(When you are done, please submit your solution using the Fire system)

In this lab assignment, you will get experience of parallel programming, first in CUDA and then in Obsidian (which generates CUDA). The exercises are associated with Joel Svensson’s lecture on May 19th 2016.

Note: Please make sure you follow the submission guidelines when you write your code.

Submit the answers to all the exercises provided by Joel: Obsidian Lab

You are provided with two files as templates that you can edit: cuda_template.cu and ObsLab.hs. Note that you must use a GPU than runs CUDA (that is one from NVIDIA). You may already have one in your laptop or desktop. If you do, please use your own machine. We will shortly provide instructions for running on a GPU instance in Amazon Web Services EC2. (We will run a single GPU instance continuously, and you will have to share it, and be careful to check if someone is already running on it.)

Submission

This lab has two deadlines:

• First deadline (Thursday, May 26 at 23:59): You need to have made a serious effort on all obligatory parts of the lab assignment.
• Final deadline (Thursday, June 2 at 23:59): You need to have passed the lab unless you have requested and been given an extension.

Before you submit your code, Clean It Up! Remember, submitting clean code is Really Important, and simply the polite thing to do. After you feel you are done, spend some time on cleaning your code; make it simpler, remove unneccessary things, etc. We will reject your solution if it is not clean. Clean code:

• Does not have long lines (< 78 characters)
• Has a consistent layout (do not use TAB characters in your code)
• Has type signatures for all top-level functions
• Has good comments
• Has no junk (junk is unused code, commented code, unneccessary comments)
• Has no overly complicated function definitions
• Does not contain any repetitive code (copy-and-paste programming)

When you are done, please submit using the Fire system.

Good luck!