This chapter is from the book
This chapter is from the book
This chapter is from the book
1.4 Conclusion
Some time ago, I had the pleasure of programming assembly language on a multicore digital signal processor, or DSP. The DSP performed matrix operations much, much faster than the computer on my desk, but there were two problems: I had to write all the routines for resource management and event handling, and there was no file system to organize the data. And without a network interface, it was hard to transfer data in and out of the device.
The Cell makes up for these shortcomings and provides many additional advantages. With SIMD processing, values can be grouped into vectors and processed in a single cycle. With Linux running on the PPE, memory and I/O can be accessed through a standard, reliable API. Most important, when all the SPEs crunch numbers simultaneously, they can process matrices at incredible speed.
The goal of this book is to enable you to build applications with similar performance. As with the DSP, however, it’s not enough just to know the C/C++ functions. You have to understand how the different processing elements work, how they’re connected, and how they access memory. But first, you need to know how to use the tools. The next chapter explains how to acquire and install IBM’s SDK.