Lecture 8
Learning objectives
After this class, you should be able to:
- Program the PS3 using the framework presented in class.
Reading assignment
- Read the code under
ps3/ppu
andps3/spu
directories onlinprog
.Exercises and review questions
- Exercises and review questions on current lecture's material
- In Example 3 of Lecture 7, each SPE reads a portion of an array from main memory and computes the square of each element. If the data size is very large, then it will not fit in cache. In that case, you will need to bring pieces of data to the SPE and compute their squares. Write a code that does this using the programming framwork discussed in class.
- Time DMA performance on the SPEs, to fetch data from main memory and from the local store of another SPE, as a function of the size of data fetched. Your code should use the programming framwork discussed in class. Report your results on the discussion board, under the
Lecture 8
thread.- Preparation for the next lecture
- Compare the performance of matrix multiplication with different compiler optimizations flags (such as -O2 and -O3). Report your results on the discussion board, under the
Lecture 8
thread.
Last modified: 3 Feb 2010