Consider the Hardware
It's a common opinion that slow software just needs faster hardware. This line of thinking is not necessarily wrong, but like misusing antibiotics, it can become a big problem over time. Software architecture has abstracted the underlying hardware so much that many developers don't have any idea how it really works. Furthermore, there is often a direct conflict of interest between best programming practices and writing code that screams on the given hardware.
First, let's look at how you can start to make the most of your CPUs' prefetch cache. Code branches such as if-then constructs can only go one of two ways (jump tables aside): condition met and condition not met. Most prefetch caches look ahead by "guessing" where your code will branch to. When the cache "guesses" correctly, it's amazingly fast. If it "guesses" wrong, on the other hand, all the preprocessing on this "wrong branch" is useless and a time-consuming cache invalidation occurs. Fortunately, it's easy to start making the prefetch cache work harder for you.
If you code your branch logic so that the most frequent result is the condition that is tested for, you will help your CPU's prefetch cache be "correct" more often, leading to fewer CPU-expensive cache invalidations. This sometimes may read a little awkwardly, but systematically applying this technique over time will decrease your code's execution time.
Now, let's look at some of the conflicts between writing code for hardware and writing against mainstream best practices.
It's common practice to write many small functions in favor of large ones to ease maintainability, but the fact is that function calls require moving data to and from the stack to prepare for the function call and to return properly from it. Many applications using this paradigm spend more time preparing and recovering from work than actually doing it! Truth is, the goto command is the fastest method to get around in a code block, followed closely by jump tables. Functions are great for us developers; from the CPU's point of view, however, they are penny smart and dollar dumb.
Inline functions are a different animal that trades requiring start up and completion tasks for overall program size. The word inline is accurate because everywhere in your source code where you have a call to an inline function, the code for that function is copied into your code verbatim and then it is compiled. Having too many inline functions, especially large ones, can significantly increase your compiled application's filesize; this might be a worthwhile trade. Speed or Filesize? Make your choice!
Depending on your compiler, there can be implications on program execution speed using classes. Many developers seem to think having class libraries that contain many generations of inheritance is wonderful when it comes at a price. Normal inheritance levels incur some overhead if you get into the nuts and bolts of them but the real problem when it comes to efficiency is those nasty virtual functions. Virtual functions require a virtual base class lookup table for each level of virtual inheritance and matters can get exponentially worse when there are multiple levels of inheritance. There are better things your processor could be doing than traversing memory linked list tables to hunt for code to run.
What hardware are you developing for? What does your compiler do to your code as it turns it to assembly language? Are you using a virtual machine? You'll rarely find a single programming methodology that will work perfectly on all hardware platforms, real or virtual.
Video game and embedded system developers know the hardware ramifications of their compiled code. Do you?
By Jason P Sage
This work is licensed under a Creative Commons Attribution 3
Back to 97 Things Every Programmer Should Know home page