Current Result Document :
| 한글제목(Korean Title) |
다중차용 인공지능 시스템을 위한 메모리 스케줄러 최적화 |
| 영문제목(English Title) |
Optimizing the Memory Scheduler for Multi-tenant Deep Learning Accelerator |
| 저자(Author) |
김태현
이혁재
이진호
Taehyun Kim
HyukJae Lee
Jinho Lee
|
| 원문수록처(Citation) |
VOL 45 NO. 01 PP. 2125 ~ 2127 (2022. 06) |
한글내용
(Korean Abstract) |
|
영문내용
(English Abstract) |
Neural Processing Unit(NPU) is a cheap and practical device-of-choice for future deep learning platform providers. In realistic datacenter settings, many NPUs may share a common memory system while different processes are executed on one or more separate NPUs. Application running on such systems may experience unfair slowdowns due to memory-sharing and fixed memory scheduling policy, which can harm service QoS and throughput. This paper points out that the commonly used First-Ready, First-Come, First-Serve (FRFCFS) policy causes unfairness in memory services among simultaneously-executed processes. Motivated byour findings, we propose an improved policy that can mitigate this problem. |
| 키워드(Keyword) |
|
| 파일첨부 |
PDF 다운로드
|
