ATUNs: Modular and Scalable Support for Atomic Operations in a Shared Memory Multiprocessor


METADATA ONLY
Loading...

Date

2020

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Atomic operations are crucial for most modern parallel and concurrent algorithms, which necessitates their optimized implementation in highly-scalable manycore processors. We pro-pose a modular and efficient, open-source ATomic UNit (ATUN) architecture that can be placed flexibly at different levels of the memory hierarchy. ATUN demonstrates near-optimal linear scaling for various synthetic and real-world workloads on an FPGA prototype with 32 RISC-V cores. We characterize the hardware complexity of our ATUN design in 22 nm FDSOI and find that it scales linearly in area (only 0.5 kGE per core) and logarithmically in the critical path. © 2020 IEEE.

Permanent link

Publication status

published

Editor

Book title

2020 57th ACM/IEEE Design Automation Conference (DAC)

Journal / series

Volume

Pages / Article No.

9218661

Publisher

IEEE

Event

57th ACM/IEEE Design Automation Conference (DAC 2020) (virtual)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Organisational unit

03996 - Benini, Luca / Benini, Luca check_circle
03950 - Hoefler, Torsten / Hoefler, Torsten check_circle

Notes

Due to the Coronavirus (COVID-19) the conference was conducted virtually.

Funding

732631 - Open Transprecision Computing (EC)

Related publications and datasets