TWI781509B - 用於將稀疏元素變換為一密集矩陣之系統及方法，以及非暫時性機器可讀儲存裝置 - Google Patents

用於將稀疏元素變換為一密集矩陣之系統及方法，以及非暫時性機器可讀儲存裝置 Download PDF

Info

Publication number
TWI781509B
TWI781509B TW110100489A TW110100489A TWI781509B TW I781509 B TWI781509 B TW I781509B TW 110100489 A TW110100489 A TW 110100489A TW 110100489 A TW110100489 A TW 110100489A TW I781509 B TWI781509 B TW I781509B
Authority
TW
Taiwan
Prior art keywords
sparse
unit
dense
elements
element access
Prior art date
Application number
TW110100489A
Other languages
English (en)
Chinese (zh)
Other versions
TW202131172A (zh
Inventor
拉非 納拉亞那斯瓦密
拉浩 納加拉簡
禹同爀
克里斯多福 丹尼爾 理瑞
Original Assignee
美商谷歌有限責任公司
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 美商谷歌有限責任公司 filed Critical 美商谷歌有限責任公司
Publication of TW202131172A publication Critical patent/TW202131172A/zh
Application granted granted Critical
Publication of TWI781509B publication Critical patent/TWI781509B/zh

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
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Mathematical Physics (AREA)
  • Theoretical Computer Science (AREA)
  • Pure & Applied Mathematics (AREA)
  • Mathematical Analysis (AREA)
  • Computational Mathematics (AREA)
  • Mathematical Optimization (AREA)
  • Data Mining & Analysis (AREA)
  • Software Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Algebra (AREA)
  • Databases & Information Systems (AREA)
  • Computing Systems (AREA)
  • Complex Calculations (AREA)
  • Error Detection And Correction (AREA)
  • Multi Processors (AREA)
  • Magnetic Resonance Imaging Apparatus (AREA)
TW110100489A 2016-02-05 2016-12-29 用於將稀疏元素變換為一密集矩陣之系統及方法，以及非暫時性機器可讀儲存裝置 TWI781509B (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US15/016,420 2016-02-05
US15/016,420 US9805001B2 (en) 2016-02-05 2016-02-05 Matrix processing apparatus

Publications (2)

Publication Number Publication Date
TW202131172A TW202131172A (zh) 2021-08-16
TWI781509B true TWI781509B (zh) 2022-10-21

Family

ID=57708453

Family Applications (4)

Application Number Title Priority Date Filing Date
TW110100489A TWI781509B (zh) 2016-02-05 2016-12-29 用於將稀疏元素變換為一密集矩陣之系統及方法，以及非暫時性機器可讀儲存裝置
TW108126777A TWI718604B (zh) 2016-02-05 2016-12-29 用於將稀疏元素變換為一密集矩陣之系統及方法，以及非暫時性機器可讀儲存裝置
TW107112523A TWI670613B (zh) 2016-02-05 2016-12-29 用於將稀疏元素變換為一密集矩陣之系統及方法，以及非暫時性機器可讀儲存裝置
TW105143869A TWI624763B (zh) 2016-02-05 2016-12-29 矩陣處理裝置

Family Applications After (3)

Application Number Title Priority Date Filing Date
TW108126777A TWI718604B (zh) 2016-02-05 2016-12-29 用於將稀疏元素變換為一密集矩陣之系統及方法，以及非暫時性機器可讀儲存裝置
TW107112523A TWI670613B (zh) 2016-02-05 2016-12-29 用於將稀疏元素變換為一密集矩陣之系統及方法，以及非暫時性機器可讀儲存裝置
TW105143869A TWI624763B (zh) 2016-02-05 2016-12-29 矩陣處理裝置

Country Status (8)

Country Link
US (6) US9805001B2 (enExample)
EP (2) EP3203382A1 (enExample)
JP (4) JP6524052B2 (enExample)
KR (4) KR101980365B1 (enExample)
CN (2) CN112000919B (enExample)
BR (1) BR102016030970A8 (enExample)
SG (2) SG10201808521PA (enExample)
TW (4) TWI781509B (enExample)

Families Citing this family (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11249759B2 (en) * 2013-07-15 2022-02-15 Texas Instruments Incorporated Two-dimensional zero padding in a stream of matrix elements
US11256508B2 (en) 2013-07-15 2022-02-22 Texas Instruments Incorporated Inserting null vectors into a stream of vectors
US9805001B2 (en) * 2016-02-05 2017-10-31 Google Inc. Matrix processing apparatus
US10635739B1 (en) 2016-08-25 2020-04-28 Cyber Atomics, Inc. Multidimensional connectivity graph-based tensor processing
US10621268B1 (en) 2016-08-25 2020-04-14 Cyber Atomics, Inc. Multidimensional tensor processing
JP6912703B2 (ja) * 2017-02-24 2021-08-04 富士通株式会社 演算方法、演算装置、演算プログラム及び演算システム
US10489481B1 (en) 2017-02-24 2019-11-26 Cyber Atomics, Inc. Efficient matrix property determination with pipelining and parallelism
US10936942B2 (en) 2017-11-21 2021-03-02 Google Llc Apparatus and mechanism for processing neural network tasks using a single chip package with multiple identical dies
CN108804684B (zh) * 2018-06-13 2020-11-03 北京搜狗科技发展有限公司 一种数据处理方法和装置
US10719323B2 (en) 2018-09-27 2020-07-21 Intel Corporation Systems and methods for performing matrix compress and decompress instructions
CN113794709B (zh) * 2021-09-07 2022-06-24 北京理工大学 一种用于二值稀疏矩阵的混合编码方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102141976A (zh) * 2011-01-10 2011-08-03 中国科学院软件研究所 稀疏矩阵的对角线数据存储方法及基于该方法的SpMV实现方法
CN103262068A (zh) * 2010-12-20 2013-08-21 萨思学会有限公司 用于使用单遍等级化单次遍历数据来产生叉积矩阵的系统及方法
US20130339506A1 (en) * 2012-06-13 2013-12-19 International Business Machines Corporation Performing synchronized collective operations over multiple process groups
CN103984527A (zh) * 2014-04-01 2014-08-13 杭州电子科技大学 优化稀疏矩阵向量乘提升不可压缩管流模拟效率的方法

Family Cites Families (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5765011A (en) 1990-11-13 1998-06-09 International Business Machines Corporation Parallel processing system having a synchronous SIMD processing with processing elements emulating SIMD operation using individual instruction streams
US5625836A (en) 1990-11-13 1997-04-29 International Business Machines Corporation SIMD/MIMD processing memory element (PME)
US5708836A (en) 1990-11-13 1998-01-13 International Business Machines Corporation SIMD/MIMD inter-processor communication
GB2251320A (en) * 1990-12-20 1992-07-01 Motorola Ltd Parallel processor
JP2557175B2 (ja) * 1992-05-22 1996-11-27 インターナショナル・ビジネス・マシーンズ・コーポレイション コンピュータ・システム
US5446908A (en) 1992-10-21 1995-08-29 The United States Of America As Represented By The Secretary Of The Navy Method and apparatus for pre-processing inputs to parallel architecture computers
US5644517A (en) 1992-10-22 1997-07-01 International Business Machines Corporation Method for performing matrix transposition on a mesh multiprocessor architecture having multiple processor with concurrent execution of the multiple processors
JP3348367B2 (ja) * 1995-12-06 2002-11-20 富士通株式会社 多重アクセス方法および多重アクセスキャッシュメモリ装置
JP3639206B2 (ja) * 2000-11-24 2005-04-20 富士通株式会社 共有メモリ型スカラ並列計算機における並列行列処理方法、及び記録媒体
EP1370966B1 (en) 2001-02-24 2010-08-25 International Business Machines Corporation A novel massively parrallel supercomputer
WO2002069550A1 (en) * 2001-02-24 2002-09-06 International Business Machines Corporation Class network routing
US6898691B2 (en) * 2001-06-06 2005-05-24 Intrinsity, Inc. Rearranging data between vector and matrix forms in a SIMD matrix processor
US6961888B2 (en) 2002-08-20 2005-11-01 Flarion Technologies, Inc. Methods and apparatus for encoding LDPC codes
US8380778B1 (en) * 2007-10-25 2013-02-19 Nvidia Corporation System, method, and computer program product for assigning elements of a matrix to processing threads with increased contiguousness
WO2011156247A2 (en) 2010-06-11 2011-12-15 Massachusetts Institute Of Technology Processor for large graph algorithm computations and matrix operations
US8549259B2 (en) 2010-09-15 2013-10-01 International Business Machines Corporation Performing a vector collective operation on a parallel computer having a plurality of compute nodes
US9170836B2 (en) * 2013-01-09 2015-10-27 Nvidia Corporation System and method for re-factorizing a square matrix into lower and upper triangular matrices on a parallel processor
JP6083300B2 (ja) * 2013-03-29 2017-02-22 富士通株式会社 プログラム、並列演算方法および情報処理装置
US9367519B2 (en) * 2013-08-30 2016-06-14 Microsoft Technology Licensing, Llc Sparse matrix data structure
US9471377B2 (en) 2013-11-13 2016-10-18 Reservoir Labs, Inc. Systems and methods for parallelizing and optimizing sparse tensor computations
US9715481B2 (en) 2014-06-27 2017-07-25 Oracle International Corporation Approach for more efficient use of computing resources while calculating cross product or its approximation for logistic regression on big data sets
US9898441B2 (en) * 2016-02-05 2018-02-20 Google Llc Matrix processing apparatus
US9805001B2 (en) * 2016-02-05 2017-10-31 Google Inc. Matrix processing apparatus

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103262068A (zh) * 2010-12-20 2013-08-21 萨思学会有限公司 用于使用单遍等级化单次遍历数据来产生叉积矩阵的系统及方法
CN102141976A (zh) * 2011-01-10 2011-08-03 中国科学院软件研究所 稀疏矩阵的对角线数据存储方法及基于该方法的SpMV实现方法
US20130339506A1 (en) * 2012-06-13 2013-12-19 International Business Machines Corporation Performing synchronized collective operations over multiple process groups
CN103984527A (zh) * 2014-04-01 2014-08-13 杭州电子科技大学 优化稀疏矩阵向量乘提升不可压缩管流模拟效率的方法

Also Published As

Publication number Publication date
EP4160448A1 (en) 2023-04-05
JP6978467B2 (ja) 2021-12-08
TWI718604B (zh) 2021-02-11
KR20230002254A (ko) 2023-01-05
SG10201808521PA (en) 2018-11-29
KR20190054052A (ko) 2019-05-21
US20180060276A1 (en) 2018-03-01
TW202131172A (zh) 2021-08-16
US20170228341A1 (en) 2017-08-10
US9805001B2 (en) 2017-10-31
BR102016030970A8 (pt) 2018-07-31
SG10201610977QA (en) 2017-09-28
US10417303B2 (en) 2019-09-17
US10719575B2 (en) 2020-07-21
KR20170093698A (ko) 2017-08-16
US9798701B2 (en) 2017-10-24
US20220391472A1 (en) 2022-12-08
CN107045493A (zh) 2017-08-15
KR20200053461A (ko) 2020-05-18
CN112000919B (zh) 2022-04-05
EP3203382A1 (en) 2017-08-09
US11366877B2 (en) 2022-06-21
KR102635985B1 (ko) 2024-02-08
JP6524052B2 (ja) 2019-06-05
JP7187635B2 (ja) 2022-12-12
KR102112094B1 (ko) 2020-05-18
KR102483303B1 (ko) 2022-12-29
US20170228343A1 (en) 2017-08-10
KR101980365B1 (ko) 2019-05-20
JP2017138965A (ja) 2017-08-10
JP2019153333A (ja) 2019-09-12
TW201732645A (zh) 2017-09-16
TWI670613B (zh) 2019-09-01
JP7797365B2 (ja) 2026-01-13
JP2023021171A (ja) 2023-02-09
JP2022000781A (ja) 2022-01-04
TW202011226A (zh) 2020-03-16
TWI624763B (zh) 2018-05-21
CN112000919A (zh) 2020-11-27
US20200012705A1 (en) 2020-01-09
TW201826143A (zh) 2018-07-16
CN107045493B (zh) 2020-08-18
BR102016030970A2 (pt) 2018-07-17
US20210034697A1 (en) 2021-02-04

Similar Documents

Publication Publication Date Title
TWI781509B (zh) 用於將稀疏元素變換為一密集矩陣之系統及方法，以及非暫時性機器可讀儲存裝置
JP7023917B2 (ja) 疎要素を密行列に変換するためのシステムおよび方法
HK40055790B (zh) 矩阵处理装置
HK40042911B (en) Matrix processing apparatus
HK40042911A (en) Matrix processing apparatus
HK40055790A (en) Matrix processing apparatus
HK1242808B (zh) 矩阵处理装置
HK1242808A1 (en) Matrix processing apparatus
HK1242810B (zh) 矩阵处理装置
HK1242810A (en) Matrix processing apparatus
HK1242810A1 (en) Matrix processing apparatus

Legal Events

Date Code Title Description
GD4A Issue of patent certificate for granted invention patent