Summary

This chapter explained the launch of multiple blocks, with each having multiple threads from the kernel function. It showed the method for choosing the two parameters for a large value of threads. It also explained the hierarchical memory architecture that can be used by CUDA programs. The memory nearest to the thread being executed is fast, and as we move away from it, memories get slower. When multiple threads want to communicate with each other, then CUDA provides the flexibility of using shared memory, by which threads from the same blocks can communicate with each other. When multiple threads use the same memory location, then there should be synchronization between the memory access; otherwise, the final result will not be as expected. We also saw the use of an atomic operation to accomplish this synchronization. If some parameters remain constant throughout the...