Author:
Mizutani Kenji,Urino Yutaka,Shimizu Takanori,Yamaguchi Hiroshi,Nakamura Shigeru,Usuki Tatsuya,Ishii Kiyo,Matsumoto Ryosuke,Inoue Takashi,Namiki Shu,Koibuchi Michihiro
Abstract
This paper presents a high-throughput dataflow processing using all-to-all communication with eight FPGAs. We demonstrated a parallel radix sorting throughput of 37.2 GB/s for 32-bit key range and 16-GiB data size.