Performance Measurements of the 3D FFT on the Blue Gene/L Supercomputer

• Published in: Euro-Par 2005 Parallel Processing pp. 795 - 803
• Main Authors: Eleftheriou, Maria, Fitch, Blake, Rayshubskiy, Aleksandr, Ward, T. J. Christopher, Germain, Robert
• Format: Book Chapter Conference Proceeding
• Language: English
• Published: Berlin, Heidelberg Springer Berlin Heidelberg 2005; Springer
• Series: Lecture Notes in Computer Science
• Subjects: Applied sciences; Communication Layer; Computer science; control theory; systems; Computer systems and distributed systems. User interface; Destination List; Exact sciences and technology; Memory Access Pattern; Node Count; Software; Task Count; Supercomputer; High performance; Communicating process; Message passing; Scalability; Fast Fourier transformation; Performance characteristic; Message passing interface; Distributed system; Distributed computing
• ISBN: 3540287000; 9783540287001
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/11549468_87

This paper presents performance characteristics of a communications-intensive kernel, the complex data 3D FFT, running on the Blue Gene/L architecture. Two implementations of the volumetric FFT algorithm were characterized, one built on the MPI library using an optimized collective all-to-all operation [2] and another built on a low-level System Programming Interface (SPI) of the Blue Gene/L Advanced Diagnostics Environment (BG/L ADE) [17]. We compare the current results to those obtained using a reference MPI implementation (MPICH2 ported to BG/L with unoptimized collectives) and to a port of version 2.1.5 the FFTW library [14]. Performance experiments on the Blue Gene/L prototype indicate that both of our implementations scale well and the current MPI-based implementation shows a speedup of 730 on 2048 nodes for 3D FFTs of size 128 × 128 × 128. Moreover, the volumetric FFT outperforms FFTW port by a factor 8 for a 128× 128× 128 complex FFT on 2048 nodes.