東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Adaptive Memory Management for CPU-GPU Heterogeneous Systems.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Adaptive Memory Management for CPU-GPU Heterogeneous Systems./
作者:	Ganguly, Debashis.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
面頁冊數:	126 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-11, Section: B.
Contained By:	Dissertations Abstracts International83-11B.
標題:	Scheduling. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29057107
ISBN:	9798426864115

Adaptive Memory Management for CPU-GPU Heterogeneous Systems.
Ganguly, Debashis.

Adaptive Memory Management for CPU-GPU Heterogeneous Systems. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 126 p.

Source: Dissertations Abstracts International, Volume: 83-11, Section: B.

Thesis (Ph.D.)--University of Pittsburgh, 2020.

This item must not be sold to any third party vendors.

High compute-density with massive thread-level parallelism of Graphics Processing Units (GPUs) is behind their unprecedented adoption in systems ranging from data-centers to high-performance computing installations. Currently, discrete GPU(s) combined with CPU via slow CPU-GPU interconnect dominate these computing platforms. The introduction of on-demand paging and fault-driven migration support in the newer generation GPUs, powered by software-managed unified memory runtime, simplified memory management in the CPU-GPU heterogeneous memory systems and ensured higher programmability. As GPUs are increasingly being used to accelerate general-purpose applications beyond traditional graphics processing, these systems raise a number of design challenges, including smart runtime systems, programming libraries, and micro-architecture.One of the key challenges this dissertation aims to address is the performance slowdown under device memory oversubscription. When the working set of an application exceeds the device's memory capacity, CPU-GPU interconnect-traffic from page eviction and software prefetching becomes a major source of performance bottleneck. Firstly, this dissertation proposes a pre-eviction policy, that adapts the semantics of software prefetcher to reduce the CPU-GPU interconnect traffic from unnecessary page thrashing. Secondly, this dissertation proposes an adaptive page migration and pinning strategy for the runtime that adapts to the irregularity in the access pattern based on the frequency of memory access. Disparate applications demand special attention for memory management based on their workload characteristics, thread-level parallelism, and memory access pattern. Finally, this dissertation introduces a smart runtime that transparently caters to different classes of applications by unifying a wide array of memory management strategies. As GPUs are becoming an integral part of commodity computing clusters, assuring system throughput and execution fairness is becoming a critical challenge for multi-tenant workloads. To this end, the dissertation proposes a CPU-GPU interconnect scheduler that provisions network traffic adapting to the disparate computation characteristics and bandwidth demands of participating applications in the composed workload. By introducing all these techniques, the dissertation makes significant progress towards realizing the goal of developing an adaptive, smart software-managed runtime for CPU-GPU heterogeneous memory systems.

ISBN: 9798426864115Subjects--Topical Terms:

750729
Scheduling.

Adaptive Memory Management for CPU-GPU Heterogeneous Systems.
LDR:03499nmm a2200301 4500 001 2348106
005 20220906075207.5
008 241004s2020 ||||||||||||||||| ||eng d
020 $a 9798426864115
035 $a (MiAaPQ)AAI29057107
035 $a (MiAaPQ)Pittsburgh39808
035 $a AAI29057107
040 $a MiAaPQ $c MiAaPQ
100 1 $a Ganguly, Debashis. $3 2090042
245 1 0 $a Adaptive Memory Management for CPU-GPU Heterogeneous Systems.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 126 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-11, Section: B.
500 $a Advisor: Melhem, Rami;Yang, Jun.
502 $a Thesis (Ph.D.)--University of Pittsburgh, 2020.
506 $a This item must not be sold to any third party vendors.
520 $a High compute-density with massive thread-level parallelism of Graphics Processing Units (GPUs) is behind their unprecedented adoption in systems ranging from data-centers to high-performance computing installations. Currently, discrete GPU(s) combined with CPU via slow CPU-GPU interconnect dominate these computing platforms. The introduction of on-demand paging and fault-driven migration support in the newer generation GPUs, powered by software-managed unified memory runtime, simplified memory management in the CPU-GPU heterogeneous memory systems and ensured higher programmability. As GPUs are increasingly being used to accelerate general-purpose applications beyond traditional graphics processing, these systems raise a number of design challenges, including smart runtime systems, programming libraries, and micro-architecture.One of the key challenges this dissertation aims to address is the performance slowdown under device memory oversubscription. When the working set of an application exceeds the device's memory capacity, CPU-GPU interconnect-traffic from page eviction and software prefetching becomes a major source of performance bottleneck. Firstly, this dissertation proposes a pre-eviction policy, that adapts the semantics of software prefetcher to reduce the CPU-GPU interconnect traffic from unnecessary page thrashing. Secondly, this dissertation proposes an adaptive page migration and pinning strategy for the runtime that adapts to the irregularity in the access pattern based on the frequency of memory access. Disparate applications demand special attention for memory management based on their workload characteristics, thread-level parallelism, and memory access pattern. Finally, this dissertation introduces a smart runtime that transparently caters to different classes of applications by unifying a wide array of memory management strategies. As GPUs are becoming an integral part of commodity computing clusters, assuring system throughput and execution fairness is becoming a critical challenge for multi-tenant workloads. To this end, the dissertation proposes a CPU-GPU interconnect scheduler that provisions network traffic adapting to the disparate computation characteristics and bandwidth demands of participating applications in the composed workload. By introducing all these techniques, the dissertation makes significant progress towards realizing the goal of developing an adaptive, smart software-managed runtime for CPU-GPU heterogeneous memory systems.
590 $a School code: 0178.
650 4 $a Scheduling. $3 750729
650 4 $a Software. $2 gtt. $3 619355
650 4 $a Evictions. $3 3687428
650 4 $a Bandwidths. $3 3560998
650 4 $a Computer science. $3 523869
690 $a 0984
710 2 $a University of Pittsburgh. $3 958527
773 0 $t Dissertations Abstracts International $g 83-11B.
790 $a 0178
791 $a Ph.D.
792 $a 2020
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=29057107