BEGIN:VCALENDAR
PRODID:-//Microsoft Corporation//Outlook MIMEDIR//EN
VERSION:1.0
BEGIN:VEVENT
DTSTART:20121114T230000Z
DTEND:20121114T233000Z
LOCATION:255-BC
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:ABSTRACT: This paper explores the performance and optimization of the IBM Blue Gene/Q (BG/Q) five dimensional torus network on up to 16K nodes. The BG/Q hardware supports multiple dynamic routing algorithms and different traffic patterns may require different algorithms to achieve best performance. Between 85% to 95% of peak network performance is achieved for all-to-all traffic, while over 85% of peak is obtained for challenging bisection pairings. A new software-controlled hardware algorithm is developed for bisection traffic that achieves better performance than any individual hardware algorithm.  To evaluate memory and network performance, the HPCC Random Access benchmark was tuned for BG/Q and achieved 858 Giga Updates per Second (GUPS) on 16K nodes. To further accelerate message processing, the message libraries on BG/Q enable the offloading of messaging overhead onto dedicated communication threads. Several applications, including Algebraic Multigrid (AMG), exhibit from 3 to 20% gain using communication threads.
SUMMARY:Looking Under the Hood of the IBM Blue Gene/Q Network
PRIORITY:3
END:VEVENT
END:VCALENDAR
BEGIN:VCALENDAR
PRODID:-//Microsoft Corporation//Outlook MIMEDIR//EN
VERSION:1.0
BEGIN:VEVENT
DTSTART:20121114T230000Z
DTEND:20121114T233000Z
LOCATION:255-BC
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:ABSTRACT: This paper explores the performance and optimization of the IBM Blue Gene/Q (BG/Q) five dimensional torus network on up to 16K nodes. The BG/Q hardware supports multiple dynamic routing algorithms and different traffic patterns may require different algorithms to achieve best performance. Between 85% to 95% of peak network performance is achieved for all-to-all traffic, while over 85% of peak is obtained for challenging bisection pairings. A new software-controlled hardware algorithm is developed for bisection traffic that achieves better performance than any individual hardware algorithm.  To evaluate memory and network performance, the HPCC Random Access benchmark was tuned for BG/Q and achieved 858 Giga Updates per Second (GUPS) on 16K nodes. To further accelerate message processing, the message libraries on BG/Q enable the offloading of messaging overhead onto dedicated communication threads. Several applications, including Algebraic Multigrid (AMG), exhibit from 3 to 20% gain using communication threads.
SUMMARY:Looking Under the Hood of the IBM Blue Gene/Q Network
PRIORITY:3
END:VEVENT
END:VCALENDAR