Performance and Aging Aware Resource Allocation for Concurrent GPU Applications Under Process Variation

Tasoulas, Zois-Gerasimos; Anagnostopoulos, Iraklis

doi:10.1109/tnano.2019.2928268

Cited by 5 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…5. Performance and Aging aware: this methodology is presented in [9]. It uses ILP to pair applications together and profiles applications before execution.…”

Section: Resultsmentioning

confidence: 99%

“…The number of SMs that are available to an application affects the IPC (intructions per cycle) and the power consumption of the application [9,18]. As shown in [7], processes can be classified into categories according to their behavior.…”

Section: Motivationmentioning

confidence: 99%

“…As a consequence, the number of available SMs does not significantly determine the performance of memory intensive applications. An additional important observation made in [9,18] is that certain applications will drop their IPC, if the system provides more SMs to the application, above a certain threshold. As a result, there is an incentive to restrain the available SMs to an application, in order to achieve greater performance.…”

Section: Motivationmentioning

confidence: 99%

“…If SMs are spatially shared among multiple applications, the computational resources of the GPU can be continuously used, eliminating the underutilization. Unfortunately, as demonstrated in [4,6,7,9], combining applications together is not trivial. Applications competing for the same resources cause slow-down, which will lead to lower GPU throughput and lower performance than executing applications on their own, even if the hardware is underutilized in the single application scenario.…”

Section: Motivationmentioning

confidence: 99%

See 3 more Smart Citations

Improving GPU Performance with a Power-Aware Streaming Multiprocessor Allocation Methodology

Tasoulas¹,

Anagnostopoulos²

2019

Electronics

Self Cite

View full text Add to dashboard Cite

Graphics processing units (GPUs) are extensively used as accelerators across multiple application domains, ranging from general purpose applications to neural networks, and cryptocurrency mining. The initial utilization paradigm for GPUs was one application accessing all the resources of the GPU. In recent years, time sharing is broadly used among applications of a GPU, nevertheless, spatial sharing is not fully explored. When concurrent applications share the computational resources of a GPU, performance can be improved by eliminating idle resources. Additionally, the incorporation of GPUs in embedded and mobile devices increases the demand for power efficient computation due to battery limitations. In this article, we present an allocation methodology for streaming multiprocessors (SMs). The presented methodology works for two concurrent applications on a GPU and determines an allocation scheme that will provide power efficient application execution, combined with improved GPU performance. Experimental results show that the developed methodology yields higher throughput while achieving improved power efficiency, compared to other SM power-aware and performance-aware policies. If the presented methodology is adopted, it will lead to higher performance of applications that are concurrently executing on a GPU. This will lead to a faster and more efficient acceleration of execution, even for devices with restrained energy sources.

show abstract

“…5. Performance and Aging aware: this methodology is presented in [9]. It uses ILP to pair applications together and profiles applications before execution.…”

Section: Resultsmentioning

confidence: 99%

Section: Motivationmentioning

confidence: 99%

Section: Motivationmentioning

confidence: 99%

Section: Motivationmentioning

confidence: 99%

See 2 more Smart Citations

Improving GPU Performance with a Power-Aware Streaming Multiprocessor Allocation Methodology

Tasoulas¹,

Anagnostopoulos²

2019

Electronics

Self Cite

View full text Add to dashboard Cite

show abstract

Toward OS-Level and Device-Level Cooperative Scheduling for Multitasking GPUs

et al. 2020

View full text Add to dashboard Cite

As one of the most popular accelerators, the graphics processing unit (GPU) has been extensively adopted throughout the world. With the burst of new applications and the growing scale of data, co-running applications on limited GPU resources has become increasingly important due to its dramatic improvement in overall system efficiency. Quality of service (QoS) support among concurrent generalpurpose GPU (GPGPU) applications is currently one of the most trending research topics. Prior efforts have been focused on providing QoS support either with OS-level or device-level scheduling methods. Each of these scheduling methods possesses pros and cons and may be unable to independently cover all the scheduling cases. In this paper, we propose a cooperative QoS scheduling scheme (C-QoS) that consists of operating-system-level (OS-level) scheduling and device-level scheduling. Our proposed scheme can control the progress of a kernel and provide thorough QoS support for concurrent applications in multitasking GPUs. Due to the accurate resource management of the copy engine and execution engine, C-QoS achieves QoS goals 23.33% more often than state-of-the-art QoS support mechanisms. The results demonstrate that cooperative methods achieve 17.27% higher system utilization than uncooperative methods. INDEX TERMS Multitasking, parallel architectures, quality of service.

show abstract