Kilo TM: Hardware Transactional Memory for GPU Architectures

Authors:
Wilson Wai Lun Fung;Inderpreet Singh;Andrew Brownsword;Tor Aamodt
Affiliations:
University of British Columbia;University of British Columbia;Electronic Arts;University of British Columbia
Venue:
IEEE Micro
Year:
2012

Citing 0
Cited 1

SI-TM: reducing transactional memory abort rates through snapshot isolation

Proceedings of the 19th international conference on Architectural support for programming languages and operating systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Programming GPUs is challenging for applications with irregular fine-grained communication between threads. To improve the programmability of GPUs and thus extend their usage to a wider range of applications, the authors propose to enable transactional memory (TM) on GPUs via Kilo TM, a novel hardware TM system that scales to thousands of concurrent transactions.