CN108241508B - 处理OpenCL内核的方法及用于该方法的计算设备 - Google Patents

处理OpenCL内核的方法及用于该方法的计算设备 Download PDF

Info

Publication number
CN108241508B
CN108241508B CN201711216401.0A CN201711216401A CN108241508B CN 108241508 B CN108241508 B CN 108241508B CN 201711216401 A CN201711216401 A CN 201711216401A CN 108241508 B CN108241508 B CN 108241508B
Authority
CN
China
Prior art keywords
core
processing
group
cores
control
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
CN201711216401.0A
Other languages
English (en)
Chinese (zh)
Other versions
CN108241508A (zh
Inventor
伯恩哈德·爱格
乌洙林
赵永显
刘东勋
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.)
Samsung Electronics Co Ltd
SNU R&DB Foundation
Original Assignee
Samsung Electronics Co Ltd
SNU R&DB Foundation
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 Samsung Electronics Co Ltd, SNU R&DB Foundation filed Critical Samsung Electronics Co Ltd
Publication of CN108241508A publication Critical patent/CN108241508A/zh
Application granted granted Critical
Publication of CN108241508B publication Critical patent/CN108241508B/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
    • 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 or look ahead
    • G06F9/3836—Instruction issuing, e.g. dynamic instruction scheduling or out of order instruction execution
    • G06F9/3851—Instruction issuing, e.g. dynamic instruction scheduling or out of order instruction execution from multiple instruction streams, e.g. multistreaming
    • 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
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • G06F9/5044—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering hardware capabilities
    • 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
    • G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • 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
    • G06F9/38—Concurrent instruction execution, e.g. pipeline or look ahead
    • G06F9/3885—Concurrent instruction execution, e.g. pipeline or look ahead using a plurality of independent parallel functional units
    • G06F9/3887—Concurrent instruction execution, e.g. pipeline or look ahead using a plurality of independent parallel functional units controlled by a single instruction for multiple data lanes [SIMD]
    • 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]
    • G06F9/5061—Partitioning or combining of resources
    • G06F9/5066—Algorithms for mapping a plurality of inter-dependent sub-tasks onto a plurality of physical CPUs
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T1/00—General purpose image data processing
    • G06T1/20—Processor architectures; Processor configuration, e.g. pipelining

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Stored Programmes (AREA)
  • Memory System Of A Hierarchy Structure (AREA)
CN201711216401.0A 2016-12-27 2017-11-28 处理OpenCL内核的方法及用于该方法的计算设备 Active CN108241508B (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR10-2016-0180133 2016-12-27
KR1020160180133A KR102592330B1 (ko) 2016-12-27 2016-12-27 OpenＣＬ 커널을 처리하는 방법과 이를 수행하는 컴퓨팅 장치

Publications (2)

Publication Number Publication Date
CN108241508A CN108241508A (zh) 2018-07-03
CN108241508B true CN108241508B (zh) 2023-06-13

Family

ID=60473303

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201711216401.0A Active CN108241508B (zh) 2016-12-27 2017-11-28 处理OpenCL内核的方法及用于该方法的计算设备

Country Status (5)

Country Link
US (1) US10503557B2 (https=)
EP (1) EP3343370A1 (https=)
JP (1) JP6951962B2 (https=)
KR (1) KR102592330B1 (https=)
CN (1) CN108241508B (https=)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111490946B (zh) * 2019-01-28 2023-08-11 阿里巴巴集团控股有限公司 基于OpenCL框架的FPGA连接实现方法及装置
KR20240136005A (ko) 2023-03-06 2024-09-13 한국전자통신연구원 병렬연산작업 오프로딩 장치 및 방법

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102099788A (zh) * 2008-06-06 2011-06-15 苹果公司 用于在多处理器上进行数据并行计算的应用编程接口
CN103608777A (zh) * 2011-06-20 2014-02-26 高通股份有限公司 图形处理单元中的存储器共享
CN104011679A (zh) * 2011-12-01 2014-08-27 超威半导体公司 异构并行处理平台的软件库
CN104834630A (zh) * 2014-02-10 2015-08-12 瑞萨电子株式会社 运算控制装置、运算控制方法、存储有程序的非瞬时计算机可读介质以及OpenCL设备

Family Cites Families (19)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS595755B2 (ja) 1977-08-02 1984-02-07 日本軽金属株式会社 太陽熱利用暖房方法
US7418470B2 (en) * 2000-06-26 2008-08-26 Massively Parallel Technologies, Inc. Parallel processing systems and method
US7673011B2 (en) 2007-08-10 2010-03-02 International Business Machines Corporation Configuring compute nodes of a parallel computer in an operational group into a plurality of independent non-overlapping collective networks
US8255345B2 (en) 2009-05-15 2012-08-28 The Aerospace Corporation Systems and methods for parallel processing with infeasibility checking mechanism
US9354944B2 (en) * 2009-07-27 2016-05-31 Advanced Micro Devices, Inc. Mapping processing logic having data-parallel threads across processors
WO2011027382A1 (en) 2009-09-01 2011-03-10 Hitachi, Ltd. Request processing system provided with multi-core processor
KR101640848B1 (ko) 2009-12-28 2016-07-29 삼성전자주식회사 멀티코어 시스템 상에서 단위 작업을 할당하는 방법 및 그 장치
KR101613971B1 (ko) 2009-12-30 2016-04-21 삼성전자주식회사 프로그램 코드의 변환 방법
JP2012094072A (ja) 2010-10-28 2012-05-17 Toyota Motor Corp 情報処理装置
US8683243B2 (en) * 2011-03-11 2014-03-25 Intel Corporation Dynamic core selection for heterogeneous multi-core systems
WO2012157786A1 (ja) * 2011-05-19 2012-11-22 日本電気株式会社 並列処理装置、並列処理方法、最適化装置、最適化方法、および、コンピュータ・プログラム
US20120331278A1 (en) 2011-06-23 2012-12-27 Mauricio Breternitz Branch removal by data shuffling
JP5238876B2 (ja) * 2011-12-27 2013-07-17 株式会社東芝 情報処理装置及び情報処理方法
KR101284195B1 (ko) * 2012-01-09 2013-07-10 서울대학교산학협력단 개방형 범용 병렬 컴퓨팅 프레임워크 동적 작업 분배 장치
KR20130093995A (ko) 2012-02-15 2013-08-23 한국전자통신연구원 계층적 멀티코어 프로세서의 성능 최적화 방법 및 이를 수행하는 멀티코어 프로세서 시스템
KR20140125893A (ko) 2013-01-28 2014-10-30 한국과학기술원 가상화된 매니코어 서버의 작업분배 시스템과 그 방법 및 기록매체
KR102062208B1 (ko) * 2013-05-03 2020-02-11 삼성전자주식회사 멀티스레드 프로그램 코드의 변환 장치 및 방법
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
US10318261B2 (en) * 2014-11-24 2019-06-11 Mentor Graphics Corporation Execution of complex recursive algorithms

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102099788A (zh) * 2008-06-06 2011-06-15 苹果公司 用于在多处理器上进行数据并行计算的应用编程接口
CN103608777A (zh) * 2011-06-20 2014-02-26 高通股份有限公司 图形处理单元中的存储器共享
CN104011679A (zh) * 2011-12-01 2014-08-27 超威半导体公司 异构并行处理平台的软件库
CN104834630A (zh) * 2014-02-10 2015-08-12 瑞萨电子株式会社 运算控制装置、运算控制方法、存储有程序的非瞬时计算机可读介质以及OpenCL设备

Also Published As

Publication number Publication date
KR20180076051A (ko) 2018-07-05
JP6951962B2 (ja) 2021-10-20
EP3343370A1 (en) 2018-07-04
JP2018106709A (ja) 2018-07-05
US20180181443A1 (en) 2018-06-28
US10503557B2 (en) 2019-12-10
KR102592330B1 (ko) 2023-10-20
CN108241508A (zh) 2018-07-03

Similar Documents

Publication Publication Date Title
US11847507B1 (en) DMA synchronization using alternating semaphores
CN111247533B (zh) 用于神经网络加速的机器学习运行时库
US20230297425A1 (en) Allocation of memory resources to simd workgroups
US9483319B2 (en) Job scheduling apparatus and method therefor
US9069610B2 (en) Compute cluster with balanced resources
CN102576314B (zh) 具有横跨多个处理器的数据并行线程之映射处理逻辑
TW201519091A (zh) 用於任務排程之電腦系統，方法及電腦可讀取記錄媒體
KR20110075297A (ko) 병렬도를 고려한 병렬 처리 장치 및 방법
US20150227586A1 (en) Methods and Systems for Dynamically Allocating Resources and Tasks Among Database Work Agents in an SMP Environment
JP2020119564A (ja) 多重経路ニューラルネットワーク及びそのレイヤにリソースを割り当てる方法並びに多重経路ニューラルネットワークアナライザ
KR102338849B1 (ko) 실시간 운영 체제에서 스택 메모리 관리를 제공하는 방법 및 시스템
KR102247249B1 (ko) 데이터베이스 관리 시스템에서 비동기적 데이터 처리를 위한 컴퓨터 프로그램
CN110825502A (zh) 神经网络处理器和用于神经网络处理器的任务调度方法
US9710381B2 (en) Method and apparatus for cache memory data processing
CN108241508B (zh) 处理OpenCL内核的方法及用于该方法的计算设备
KR20190057558A (ko) 멀티 코어 제어 시스템
GB2572248A (en) Resource allocation
KR101755154B1 (ko) 이종 연산 처리 장치에 대한 동적 작업 할당 방법 및 장치
CN116775246A (zh) 任务的分配方法、装置及电子设备
CN116010093A (zh) 数据处理方法、装置、计算机设备和可读存储介质
CN118575190A (zh) 用于工作组分布的动态分派
JP6445876B2 (ja) リソース割当装置、リソース割当システム、および、リソース割当方法
KR20250103201A (ko) 다중 pe pim 아키텍처에서의 자원 관리 장치 및 방법
CN121900898A (zh) 任务执行方法、图形处理器、设备、介质及产品
CN121879960A (zh) 资源分配方法及系统

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