NCA CUDA Programming & Parallel Computing 3

Question 1

What is the purpose of cudaMemcpy with the flag cudaMemcpyDeviceToHost?

Accepted Answer

Copies data from GPU global memory to host RAM

Answer

cudaMemcpyDeviceToHost transfers data from device (GPU) memory back to host (CPU) memory.

Question 2

In CUDA, what is 'occupancy'?

Accepted Answer

The ratio of active warps to maximum warps on an SM

Answer

Occupancy measures how many warps are active on an SM relative to the hardware maximum, indicating how well latency can be hidden.

Question 3

Which qualifier declares a function that runs on the GPU and is called from the host?

Accepted Answer

__global__

Answer

__global__ marks a kernel function that executes on the GPU but is invoked from CPU code using the <<<>>> launch syntax.

Question 4

What causes shared memory bank conflicts?

Accepted Answer

Multiple threads accessing the same shared memory bank in a single transaction

Answer

Bank conflicts occur when multiple threads in a warp access different addresses that map to the same memory bank, forcing serialized access.

Question 5

What does the CUDA programming model term 'grid' refer to?

Accepted Answer

The collection of all thread blocks launched by a kernel

Answer

A grid is the complete set of thread blocks that are launched together when a kernel is invoked.

(NCA) NVIDIA-Certified Associate Practice Test