Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

PMR - Fast Application Response via Parallel Memory Reclaim on Mobile Devices

USENIX via YouTube

Overview

Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn about PMR (Parallel Memory Reclaim), an innovative memory management solution designed to enhance mobile application performance through this 14-minute conference presentation from USENIX ATC '25. Discover how researchers from East China Normal University, National Yang Ming Chiao Tung University, City University of Hong Kong, and MBZUAI address the critical challenge of inefficient memory management in Android systems that struggle to meet the performance demands of modern mobile applications. Explore the two key techniques that form the foundation of PMR: Proactive Page Shrinking (PPS), which decouples time-consuming page shrinking and page writeback operations for parallel execution, and Storage-Friendly Page Writeback (SPW), which optimizes write I/O operations through batched unmapping of victim pages for efficient bulk writeback. Understand how current kernel-level memory reclaim designs fail to exploit upgraded storage devices and learn about the experimental methodology used to validate PMR's effectiveness on real-world mobile devices. Examine the impressive performance improvements achieved, including up to 43.6% faster application response times compared to the original Android memory reclaim approach, and gain insights into how parallel memory reclaim can significantly enhance user experience on mobile devices with increasingly high memory demands.

Syllabus

USENIX ATC '25 - PMR: Fast Application Response via Parallel Memory Reclaim on Mobile Devices

Taught by

USENIX

Reviews

Start your review of PMR - Fast Application Response via Parallel Memory Reclaim on Mobile Devices

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.