C.W.K.
Stream
Quiz · 5 questions

➡️ Vectors — The First Real Workload

Embarrassingly parallel arithmetic, the 9-step GPU workflow, VRAM capacity zones

Level 0Beginner
0 XP0/38 lessons0/12 achievements
0/100 XP to next level100 XP to go0% complete

Quiz

01Why are vector operations called 'embarrassingly parallel'?
Hint
It's about cross-element dependencies, not the work being trivial.
02What does cudaMalloc do?
Hint
Memory on what kind of device?
03What happens in the 'Yellow Zone' of VRAM capacity?
Hint
Yellow means slow but not failing.
04How many steps are in the canonical GPU workflow?
Hint
Count the rows in the 9-step table.
05When you write a + b for two CUDA tensors in PyTorch, what eventually runs on the GPU?
Hint
What did you write in lesson 3?
Spotted a bug or have feedback on this page?Report an Issue

Comments 0

🔔 Reply notifications (sign in)
Sign inPlease sign in to comment.

No comments yet — be the first.