NCA CUDA Programming & Parallel Computing 2

Question 1

Which CUDA memory type offers the lowest latency access for threads within the same block?

Accepted Answer

Shared memory

Answer

Shared memory is on-chip and accessible by all threads in a block with very low latency compared to off-chip global memory.

Question 2

What is a CUDA warp?

Accepted Answer

A group of 32 threads that execute in lockstep

Answer

A warp consists of 32 threads that are scheduled and executed together in SIMT fashion on an SM.

Question 3

What does the __syncthreads() intrinsic do in CUDA?

Accepted Answer

Acts as a barrier for all threads within a block

Answer

__syncthreads() inserts a barrier so all threads in the same block must reach that point before any can proceed.

Question 4

Which kernel launch configuration parameter controls the number of threads per block?

Accepted Answer

blockDim

Answer

blockDim specifies the dimensions (and thus total count) of threads within each block.

Question 5

When does warp divergence occur?

Accepted Answer

When threads within a warp follow different branches of an if-else

Answer

Warp divergence happens when threads in the same warp take different code paths, causing serial execution of each path.

(NCA) NVIDIA-Certified Associate Practice Test