G-DMA: improving memory access performance for hardware accelerated sparse graph computation

Scatter-gather direct memory access (DMA) transfers can be used to efficiently fetch graph memory data for onchip processing of graph applications. We present a hardware controlled graph DMA engine which can operate autonomously without the need for CPU interaction. Graph processing algorithms can asynchronously request graph data which is fetched from memory and streamed to the processing core. An implementation of Dijkstra's shortest path algorithm operating on real-world social network graph data is used to demonstrate the operation of our hardware controlled graph DMA engine. Our system shows a 38% decrease in processing time over a standard CPU implementation and up to an 11% improvement over a hardware implementation using standard AXI4 read requests.

[1]  K. Sridharan,et al.  Hardware architecture for finding shortest paths , 2009, TENCON 2009 - 2009 IEEE Region 10 Conference.

[2]  Phillip H. Jones,et al.  CyGraph: A Reconfigurable Architecture for Parallel Breadth-First Search , 2014, 2014 IEEE International Parallel & Distributed Processing Symposium Workshops.

[3]  Steve,et al.  使用Zynq-7000 All Programmable SoC实现图像传感器色彩校正 , 2013 .

[4]  Yu Wang,et al.  A Reconfigurable Computing Approach for Efficient and Scalable Parallel Graph Exploration , 2012, 2012 IEEE 23rd International Conference on Application-Specific Systems, Architectures and Processors.

[6]  Jason D. Bakos,et al.  Memory Access Scheduling on the Convey HC-1 , 2013, 2013 IEEE 21st Annual International Symposium on Field-Programmable Custom Computing Machines.

[7]  J. Abdul-Jabbar,et al.  A New Hardware Architecture for Parallel Shortest Path Searching Processor Based-on FPGA Technology , 2012 .

[8]  Jure Leskovec,et al.  {SNAP Datasets}: {Stanford} Large Network Dataset Collection , 2014 .

[9]  Luca Benini,et al.  Energy and performance exploration of accelerator coherency port using Xilinx ZYNQ , 2013 .

[10]  Nachiket Kapre,et al.  GraphMMU: Memory Management Unit for Sparse Graph Accelerators , 2015, 2015 IEEE International Parallel and Distributed Processing Symposium Workshop.

[11]  Edsger W. Dijkstra,et al.  A note on two problems in connexion with graphs , 1959, Numerische Mathematik.