This repo implements the architecture that appears in the following papers:
- Bingyi Zhang, Hanqing Zeng and Viktor Prasanna, Hardware Acceleration of Large Scale GCN Inference, The 31st IEEE International Conference on Application-specific Systems, Architectures and Processors. [PDF]
- Zeng, Hanqing, and Viktor Prasanna. "Graphact: Accelerating GCN training on CPU-FPGA heterogeneous platforms." The 2020 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays. 2020 [PDF]
We will keep adding instructions here for running the hardware modules.
- Quartus Prime Pro 20.2
- Modelsim
- Intel Stratix 10 GX
- acc: selecting Native Floating Point DSP intel Stratrix 10 FPGA IP. The detailed configurations are:
- sourcebuffer: selecting RAM: 4-port intel FPGA IP. The detailed configurations are:
- fifoindpr: selecting FIFO Intel FPGA Ip. The detailed configurations are:
- MAC: selecting Native Floating Point DSP intel Stratrix 10 FPGA IP. The detailed configurations are: