Gabriel's Journals

July 30, 2010

  • The SERVICE web site had a problem with our PHP scripts and so journals were down for a couple of weeks.
  • I have continued working on finalizing the Storytelling Alice curriculum. I have created a template system and the lessons now look more uniform in formatting. I will finish off by editing the lessons for grammar and clarity and by also wrapping up sections which were not finished. I will report which ones have been completed and which remain in the following journal entry.
  • Finally, I will begin writing up some things for the final report due in the middle of next month.
July 16, 2010

  • After discussing with Dr. Gardner about the CUDA to OpenCL compiler, which he was very interested in, I will likely be looking into Clang and LLVM as the compiler technologies to build upon.
  • However, as this topic is not directly related to the SERVICE project, I will focus on finishing the Storytelling Alice curriculum.
  • The lessons currently have differing formats, so I will be making a Word template to fit them all into. This will allow future changes to the lesson styles and layouts to be much easier to do and less tedious.
July 09, 2010

  • In an impromptu meeting with Dr. Feng, we talked about doing a CUDA to OpenCL compiler. I have interests in working with compilers and would like to see more OpenCL programs, therefore, I believe that I will work on this for my master's thesis.
  • I also got the most recent revisions of the lessons from Dr. Feng, so I will go about finalizing the styles, layouts, and fixing any glaring issues. If I have more time, I will go ahead and add in more parts that are not completed yet.
July 04, 2010

  • This last week I was able to successfully merge some simple CUDA kernels by hand. I also read generated the PTX code for them and was also able to merge those by hand, producing code very similar to what the generated PTX code from my merged CUDA kernels was.
  • Unfortunately, I am still waiting to hear back from a couple of the other memebers. I hope to do so soon so that I can begin finalizing the lessons.
  • I met with Dr. Feng and Dr. Gardner and we discussed my progress. There is a new architecture for NVIDIA cards that allows for multiple kernels to be run at once, so I may start looking into another direction for my master's thesis. Automatically merging kernels in software would be a backwards compatible approach, but should not be necessary for new GPUs.
  • Therefore, this next week I will look into what other aspects of GPU virtualization I can focus on. I will also begin looking through the lessons I have and seeing what needs to be done.