Title :
RadixBoost: A hardware acceleration structure for scalable radix sort on graphic processors
Author :
Xingyu Liu ; Shikai Li ; Kuan Fang ; Yufei Ni ; Zonghui Li ; Yangdong Deng
Author_Institution :
Inst. of Microelectron., Tsinghua Univ., Beijing, China
Abstract :
In this paper, we propose RadixBoost, a hardware acceleration structure for scalable 32-bit integer radix sort on GPU. The whole structure is integrated into a GPU microarchitecture as a special functional unit and can be started by new instructions. Our design enables a significantly faster sorting procedure for general purpose GPU computing. The RadixBoost architecture was validated by an FPGA prototype integrated in FPGA-based GPU microarchitecture simulator, Fastlanes. An ASIC evaluation of RadixBoost was also performed. Our results proved that RadixBoost outperformed its GPU software equivalent by a factor of over 6 with an 1% and 3% increase in area and power respectively in cutting-edge Fermi GPU.
Keywords :
application specific integrated circuits; field programmable gate arrays; graphics processing units; integrated circuit design; logic design; ASIC; FPGA; Fastlanes; Fermi GPU; RadixBoost; graphic processors; hardware acceleration structure; microarchitecture; scalable radix; word length 32 bit; Acceleration; Application specific integrated circuits; Arrays; Field programmable gate arrays; Graphics processing units; Hardware; Sorting; ASIC evaluation; FPGA; GPU; hardware acceleration; prefix sum; radix sort;
Conference_Titel :
Circuits and Systems (ISCAS), 2015 IEEE International Symposium on
Conference_Location :
Lisbon
DOI :
10.1109/ISCAS.2015.7168848