A Novel Architecture of Multi-GPU Computing Card

Sen Guo, Sanfeng Chen, YongSheng Liang

Abstract


The data transmission between GPUS in the existing multi_GPU computing card is often through PCIE which is in relative low speed, so the PCIE has become bottleneck of Overall performance. A novel architecture of multi_GPU computing card have been proposed in this paper: A multi-channel memory which have multiple interfaces is added, including one common interface shared by different GPUs, which is connected with a FPGA arbitration circuit and several other interfaces connected with dedicated GPUs frame buffer independently, and this multi-channel memory is called "global shared memory". The result of a simulation of accelerating computer tomography algebraic reconstruction on multi-GPU demonstrates effectiveness of this approach.

 

DOI: http://dx.doi.org/10.11591/telkomnika.v11i8.3038

 


Keywords


Multi-GPU; tomography algebraic reconstruction; GPGPU; CUDA

Full Text:

PDF

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Indonesian Journal of Electrical Engineering and Computer Science (IJEECS)
p-ISSN: 2502-4752, e-ISSN: 2502-4760
This journal is published by the Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU).

shopify stats IJEECS visitor statistics