Multiple Choice
If variable a is host variable and dev_a is a device (GPU) variable, to copy input from variable a to variable dev_a select correct statement:
A) memcpy( dev_a, &a, size) ;
B) cudamemcpy( dev_a, &a, size, cudamemcpyhosttodevice ) ;
C) memcpy( (void*) dev_a, &a, size) ;
D) cudamemcpy( (void*) &dev_a, &a, size, cudamemcpydevicetohost ) ;
Correct Answer:

Verified
Correct Answer:
Verified
Q6: CUDA provides ------- warp and thread scheduling.
Q7: CUDA supports programming in ....<br>A)c or c++
Q8: FADD, FMAD, FMIN, FMAX are ----- supported
Q9: NVIDIA 8-series GPUs offer -------- .<br>A)50-200 gflops<br>B)200-400
Q10: CUDA stands for --------, designed by NVIDIA.<br>A)common
Q12: The NVIDIA G80 is a ---- CUDA
Q13: Each streaming multiprocessor (SM) of CUDA herdware
Q14: Each NVIDIA GPU has ------ Streaming Multiprocessors<br>A)8<br>B)1024<br>C)512<br>D)16
Q15: If variable a is host variable and
Q16: Out-of-order instructions is not possible on GPUs.