BR112016002637A8 - Sincronização de barreira com cálculo dinâmico de largura - Google Patents

Sincronização de barreira com cálculo dinâmico de largura

Info

Publication number
BR112016002637A8
BR112016002637A8 BR112016002637A BR112016002637A BR112016002637A8 BR 112016002637 A8 BR112016002637 A8 BR 112016002637A8 BR 112016002637 A BR112016002637 A BR 112016002637A BR 112016002637 A BR112016002637 A BR 112016002637A BR 112016002637 A8 BR112016002637 A8 BR 112016002637A8
Authority
BR
Brazil
Prior art keywords
barrier
group
subgroup
string
width
Prior art date
Application number
BR112016002637A
Other languages
English (en)
Other versions
BR112016002637B1 (pt
BR112016002637A2 (pt
Inventor
Ruben Gaster Benedict
Original Assignee
Qualcomm Inc
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 Qualcomm Inc filed Critical Qualcomm Inc
Publication of BR112016002637A2 publication Critical patent/BR112016002637A2/pt
Publication of BR112016002637A8 publication Critical patent/BR112016002637A8/pt
Publication of BR112016002637B1 publication Critical patent/BR112016002637B1/pt

Links

Classifications

    • 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
    • G06F9/46—Multiprogramming arrangements
    • G06F9/52—Program synchronisation; Mutual exclusion, e.g. by means of semaphores
    • G06F9/522—Barrier synchronisation
    • 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
    • G06F9/30076—Arrangements for executing specific machine instructions to perform miscellaneous control operations, e.g. NOP
    • G06F9/30087—Synchronisation or serialisation 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
    • G06F9/38—Concurrent instruction execution, e.g. pipeline, 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; 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]

Abstract

SINCRONIZAÇÃO DE BARREIRA COM CÁLCULO DINÂMICO DE LARGURA. Um sequenciador de uma unidade de processamento determina, durante a execução, uma largura de barreira de uma operação de barreira para um grupo de cadeias, sendo que a largura da barreira é menor do que um número total de cadeias no grupo de cadeias, e sendo que as cadeias no grupo de cadeias executam o código de dados paralelos um uma ou mais unidades de computação. Em resposta à cada cadeia em um subgrupo do grupo de cadeias que executou a operação de barreira, o subgrupo incluindo um mesmo número de cadeias que a largura da barreira, o sequenciador pode permitir que o subgrupo do grupo de cadeias execute nos um ou mais processadores depois da operação de barreira sem esperar por outras cadeias no grupo de cadeias executarem a operação de barreira, sendo que o subgrupo do grupo de cadeias é menor que o número total de cadeias no grupo de cadeias.
BR112016002637-3A 2013-08-13 2014-08-07 Método e sistema de computação para sincronizar threads em um grupo de threads, e memória legível por computador BR112016002637B1 (pt)

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US13/965,818 US9218223B2 (en) 2013-08-13 2013-08-13 Barrier synchronization with dynamic width calculation
US13/965,818 2013-08-13
PCT/US2014/050143 WO2015023509A1 (en) 2013-08-13 2014-08-07 Barrier synchronization with dynamic width calculation

Publications (3)

Publication Number Publication Date
BR112016002637A2 BR112016002637A2 (pt) 2017-08-01
BR112016002637A8 true BR112016002637A8 (pt) 2022-08-23
BR112016002637B1 BR112016002637B1 (pt) 2023-03-14

Family

ID=51422147

Family Applications (1)

Application Number Title Priority Date Filing Date
BR112016002637-3A BR112016002637B1 (pt) 2013-08-13 2014-08-07 Método e sistema de computação para sincronizar threads em um grupo de threads, e memória legível por computador

Country Status (8)

Country Link
US (1) US9218223B2 (pt)
EP (2) EP3964951A1 (pt)
JP (1) JP6130065B2 (pt)
KR (1) KR101724247B1 (pt)
CN (1) CN105453045B (pt)
BR (1) BR112016002637B1 (pt)
CA (1) CA2917609C (pt)
WO (1) WO2015023509A1 (pt)

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9916162B2 (en) * 2013-12-26 2018-03-13 Intel Corporation Using a global barrier to synchronize across local thread groups in general purpose programming on GPU
DE102016203965A1 (de) * 2016-03-10 2017-09-14 Robert Bosch Gmbh Überwachung eines Rechensystems
US10324730B2 (en) * 2016-03-24 2019-06-18 Mediatek, Inc. Memory shuffle engine for efficient work execution in a parallel computing system
US10223436B2 (en) * 2016-04-27 2019-03-05 Qualcomm Incorporated Inter-subgroup data sharing
US20170357705A1 (en) * 2016-06-08 2017-12-14 Knuedge Incorporated Performing a synchronization operation on an electronic device
US10318355B2 (en) * 2017-01-24 2019-06-11 Oracle International Corporation Distributed graph processing system featuring interactive remote control mechanism including task cancellation
US11353868B2 (en) * 2017-04-24 2022-06-07 Intel Corporation Barriers and synchronization for machine learning at autonomous machines
US10990453B2 (en) * 2018-04-12 2021-04-27 Advanced Micro Devices, Inc. Improving latency by performing early synchronization operations in between sets of program operations of a thread
GB2574817B (en) * 2018-06-18 2021-01-06 Advanced Risc Mach Ltd Data processing systems
JP7159696B2 (ja) * 2018-08-28 2022-10-25 富士通株式会社 情報処理装置，並列計算機システムおよび制御方法
US11449339B2 (en) * 2019-09-27 2022-09-20 Red Hat, Inc. Memory barrier elision for multi-threaded workloads
US11409579B2 (en) * 2020-02-24 2022-08-09 Intel Corporation Multiple independent synchonization named barrier within a thread group
KR102501187B1 (ko) * 2020-04-03 2023-02-17 서울대학교산학협력단 배리어 구현 방법 및 시스템
US11461130B2 (en) 2020-05-26 2022-10-04 Oracle International Corporation Methodology for fast and seamless task cancelation and error handling in distributed processing of large graph data
US11204774B1 (en) * 2020-08-31 2021-12-21 Apple Inc. Thread-group-scoped gate instruction
GB2604150B (en) * 2021-02-26 2023-06-14 Advanced Risc Mach Ltd Data processing systems
US20220342721A1 (en) * 2021-04-22 2022-10-27 EMC IP Holding Company, LLC System and Method for Efficient Snapshots Barrier Mechanism for System With Presorted Container-Based Log

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6574725B1 (en) 1999-11-01 2003-06-03 Advanced Micro Devices, Inc. Method and mechanism for speculatively executing threads of instructions
JP3571976B2 (ja) 1999-11-08 2004-09-29 富士通株式会社 デバッグ装置及び方法並びにプログラム記録媒体
US7512950B1 (en) 2003-08-14 2009-03-31 Sun Microsystems, Inc. Barrier synchronization object for multi-threaded applications
JP4276028B2 (ja) * 2003-08-25 2009-06-10 株式会社日立製作所 マルチプロセッサシステムの同期方法
US7937709B2 (en) * 2004-12-29 2011-05-03 Intel Corporation Synchronizing multiple threads efficiently
US7865911B2 (en) * 2005-11-08 2011-01-04 Microsoft Corporation Hybrid programming
US7555607B2 (en) 2005-11-10 2009-06-30 Hewlett-Packard Development Company, L.P. Program thread syncronization for instruction cachelines
US8484516B2 (en) * 2007-04-11 2013-07-09 Qualcomm Incorporated Inter-thread trace alignment method and system for a multi-threaded processor
US8966488B2 (en) 2007-07-06 2015-02-24 XMOS Ltd. Synchronising groups of threads with dedicated hardware logic
US8866827B2 (en) * 2008-06-26 2014-10-21 Microsoft Corporation Bulk-synchronous graphics processing unit programming
JP5239751B2 (ja) * 2008-10-31 2013-07-17 富士通株式会社 ノード間同期装置、ノード間同期方法およびノード間同期プログラム
JP5447807B2 (ja) * 2009-08-07 2014-03-19 株式会社日立製作所 バリア同期方法及び計算機
US8539204B2 (en) 2009-09-25 2013-09-17 Nvidia Corporation Cooperative thread array reduction and scan operations

Also Published As

Publication number Publication date
CA2917609C (en) 2017-10-24
EP3033679A1 (en) 2016-06-22
CN105453045B (zh) 2017-04-12
BR112016002637B1 (pt) 2023-03-14
US20150052537A1 (en) 2015-02-19
WO2015023509A1 (en) 2015-02-19
CN105453045A (zh) 2016-03-30
US9218223B2 (en) 2015-12-22
KR20160036067A (ko) 2016-04-01
EP3964951A1 (en) 2022-03-09
CA2917609A1 (en) 2015-02-19
JP2016525746A (ja) 2016-08-25
BR112016002637A2 (pt) 2017-08-01
JP6130065B2 (ja) 2017-05-17
KR101724247B1 (ko) 2017-04-06

Similar Documents

Publication Publication Date Title
BR112016002637A8 (pt) Sincronização de barreira com cálculo dinâmico de largura
BR112018004933A2 (pt) agendamento eficaz de tarefas multiversionadas
BR112017026917A2 (pt) ?método e dispositivo para processamento de rede neural convolucional cnn e mídia de armazenamento não volátil?
BR112018002040A2 (pt) controle de uma nuvem de dispositivo
BR112017010388A2 (pt) escala dos agentes de assistente pessoal digital por meio de dispositivos
BR112015015230A8 (pt) Sistema e processo para abordar generalização em uma rede neural
BR112018007430A2 (pt) aceleração de subgráficos de tarefa pela sincronização de remapeamento
BR112015025695A2 (pt) pré-geração de objeto de exibição
BR112016021216A2 (pt) instrução de fim de transação condicional
BR112017021986A2 (pt) sistema e método para extrair e compartilhar dados de usuário relacionados com aplicativo
BR112017024351A2 (pt) arquitetura baseada em bloco com execução paralela de blocos sucessivos
BR112014019336A2 (pt) ambiente e método para o desenvolvimento multi-plataforma de aplicações de software
BR112015030066A2 (pt) processadores, métodos e sistemas para acessar um conjunto de registradores como uma pluralidade de registradores menores ou como um registrador maior combinado
BR112017002636A2 (pt) compartilhamento equitativo de recursos de sistema em execução de fluxo de trabalho
BR112013030585A2 (pt) monitoramento de saída de área demarcada
BR112012007445A2 (pt) dados de treinamento de face compartilhados
BR112016007119A2 (pt) domínios de falha em hardware moderno
BR112014021507A2 (pt) Método e aparelho para compartilhar informação, e dispositivo de computador
BR112017004028A2 (pt) sistema criptográfico, primeiro dispositivo de rede configurado para determinar uma chave compartilhada com qualquer um dentre múltiplos dispositivos de rede, método de compartilhamento para determinar uma chave compartilhada com qualquer um dentre múltiplos dispositivos de rede, e programa de computador
BR112015020394A2 (pt) método para segurança de um primeiro programa, e, produto de software de computador
BR112014026626A8 (pt) criação de grupos de rede social
BR112016007137A8 (pt) sistema, meio de armazenamento e método para otimizar transferência de dados em plataformas de computação em nuvem
BR112015013917A2 (pt) método, unidade de computação, e sistema
BR112018001970A2 (pt) mecanismo de regras para dispositivos conectados
BR112018074025A2 (pt) otimizador de consulta para utilização de cpu e reformador de código

Legal Events

Date Code Title Description
B06U Preliminary requirement: requests with searches performed by other patent offices: procedure suspended [chapter 6.21 patent gazette]
B15K Others concerning applications: alteration of classification

Free format text: A CLASSIFICACAO ANTERIOR ERA: G06F 9/52

Ipc: G06F 9/52 (2006.01), G06F 9/38 (2006.01), G06F 9/3

B06A Patent application procedure suspended [chapter 6.1 patent gazette]
B09A Decision: intention to grant [chapter 9.1 patent gazette]
B16A Patent or certificate of addition of invention granted [chapter 16.1 patent gazette]

Free format text: PRAZO DE VALIDADE: 20 (VINTE) ANOS CONTADOS A PARTIR DE 07/08/2014, OBSERVADAS AS CONDICOES LEGAIS