RGEM: A Responsive GPGPU Execution Model for Runtime Engines

Kato, Shigeo; Lakshmanan, Karthik; Kumar, Amit; Kelkar, Mihir; Ishikawa, Yutaka; Rajkumar, Ragunathan

doi:10.1109/rtss.2011.13

Cited by 98 publications

(77 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RGEM [Kato et al 2011c] develops a responsive GPGPU execution model for GPGPU tasks in real-time multi-tasking environments, similarly to TimeGraph [Kato et al 2011d]. RGEM introduces two scheduling methods: Memory-Copy Transaction scheduling and Kernel Launch scheduling.…”

Section: Algorithms For Scheduling a Single Gpumentioning

confidence: 99%

GPU Virtualization and Scheduling Methods

2017

View full text Add to dashboard Cite

The integration of graphics processing units (GPUs) on high-end compute nodes has established a new accelerator-based heterogeneous computing model, which now permeates high performance computing. The same paradigm nevertheless has limited adoption in cloud computing or other large-scale distributed computing paradigms. Heterogeneous computing with GPUs can benefit the Cloud by reducing operational costs and improving resource and energy efficiency. However, such a paradigm shift would require effective methods for virtualizing GPUs, as well as other accelerators. In this survey paper, we present an extensive and in-depth survey of GPU virtualization techniques and their scheduling methods. We review a wide range of virtualization techniques implemented at the GPU library, driver, and hardware levels. Furthermore, we review GPU scheduling methods that address performance and fairness issues between multiple virtual machines sharing GPUs. We believe that our survey delivers a perspective on the challenges and opportunities for virtualization of heterogeneous computing environments.

show abstract

Section: Algorithms For Scheduling a Single Gpumentioning

confidence: 99%

GPU Virtualization and Scheduling Methods

2017

View full text Add to dashboard Cite

show abstract

“…The execution on a modern GPU is shown in Figure 2a, where the kernel with a deadline (K3) does not get scheduled until all previously issued kernels (K1 and K2) have finished executing. A software implementation [16] or a modification to GPU command scheduler could allow priorities to be assigned to processes, resulting in the timeline shown in Figure 2b.…”

Section: Arguments For Preemptive Executionmentioning

confidence: 99%

“…GERM [7] and TimeGraph [17] focus on graphics applications and provide a GPU command schedulers integrated in the device driver. RGEM [16] is a software runtime library targeted at providing responsiveness to prioritized CUDA applications by scheduling DMA transfers and kernel invocations. RGEM implements memory transfers as a series of smaller transfers and thus create the potential preemption points, lowering the stall time due to the competing memory transfers.…”

Section: Related Workmentioning

confidence: 99%

“…However, as the number of applications ported to GPUs grows, sharing scenarios are starting to appear. Issues with GPU sharing, such as priority inversion and no fairness, have already been noticed by operating systems [30,17,18,27] and real-time [16,6] research communities. Moreover, with the integration of programmable GPUs into mobile SoCs [31,5] and consumer CPUs [3,15], the demand for GPU sharing is likely to increase.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enabling preemptive multiprogramming on GPUs

Tanasic

Gelado

Cabezas

et al. 2014

SIGARCH Comput. Archit. News

View full text Add to dashboard Cite

GPUs are being increasingly adopted as compute accelerators in many domains, spanning environments from mobile systems to cloud computing. These systems are usually running multiple applications, from one or several users. However GPUs do not provide the support for resource sharing traditionally expected in these scenarios. Thus, such systems are unable to provide key multiprogrammed workload requirements, such as responsiveness, fairness or quality of service.In this paper, we propose a set of hardware extensions that allow GPUs to efficiently support multiprogrammed GPU workloads. We argue for preemptive multitasking and design two preemption mechanisms that can be used to implement GPU scheduling policies. We extend the architecture to allow concurrent execution of GPU kernels from different user processes and implement a scheduling policy that dynamically distributes the GPU cores among concurrently running kernels, according to their priorities. We extend the NVIDIA GK110 (Kepler) like GPU architecture with our proposals and evaluate them on a set of multiprogrammed workloads with up to eight concurrent processes. Our proposals improve execution time of high-priority processes by 15.6x, the average application turnaround time between 1.5x to 2x, and system fairness up to 3.4x.

show abstract

“…GPUs have received serious consideration in the real-time community only recently. Both theoretical work ( [9], [10]) on partitioning and scheduling algorithms and applied work ( [11], [12], [13]) on qualityof-service techniques and improved responsiveness has been done. Outside the real-time community, others have proposed operating system designs where GPUs are scheduled in much the same way as CPUs [14].…”

Section: Introductionmentioning

confidence: 99%

Robust Real-Time Multiprocessor Interrupt Handling Motivated by GPUs

Elliott

Anderson

2012

2012 24th Euromicro Conference on Real-Time Systems

View full text Add to dashboard Cite

Abstract-Architectures in which multicore chips are augmented with graphics processing units (GPUs) have great potential in many domains in which computationally intensive real-time workloads must be supported. However, unlike standard CPUs, GPUs are treated as I/O devices and require the use of interrupts to facilitate communication with CPUs. Given their disruptive nature, interrupts must be dealt with carefully in real-time systems. With GPU-driven interrupts, such disruptiveness is further compounded by the closed-source nature of GPU drivers. In this paper, such problems are considered and a solution is presented in the form of an extension to LITMUS RT called klmirqd. The design of klmirqd targets systems with multiple CPUs and GPUs. In such settings, interruptrelated issues arise that have not been previously addressed.

show abstract

RGEM: A Responsive GPGPU Execution Model for Runtime Engines

Cited by 98 publications

References 14 publications

GPU Virtualization and Scheduling Methods

GPU Virtualization and Scheduling Methods

Enabling preemptive multiprogramming on GPUs

Robust Real-Time Multiprocessor Interrupt Handling Motivated by GPUs

Contact Info

Product

Resources

About