Hand in your solution on RPILMS, unless instructions say otherwise. Each team should submit its solution under only 1 student's name. The other student's submission should just name the lead student. (This makes it easier for us to avoid grading it twice.)
If you have problems, then ask for help. The goal is to learn the material.
Homework 4, due Fri 2017-03-03, 9am.
Each person pick a topic from the 2016 GTC and give a 3 minute talk on it. We'll do 10 on Mon Mar 6 and the rest on Thurs Mar 9. Email Yin Li with your preferred date; first come, first served.
- Rewrite my CUDA matrix multiplication program, matmul2.cu, to tile the matrix into shared memory. How much faster is it?
- Now do it with cuBLAS. (You have to learn enough cuBLAS to do this.)