1
edit
Changes
→Bruno's Findings
So this is a good candidate for parallelization because we can send each iteration of the average calculation to a different GPU thread and since this is a simple average calculation, the GPU will be able to do it.
Running with a 1000x1000 matrix, with a epsilon error factor of 0.001, the program took almost 5 minutes to run completely and 99% of the time was on the getHeat() method (the heat calculation core).
====Carlos's Findings====
The array processing is a good choice and it is used in many applications, for example game development and image processing. It can calculate the transformation of a game world scene and its objects; besides, add filters on images as we can see in mobile apps such as Instagram.
It is a good candidate because it operates simple and repetitive calculations that can be divide among CUDA processors.
====Conclusion====
After analyzing both solutions and their applications, we have chosen the Heat Equation because of the number of different algorithms that we can find to solve array processing problems, such as CBLAS and cuBLAS. Due to the possibility of doing something that is not often done, we will work with the Heat Equation during this semester.
=== Assignment 2 ===
=== Assignment 3 ===
