Accelerator for a Convolutional Layer written in Verilog. For SCU ELEN249, taught by Kiran Gunnam.
-
Implement all the 3 approaches listed in the paper (Code 1, Code 2 and Code 3) in MATLAB.
completed in ./matlab/ folder
-
Model the core part of the hardware accelerator (as shown in Fig 7 of the paper for the convolutional layer with unroll factor <64,7> in MATLAB and Verilog . Both should match.
completed in ./64_7/ folder
-
Model the DRAM access patterns for the input and output for all the 3 approaches in MATLAB.
see README.md in ./matlab/ folder