Pang et al., 2023 - Google Patents

Efficient CUDA stream management for multi-DNN real-time inference on embedded GPUs

Pang et al., 2023

Document ID
728451386753944524
Author
Pang W
Luo X
Chen K
Ji D
Qiao L
Yi W
Publication year
Publication venue
Journal of Systems Architecture

External Links

Snippet

Abstract Deep Neural Networks (DNNs) are widely used in Cyber–Physical Systems (CPS) that often involve multiple DNN tasks with varying real-time requirements. These tasks need to be deployed on a single embedded hardware platform with limited resources, such as an …
Continue reading at www.sciencedirect.com (other versions)

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for programme control, e.g. control unit
    • G06F9/06—Arrangements for programme control, e.g. control unit using stored programme, i.e. using internal store of processing equipment to receive and retain programme
    • G06F9/46—Multiprogramming arrangements
    • G06F9/48—Programme initiating; Programme switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
    • G06F9/4887—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues involving deadlines, e.g. rate based, periodic
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for programme control, e.g. control unit
    • G06F9/06—Arrangements for programme control, e.g. control unit using stored programme, i.e. using internal store of processing equipment to receive and retain programme
    • G06F9/46—Multiprogramming arrangements
    • G06F9/48—Programme initiating; Programme switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G06F9/485—Task life-cycle, e.g. stopping, restarting, resuming execution
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for programme control, e.g. control unit
    • G06F9/06—Arrangements for programme control, e.g. control unit using stored programme, i.e. using internal store of processing equipment to receive and retain programme
    • 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
    • G06F9/505—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 the load
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for programme control, e.g. control unit
    • G06F9/06—Arrangements for programme control, e.g. control unit using stored programme, i.e. using internal store of processing equipment to receive and retain programme
    • 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
    • G06F9/5038—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 the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for programme control, e.g. control unit
    • G06F9/06—Arrangements for programme control, e.g. control unit using stored programme, i.e. using internal store of processing equipment to receive and retain programme
    • 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
    • G06F9/5011—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for programme control, e.g. control unit
    • G06F9/06—Arrangements for programme control, e.g. control unit using stored programme, i.e. using internal store of processing equipment to receive and retain programme
    • 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; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for programme control, e.g. control unit
    • G06F9/06—Arrangements for programme control, e.g. control unit using stored programme, i.e. using internal store of processing equipment to receive and retain programme
    • G06F9/46—Multiprogramming arrangements
    • G06F9/52—Programme synchronisation; Mutual exclusion, e.g. by means of semaphores; Contention for resources among tasks
    • G06F9/524—Deadlock detection or avoidance
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for programme control, e.g. control unit
    • G06F9/06—Arrangements for programme control, e.g. control unit using stored programme, i.e. using internal store of processing equipment to receive and retain programme
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5083—Techniques for rebalancing the load in a distributed system
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for programme control, e.g. control unit
    • G06F9/06—Arrangements for programme control, e.g. control unit using stored programme, i.e. using internal store of processing equipment to receive and retain programme
    • 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, out of order instruction execution
    • G06F9/3851—Instruction issuing, e.g. dynamic instruction scheduling, out of order instruction execution from multiple instruction streams, e.g. multistreaming
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for programme control, e.g. control unit
    • G06F9/06—Arrangements for programme control, e.g. control unit using stored programme, i.e. using internal store of processing equipment to receive and retain programme
    • G06F9/46—Multiprogramming arrangements
    • G06F9/54—Interprogramme communication; Intertask communication
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for programme control, e.g. control unit
    • G06F9/06—Arrangements for programme control, e.g. control unit using stored programme, i.e. using internal store of processing equipment to receive and retain programme
    • G06F9/44—Arrangements for executing specific programmes
    • G06F9/455—Emulation; Software simulation, i.e. virtualisation or emulation of application or operating system execution engines
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F15/00—Digital computers in general; Data processing equipment in general
    • G06F15/16—Combinations of two or more digital computers each having at least an arithmetic unit, a programme unit and a register, e.g. for a simultaneous processing of several programmes
    • G06F15/163—Interprocessor communication
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F2209/00—Indexing scheme relating to G06F9/00
    • G06F2209/50—Indexing scheme relating to G06F9/50
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F15/00—Digital computers in general; Data processing equipment in general
    • G06F15/76—Architectures of general purpose stored programme computers
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
    • G06F13/14—Handling requests for interconnection or transfer
    • G06F13/36—Handling requests for interconnection or transfer for access to common bus or bus system
    • G06F13/368—Handling requests for interconnection or transfer for access to common bus or bus system with decentralised access control
    • G06F13/372—Handling requests for interconnection or transfer for access to common bus or bus system with decentralised access control using a time-dependent priority, e.g. individually loaded time counters or time slot
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06F—ELECTRICAL DIGITAL DATA PROCESSING
    • G06F13/00—Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
    • G06F13/14—Handling requests for interconnection or transfer
    • G06F13/16—Handling requests for interconnection or transfer for access to memory bus
    • G06F13/1605—Handling requests for interconnection or transfer for access to memory bus based on arbitration
    • G06F13/1642—Handling requests for interconnection or transfer for access to memory bus based on arbitration with request queuing

Similar Documents

Publication Publication Date Title
Bai et al. {PipeSwitch}: Fast pipelined context switching for deep learning applications
Kang et al. Lalarand: Flexible layer-by-layer cpu/gpu scheduling for real-time dnn tasks
US9009711B2 (en) Grouping and parallel execution of tasks based on functional dependencies and immediate transmission of data results upon availability
Verner et al. Processing data streams with hard real-time constraints on heterogeneous systems
Pang et al. Efficient CUDA stream management for multi-DNN real-time inference on embedded GPUs
Hartmann et al. Gpuart-an application-based limited preemptive gpu real-time scheduler for embedded systems
Yu et al. Smguard: A flexible and fine-grained resource management framework for gpus
Yeh et al. Deadline-aware offloading for high-throughput accelerators
Zhou et al. Task mapping in heterogeneous embedded systems for fast completion time
Goswami et al. GPUShare: Fair-sharing middleware for GPU clouds
Wu et al. Switchflow: preemptive multitasking for deep learning
Yang et al. PK-OMLP: An OMLP based k-exclusion real-time locking protocol for multi-GPU sharing under partitioned scheduling
Elliott et al. Gpusync: Architecture-aware management of gpus for predictable multi-gpu real-time systems
Shih et al. Fairness scheduler for virtual machines on heterogonous multi-core platforms
Biondi et al. Moving from single-core to multicore: Initial findings on a fuel injection case study
Tran et al. Efficient contention-aware scheduling of SDF graphs on shared multi-bank memory
Kerbl et al. Hierarchical Bucket Queuing for Fine‐Grained Priority Scheduling on the GPU
Kumar et al. Global analysis of resource arbitration for MPSoC
Singh Toward predictable execution of real-time workloads on modern GPUs
Gai et al. Stack size minimization for embedded real-time systems-on-a-chip
Ali Deterministic Scheduling of Real-Time Tasks on Heterogeneous Multicore Platforms
Alfranseder Efficient and robust dynamic scheduling and synchronization in practical embedded real-time multiprocessor systems
Alhammad Memory Efficient Scheduling for Multicore Real-time Systems
Saraswat et al. Design and implementation of a process scheduler simulator and an improved process scheduling algorithm for multimedia operating systems
Erciyes et al. Real-Time Operating Systems