSING COMPUTER SYSTEMS

Publications (2)

Publication Number Publication Date
CN111247775A CN111247775A (zh) 2020-06-05
CN111247775B true CN111247775B (zh) 2022-04-12

Family

ID=66171106

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201880067730.XA Active CN111247775B (zh) 2017-10-20 2018-10-12 用于消息传递计算系统的存储器映射接口

Country Status (6)

Country Link
US (2) US10452540B2 (cg-RX-API-DMAC7.html)
JP (1) JP7248667B2 (cg-RX-API-DMAC7.html)
CN (1) CN111247775B (cg-RX-API-DMAC7.html)
DE (1) DE112018004382B4 (cg-RX-API-DMAC7.html)
GB (1) GB2581904B (cg-RX-API-DMAC7.html)
WO (1) WO2019077455A1 (cg-RX-API-DMAC7.html)

Families Citing this family (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9924490B2 (en) * 2013-10-09 2018-03-20 International Business Machines Corporation Scaling multi-core neurosynaptic networks across chip boundaries
US9406015B2 (en) 2013-12-27 2016-08-02 International Business Machines Corporation Transform for a neurosynaptic core circuit
US9412063B2 (en) * 2013-12-27 2016-08-09 International Business Machines Corporation Transform architecture for multiple neurosynaptic core circuits
US12210952B2 (en) * 2017-11-29 2025-01-28 Electronics And Telecommunications Research Institute Reorganizable data processing array for neural network computing
EP3716154A1 (en) * 2019-03-27 2020-09-30 GrAl Matter Labs S.A.S. Neuromorphic processing system and method of operating the same
CN114144793B (zh) * 2019-08-05 2024-10-18 华为技术有限公司 数据传输方法、装置、电子设备及可读存储介质
CN112418389A (zh) * 2019-08-23 2021-02-26 北京希姆计算科技有限公司 数据处理方法、装置、电子设备及计算机可读存储介质
CN111241173B (zh) * 2019-12-29 2024-03-12 航天信息股份有限公司 一种用于多个系统间数据交互的方法及系统
DE102020202093A1 (de) 2020-02-19 2021-08-19 Robert Bosch Gesellschaft mit beschränkter Haftung Verfahren und Vorrichtung für maschinelles Lernen
KR102891573B1 (ko) 2020-06-30 2025-11-26 삼성전자주식회사 텐서 처리 방법, 가속기 및 이를 포함한 가속기 시스템
US20220101108A1 (en) * 2020-09-30 2022-03-31 International Business Machines Corporation Memory-mapped neural network accelerator for deployable inference systems
US20230133088A1 (en) * 2021-11-01 2023-05-04 Femtosense, Inc. Methods and apparatus for system-on-a-chip neural network processing applications
CN114785907B (zh) * 2022-04-18 2025-06-24 清华大学 通信系统、通信方法、存储介质及程序产品

Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5214747A (en) * 1990-12-24 1993-05-25 Eastman Kodak Company Segmented neural network with daisy chain control
CN1250532A (zh) * 1997-01-09 2000-04-12 奥潘弗雷姆有限公司 数据共享方法和计算机体系结构
CN103117933A (zh) * 2013-03-04 2013-05-22 中国科学院高能物理研究所 在多点通信网络中传送数据的方法和系统
US8489854B1 (en) * 2010-02-26 2013-07-16 Western Digital Technologies, Inc. Non-volatile semiconductor memory storing an inverse map for rebuilding a translation table
CN103455371A (zh) * 2012-05-31 2013-12-18 国际商业机器公司 用于优化的管芯内小节点间消息通信的方法和系统
CN104915302A (zh) * 2014-03-10 2015-09-16 华为技术有限公司 数据传输处理方法和数据传输器
CN105027213A (zh) * 2013-03-12 2015-11-04 惠普发展公司,有限责任合伙企业 可编程地址映射和存储器访问操作
CN105229675A (zh) * 2013-05-21 2016-01-06 高通股份有限公司 尖峰网络的高效硬件实现
CN105786398A (zh) * 2014-11-18 2016-07-20 财团法人工业技术研究院 存储器映射方法和存储器映射系统
EP3098762A1 (en) * 2015-05-29 2016-11-30 Samsung Electronics Co., Ltd. Data-optimized neural network traversal

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH05242065A (ja) * 1992-02-28 1993-09-21 Hitachi Ltd 情報処理装置及びシステム
US5956703A (en) * 1995-07-28 1999-09-21 Delco Electronics Corporation Configurable neural network integrated circuit
JP3524250B2 (ja) * 1995-11-27 2004-05-10 キヤノン株式会社 デジタル画像処理プロセッサ
US7620791B1 (en) * 2006-04-14 2009-11-17 Tilera Corporation Mapping memory in a parallel processing environment
US7624248B1 (en) * 2006-04-14 2009-11-24 Tilera Corporation Managing memory in a parallel processing environment
US9262712B2 (en) * 2013-03-08 2016-02-16 International Business Machines Corporation Structural descriptions for neurosynaptic networks
KR20150016089A (ko) * 2013-08-02 2015-02-11 안병익 신경망 컴퓨팅 장치 및 시스템과 그 방법
US10650301B2 (en) * 2014-05-08 2020-05-12 International Business Machines Corporation Utilizing a distributed and parallel set of neurosynaptic core circuits for neuronal computation and non-neuronal computation
KR102835519B1 (ko) * 2016-09-28 2025-07-17 에스케이하이닉스 주식회사 합성곱 신경망의 연산 장치 및 방법
US10726583B2 (en) * 2016-12-30 2020-07-28 Intel Corporation System and method of encoding and decoding feature maps and weights for a convolutional neural network
US11062203B2 (en) * 2016-12-30 2021-07-13 Intel Corporation Neuromorphic computer with reconfigurable memory mapping for various neural network topologies

Patent Citations (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5214747A (en) * 1990-12-24 1993-05-25 Eastman Kodak Company Segmented neural network with daisy chain control
CN1250532A (zh) * 1997-01-09 2000-04-12 奥潘弗雷姆有限公司 数据共享方法和计算机体系结构
US8489854B1 (en) * 2010-02-26 2013-07-16 Western Digital Technologies, Inc. Non-volatile semiconductor memory storing an inverse map for rebuilding a translation table
CN103455371A (zh) * 2012-05-31 2013-12-18 国际商业机器公司 用于优化的管芯内小节点间消息通信的方法和系统
CN103117933A (zh) * 2013-03-04 2013-05-22 中国科学院高能物理研究所 在多点通信网络中传送数据的方法和系统
CN105027213A (zh) * 2013-03-12 2015-11-04 惠普发展公司,有限责任合伙企业 可编程地址映射和存储器访问操作
CN105229675A (zh) * 2013-05-21 2016-01-06 高通股份有限公司 尖峰网络的高效硬件实现
CN104915302A (zh) * 2014-03-10 2015-09-16 华为技术有限公司 数据传输处理方法和数据传输器
CN105786398A (zh) * 2014-11-18 2016-07-20 财团法人工业技术研究院 存储器映射方法和存储器映射系统
EP3098762A1 (en) * 2015-05-29 2016-11-30 Samsung Electronics Co., Ltd. Data-optimized neural network traversal

Non-Patent Citations (3)

* Cited by examiner, † Cited by third party
Title
"Implementing Spiking Neural Networks for Real-Time Signal-Processing and Control Applications: A Model-Validated FPGA Approach";Martin J. Pearson,等;《IEEE Transactions on Neural Networks 》;20070904;第1472-1487页 *
"大数据技术发展的十个前沿方向(中)";吴甘沙;《大数据》;20150630;第1-11页 *
Martin J. Pearson,等."Implementing Spiking Neural Networks for Real-Time Signal-Processing and Control Applications: A Model-Validated FPGA Approach".《IEEE Transactions on Neural Networks 》.2007,第1472-1487页. *

Also Published As

Publication number Publication date
CN111247775A (zh) 2020-06-05
US10838860B2 (en) 2020-11-17
DE112018004382T5 (de) 2020-05-14
GB2581904A (en) 2020-09-02
JP2021500648A (ja) 2021-01-07
US10452540B2 (en) 2019-10-22
DE112018004382B4 (de) 2025-04-17
JP7248667B2 (ja) 2023-03-29
US20200004678A1 (en) 2020-01-02
WO2019077455A1 (en) 2019-04-25
US20190121734A1 (en) 2019-04-25
GB202007034D0 (en) 2020-06-24
GB2581904B (en) 2022-11-16

Similar Documents

Publication Publication Date Title
US10838860B2 (en) Memory-mapped interface to message-passing computing systems
US12335142B2 (en) Network interface for data transport in heterogeneous computing environments
EP3706394B1 (en) Writes to multiple memory destinations
US11494212B2 (en) Technologies for adaptive platform resource assignment
US12554961B2 (en) Block transfer of neuron output values through data memory for neurosynaptic processors
US20190303741A1 (en) Defect resistant designs for location-sensitive neural network processor arrays
JP7051854B2 (ja) 面積高効率、再設定可能、エネルギ高効率、速度高効率のニューラル・ネットワーク基板
CN109564637B (zh) 用于可扩展流突触超级计算机的方法、系统和介质
US11645501B2 (en) Distributed, event-based computation using neuromorphic cores
US20210166107A1 (en) Event-based neural network with hierarchical addressing for routing event packets between core circuits of the neural network
CN109478171A (zh) 提高openfabrics环境中的吞吐量
US9823862B2 (en) Storage system
US12056072B1 (en) Low latency memory notification
US20250258778A1 (en) Ordered store operations in a multiprocessor system
Bonatto et al. Memory subsystem architecture design for multimedia applications

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant