CN116113940A - 一种图计算装置、处理方法及相关设备 - Google Patents

一种图计算装置、处理方法及相关设备 Download PDF

Info

Publication number
CN116113940A
CN116113940A CN202080104160.4A CN202080104160A CN116113940A CN 116113940 A CN116113940 A CN 116113940A CN 202080104160 A CN202080104160 A CN 202080104160A CN 116113940 A CN116113940 A CN 116113940A
Authority
CN
China
Prior art keywords
graph
calculation
iterative
computation
instruction
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.)
Pending
Application number
CN202080104160.4A
Other languages
English (en)
Other versions
CN116113940A8 (zh
Inventor
周若愚
朱凡
孙文博
周昔平
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.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies Co Ltd
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 Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Publication of CN116113940A publication Critical patent/CN116113940A/zh
Publication of CN116113940A8 publication Critical patent/CN116113940A8/zh
Pending legal-status Critical Current

Links

Images

Classifications

    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/90Details of database functions independent of the retrieved data types
    • G06F16/901Indexing; Data structures therefor; Storage structures
    • G06F16/9024Graphs; Linked lists
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/50Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5027Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
    • G06F9/5044Allocation 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
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/30003Arrangements for executing specific machine instructions
    • G06F9/3005Arrangements for executing specific machine instructions to perform operations for flow control
    • G06F9/30065Loop control instructions; iterative instructions, e.g. LOOP, REPEAT
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/30003Arrangements for executing specific machine instructions
    • G06F9/30076Arrangements for executing specific machine instructions to perform miscellaneous control operations, e.g. NOP
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/30Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/38Concurrent instruction execution, e.g. pipeline or look ahead
    • G06F9/3836Instruction issuing, e.g. dynamic instruction scheduling or out of order instruction execution

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Software Systems (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Databases & Information Systems (AREA)
  • Data Mining & Analysis (AREA)
  • Advance Control (AREA)
  • Combined Controls Of Internal Combustion Engines (AREA)
  • Executing Machine-Instructions (AREA)

Abstract

一种图计算装置(11)、处理方法及相关设备,其中的图计算装置(11)包括至少一个处理引擎PE(101),至少一个处理引擎PE(101)中的每一个处理引擎PE(101)包括M个状态缓冲区(1011‑1、1011‑2、……、1011‑M)、仲裁逻辑单元(1012)和X个运算单元(1013‑1、1013‑2、……、1013‑X);其中,M个状态缓冲区(1011‑1、1011‑2、……、1011‑M)中的每个状态缓冲区(1011),用于存储一次迭代计算任务的状态数据;仲裁逻辑单元(1012),用于基于M个状态缓冲区(1011‑1、1011‑2、……、1011‑M)中的状态数据,确定当前时钟周期待执行的L条图计算指令,并将L条图计算指令分配至X个运算单元(1013‑1、1013‑2、……、1013‑X);X个运算单元(1013‑1、1013‑2、……、1013‑X)中的每个运算单元(1013),用于执行仲裁逻辑单元(1012)分配的图计算指令。该图计算装置(11)可以提升处理器(10)的性能。

Description

PCT国内申请,说明书已公开。

Claims (22)

  1. PCT国内申请,权利要求书已公开。
CN202080104160.4A 2020-08-21 2020-08-21 一种图计算装置、处理方法及相关设备 Pending CN116113940A (zh)

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/110517 WO2022036690A1 (zh) 2020-08-21 2020-08-21 一种图计算装置、处理方法及相关设备

Publications (2)

Publication Number Publication Date
CN116113940A true CN116113940A (zh) 2023-05-12
CN116113940A8 CN116113940A8 (zh) 2024-05-21

Family

ID=80350293

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202080104160.4A Pending CN116113940A (zh) 2020-08-21 2020-08-21 一种图计算装置、处理方法及相关设备

Country Status (4)

Country Link
US (1) US20230195526A1 (zh)
EP (1) EP4191441A4 (zh)
CN (1) CN116113940A (zh)
WO (1) WO2022036690A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115934031B (zh) * 2023-03-15 2023-09-01 紫光同芯微电子有限公司 一种计算引擎、数据处理方法、设备及存储介质

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102810087B (zh) * 2011-05-30 2017-04-12 中兴通讯股份有限公司 一种傅立叶变换的实现装置
CN104823380A (zh) * 2012-12-14 2015-08-05 诺基亚技术有限公司 用于解码的方法和装置
US20160232006A1 (en) * 2015-02-09 2016-08-11 Qualcomm Incorporated Fan out of result of explicit data graph execution instruction
CN108132838B (zh) * 2016-11-30 2021-12-14 华为技术有限公司 一种图数据处理的方法、装置及系统
CN108287759B (zh) * 2017-01-10 2021-07-09 阿里巴巴集团控股有限公司 处理数据过程中的调度方法、装置和系统
CN111433758B (zh) * 2018-11-21 2024-04-02 吴国盛 可编程运算与控制芯片、设计方法及其装置
CN110232087B (zh) * 2019-05-30 2021-08-17 湖南大学 大数据增量迭代方法、装置、计算机设备和存储介质

Also Published As

Publication number Publication date
EP4191441A1 (en) 2023-06-07
WO2022036690A1 (zh) 2022-02-24
US20230195526A1 (en) 2023-06-22
EP4191441A4 (en) 2023-08-23
CN116113940A8 (zh) 2024-05-21

Similar Documents

Publication Publication Date Title
US5710902A (en) Instruction dependency chain indentifier
US20210406027A1 (en) Advanced processor architecture
Rau et al. Some scheduling techniques and an easily schedulable horizontal architecture for high performance scientific computing
KR100464406B1 (ko) 가변길이 vliw 명령어를 위한 디스패치 장치 및 방법
CN106104481B (zh) 用于执行确定性和机会性多线程的系统和方法
US7117345B2 (en) Non-stalling circular counterflow pipeline processor with reorder buffer
JP2928695B2 (ja) 静的インタリーブを用いたマルチスレッドマイクロプロセッサおよびそれを備えたシステムでの命令スレッド実行方法
KR100284789B1 (ko) N-지로 분기를 갖는 슈퍼스칼라 또는 초장 명령어 워드컴퓨터에서 다음 명령어를 선택하는 방법 및 장치
US5604878A (en) Method and apparatus for avoiding writeback conflicts between execution units sharing a common writeback path
US20160291982A1 (en) Parallelized execution of instruction sequences based on pre-monitoring
EP1134654A1 (en) Program product and data processor
US20170083335A1 (en) Broadcast channel architectures for block-based processors
CN101373427A (zh) 程序执行控制装置
KR20180021812A (ko) 연속하는 블록을 병렬 실행하는 블록 기반의 아키텍쳐
CN113326066B (zh) 量子控制微体系结构、量子控制处理器及指令执行方法
US20220214884A1 (en) Issuing instructions based on resource conflict constraints in microprocessor
US20230093393A1 (en) Processor, processing method, and related device
US20230195526A1 (en) Graph computing apparatus, processing method, and related device
EP3278212A1 (en) Parallelized execution of instruction sequences based on premonitoring
JP6349088B2 (ja) パイプラインでブロックをスケジュールするコンパイル方法及び装置
WO2021253359A1 (zh) 一种图指令处理方法及装置
JP3512707B2 (ja) マイクロコンピュータ
Kol Self-timed asynchronous architecture of an advanced general purpose microprocessor
CN118245187A (zh) 线程调度方法及装置、电子设备及存储介质
JP3743155B2 (ja) パイプライン制御型計算機

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
CI02 Correction of invention patent application
CI02 Correction of invention patent application

Correction item: PCT international application to national stage day

Correct: 2023.02.13

False: 2023.02.07

Number: 19-02

Page: The title page

Volume: 39

Correction item: PCT international application to national stage day

Correct: 2023.02.13

False: 2023.02.07

Number: 19-02

Volume: 39