KRISP: Enabling Kernel-wise RIght-sizing for Spatial Partitioned GPU Inference Servers-Reference-Cited by-同舟云学术

KRISP: Enabling Kernel-wise RIght-sizing for Spatial Partitioned GPU Inference Servers

Published:2023-02 Issue: Volume: Page:
ISSN:
Container-title:2023 IEEE International Symposium on High-Performance Computer Architecture (HPCA)
language:
Short-container-title:

Author:

Chow Marcus¹,Jahanshahi Ali¹,Wong Daniel¹

Affiliation:

1. University of California,Department of Computer Science & Engineering,Riverside

Funder

National Science Foundation

Publisher

IEEE

Link

http://xplorestaging.ieee.org/ielx7/10070856/10070923/10071121.pdf?arnumber=10071121

Reference69 articles.

1. Clipper: A {Low-Latency} in online prediction serving system;crankshaw;14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17),2017

2. Very deep convolutional networks for large-scale image recognition;simonyan,2014

3. μDPM: Dynamic Power Management for the Microsecond Era

4. {INFaaS}: Automated model-less inference serving;romero;2021 USENIX Annual Technical Conference (USENIX ATC 21),2021

5. Independent forward progress of work-groups;du¸tu;Proceedings of the ACM/IEEE 47th Annual International Symposium on Computer Architecture,0

Cited by 8 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. InSS: An Intelligent Scheduling Orchestrator for Multi-GPU Inference With Spatio-Temporal Sharing;IEEE Transactions on Parallel and Distributed Systems;2024-10

2. Corun: Concurrent Inference and Continuous Training at the Edge for Cost-Efficient AI-Based Mobile Image Sensing;Sensors;2024-08-14

3. ElasticRoom: Multi-Tenant DNN Inference Engine via Co-design with Resource-constrained Compilation and Strong Priority Scheduling;Proceedings of the 33rd International Symposium on High-Performance Parallel and Distributed Computing;2024-06-03

4. Paldia: Enabling SLO-Compliant and Cost-Effective Serverless Computing on Heterogeneous Hardware;2024 IEEE International Parallel and Distributed Processing Symposium (IPDPS);2024-05-27

5. Towards Deterministic End-to-end Latency for Medical AI Systems in NVIDIA Holoscan;2024 ACM/IEEE 15th International Conference on Cyber-Physical Systems (ICCPS);2024-05-13