• Corpus ID: 18344830

TimeGraph: GPU Scheduling for Real-Time Multi-Tasking Environments

@inproceedings{Kato2011TimeGraphGS,
  title={TimeGraph: GPU Scheduling for Real-Time Multi-Tasking Environments},
  author={Shinpei Kato and Karthik Lakshmanan and Ragunathan Raj Rajkumar and Yutaka Ishikawa},
  booktitle={USENIX Annual Technical Conference},
  year={2011}
}
The Graphics Processing Unit (GPU) is now commonly used for graphics and data-parallel computing. As more and more applications tend to accelerate on the GPU in multi-tasking environments where multiple tasks access the GPU concurrently, operating systems must provide prioritization and isolation capabilities in GPU resource management, particularly in real-time setups. We present TimeGraph, a real-time GPU scheduler at the device-driver level for protecting important GPU workloads from… 
STGM: Spatio-Temporal GPU Management for Real-Time Tasks
  • S. Saha, Yecheng Xiang, Hyoseung Kim
  • Computer Science
    2019 IEEE 25th International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA)
  • 2019
TLDR
A spatial-temporal GPU management framework that controls the allocation and sharing of GPU's internal execution engines, e.g., streaming multiprocessors in Nvidia architectures, with analytical bounds that improves temporal isolation and improves schedulability compared to the existing real-time GPU management approaches.
A memory-driven scheduling scheme and optimization for concurrent execution in GPU
TLDR
A reservation algorithm based on device memory (RBDM) is adopted to provide more opportunity for the High-priority task in the real-time GPU scheduling scheme and high priority first wake and small memory HPFW are employed in the scheduling of waiting tasks to improve the priority response time and system performance.
RTGPU: Real-Time GPU Scheduling of Hard Deadline Parallel Tasks with Fine-Grain Utilization
TLDR
The RTGPU approach provides superior schedulability compared with previous work, and gives real-time guarantees to meet hard deadlines for multiple GPU applications according to comprehensive validation and evaluation on a real NVIDIA GTX1080Ti GPU system.
CUsched: multiprogrammed workload scheduling on GPU architectures
TLDR
This paper proposes a set of hardware extensions to the current GPU architectures to efficiently support multi-programmed GPU workloads, allowing concurrent execution of codes from different user processes.
GPUSync: A Framework for Real-Time GPU Management
TLDR
GPUSync is described, which is a framework for managing graphics processing units (GPUs) in multi-GPU multicore real-time systems and provides budget policing to the extent possible, given that GPU access is non-preemptive.
Loadable Real-Time Extension for CPU / GPU Resource Coordination
TLDR
Experimental results indicate that the proposed kernel modification free Linux-RTXG framework achieves, GPU scheduling overhead and quality of service management performance comparable to existing kernel-dependent approaches.
Run-Time Scheduling Framework for Event-Driven Applications on a GPU-Based Embedded System
TLDR
This work proposes a novel run-time scheduling framework that considers both temporal and spatial preemptions concurrently in a GPU and demonstrates the capability and novelty of the framework compared to the existing scheduling frameworks with realistic benchmark applications and with different execution scenarios.
Dynamic schedule management framework for aperiodic soft-real-time jobs on GPU based architectures
TLDR
A schedule management framework for aperiodic soft-real-time jobs that may be used by a CPU GPU system designer/integrator to select, conFigure and deploy a suitable architectural platform and to perform concurrent scheduling of these jobs.
Multitasking Real-time Embedded GPU Computing Tasks
TLDR
This study highlights the shortcomings of current GPU architectures with regard to running multiple real-time tasks, and recommends new features that would improve scheduling, including hardware priorities, preemption, programmable scheduling, and a common time concept and atomics across the CPU and GPU.
...
...

References

SHOWING 1-10 OF 35 REFERENCES
CPU reservations and time constraints: efficient, predictable scheduling of independent activities
TLDR
This paper presents a system that can schedule multiple independent activities so that they can obtain minimum guaranteed execution rates with application-specified reservation granularities via CPU Reservations.
GViM: GPU-accelerated virtual machines
TLDR
GViM is presented, a system designed for virtualizing and managing the resources of a general purpose system accelerated by graphics processors and how such accelerators can be virtualized without additional hardware support.
Fair and timely scheduling via cooperative polling
TLDR
This paper presents a hierarchical scheduling model that aims to provide high-definition video conferencing applications with tight timing response, while at the same time preserve the strengths of current schedulers, namely fairness and efficiency.
GPU virtualization on VMware's hosted I/O architecture
TLDR
This paper describes in detail the specific GPU virtualization architecture developed for VMware's hosted products (VMware Workstation and VMware Fusion) and finds that taking advantage of hardware acceleration significantly closes the gap between pure emulation and native, but that different implementations and host graphics stacks show distinct variation.
Borrowed-virtual-time (BVT) scheduling: supporting latency-sensitive threads in a general-purpose scheduler
TLDR
Borrowed-Virtual-Time (BVT) Scheduling is presented, showing that it provides low-latency for real-time and interactive applications yet weighted sharing of the CPU across applications according to system policy, even with thread failure at the real- time level, all with a low-overhead implementation on multiprocessor as well as uniprocessors.
Graphic engine resource management
TLDR
This paper describes the design, implementation and evaluation of a Graphic Processing Unit (GPU) scheduler based on Deficit Round Robin scheduling that successfully allocates to every process an equal share of the GPU time regardless of their demand.
Real-time filesystems. Guaranteeing timing constraints for disk accesses in RT-Mach
TLDR
This study considers the use of two real-time disk scheduling algorithms: earliest deadline scheduling and just-in-time scheduling, a variation of aperiodic servers for the disk and shows the following positive but rather surprising result: the real- time scheduling filesystem not only provides guaranteed and timely access but also does so at relatively high levels of throughput.
Redline: First Class Support for Interactivity in Commodity Operating Systems
TLDR
Redline delivers responsiveness to interactive applications even in the face of extreme workloads including fork bombs, memory bombs and bursty, large disk I/O requests, reducing application pauses by up to two orders of magnitude.
Portable RK: a portable resource kernel for guaranteed and enforced timing behavior
  • S. Oikawa, R. Rajkumar
  • Computer Science
    Proceedings of the Fifth IEEE Real-Time Technology and Applications Symposium
  • 1999
TLDR
The evaluation results show that Portable RK in the form of Linux/RK gives direct control over timely resource utilization by applications and that its overhead costs are small enough to be negligible.
VMM-independent graphics acceleration
TLDR
VMGL allows applications executing within virtual machines (VMs) to leverage hardware rendering acceleration, thus solving a problem that has limited virtualization of a growing class of graphics-intensive applications.
...
...