CD-MSA: Cooperative and Deadline-Aware Scheduling for Efficient Multi-Tenancy on DNN Accelerators

With DNN turning into the backbone of AI cloud services and propelling the emergence of INFerence-as-a-Service (INFaaS), DNN-specific accelerators have become the indispensable components of cloud inference systems. Due to the conservative "one-task-at-a-time" working mode and deadline bli...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on parallel and distributed systems Ročník 34; číslo 7; s. 1 - 17
Hlavní autoři:	Wang, Chunyang, Bai, Yuebin, Sun, Desen
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.07.2023 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Accelerators Arrays Computer architecture deep neural networks domain-specific architectures Hardware Inference Preempting Processor scheduling Quality of service Real-time systems Run time (computers) Scheduling scheduling and task partitioning Switches System-on-chip Systolic arrays Task analysis Throughput
ISSN:	1045-9219, 1558-2183
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!