BEGIN:VCALENDAR
PRODID:-//Microsoft Corporation//Outlook MIMEDIR//EN
VERSION:1.0
BEGIN:VEVENT
DTSTART:20121114T183000Z
DTEND:20121114T190000Z
LOCATION:255-BC
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:ABSTRACT: For scalable 3-D FFT computation using multiple GPUs, efficient all-to-all communication between GPUs is the most important factor in good performance. Implementations with point-to-point MPI library functions and CUDA memory copy APIs typically exhibit very large overheads especially for small message sizes in all-to-all communications between many nodes. We propose several schemes to minimize the overheads, including employment of lower-level API of InfiniBand to effectively overlap intra- and inter-node communication, as well as auto-tuning strategies to control scheduling and determine rail assignments. As a result we achieve very good strong scalability as well as good performance, up to 4.8TFLOPS using 256 nodes of TSUBAME 2.0 Supercomputer (768 GPUs) in double precision.
SUMMARY:Scalable Multi-GPU 3-D FFT for TSUBAME 2.0 Supercomputer
PRIORITY:3
END:VEVENT
END:VCALENDAR
BEGIN:VCALENDAR
PRODID:-//Microsoft Corporation//Outlook MIMEDIR//EN
VERSION:1.0
BEGIN:VEVENT
DTSTART:20121114T183000Z
DTEND:20121114T190000Z
LOCATION:255-BC
DESCRIPTION;ENCODING=QUOTED-PRINTABLE:ABSTRACT: For scalable 3-D FFT computation using multiple GPUs, efficient all-to-all communication between GPUs is the most important factor in good performance. Implementations with point-to-point MPI library functions and CUDA memory copy APIs typically exhibit very large overheads especially for small message sizes in all-to-all communications between many nodes. We propose several schemes to minimize the overheads, including employment of lower-level API of InfiniBand to effectively overlap intra- and inter-node communication, as well as auto-tuning strategies to control scheduling and determine rail assignments. As a result we achieve very good strong scalability as well as good performance, up to 4.8TFLOPS using 256 nodes of TSUBAME 2.0 Supercomputer (768 GPUs) in double precision.
SUMMARY:Scalable Multi-GPU 3-D FFT for TSUBAME 2.0 Supercomputer
PRIORITY:3
END:VEVENT
END:VCALENDAR