Multicore programming with CPU and GPU
HW1 ~ HW4 → CPU
HW1 : 1D array filter
HW2 : locked open addressing hash table
HW3 : matrix multiplication
HW4 : Smith-Waterman
HW5 ~ HW7 → GPU
HW5 : matrix multiplication
HW6 : parallel sum reduction
HW7 : DNN VGG16