Skip to main content

Intelligent Scheduling and Memory Management Techniques for Modern GPU Architectures

Abstract With the massive multithreading execution feature, graphics processing units (GPUs) have been widely deployed to accelerate general-purpose parallel workloads (GPGPUs). However, using GPUs to accelerate computation does not always gain good performance improvement. This is mainly due to three inefficiencies in modern GPU and system architectures.

First, not all parallel threads have a uniform amount of workload to fully utilize GPU’s computation ability, leading to a sub-optimal performance problem, called warp criticality. To mitigate the degree of warp criticality, I propose a Criticality-Aware Warp Acceleration mechanism, called CAWA. CAWA predicts and accelerates the critical warp execution by allocating larger execution time slices an... (more)
Created Date 2017
Contributor Lee, Shin-Ying (Author) / Wu, Carole-Jean (Advisor) / Chakrabarti, Chaitali (Committee member) / Ren, Fengbo (Committee member) / Shrivastava, Aviral (Committee member) / Arizona State University (Publisher)
Subject Computer engineering / Computer science / Electrical engineering / Cache Bypassing / GPGPU / Performance Prediction / Resource Contention / Warp Scheduling
Type Doctoral Dissertation
Extent 161 pages
Language English
Reuse Permissions All Rights Reserved
Note Doctoral Dissertation Computer Engineering 2017
Collaborating Institutions Graduate College / ASU Library
Additional Formats MODS / OAI Dublin Core / RIS

  Full Text
8.0 MB application/pdf
Download Count: 287

Description Dissertation/Thesis