How can adding code to a loop make it faster?

by

My guess is, that in the first case two different branches end up in the same branch-prediction slot on the CPU. If these two branches predict different each time the code will slow down.

In the second loop, the added code may just be enough to move one of the branches to a different branch prediction slot.

To be sure you can give the Intel VTune analyzer or the AMD CodeAnalyst tool a try. These tools will show you what’s exactly going on in your code.

However, keep in mind that it’s most probably not worth to optimize this code further. If you tune your code to be faster on your CPU it may at the same time become slower on a different brand.

EDIT:

If you want to read on the branch-prediction give Agner Fog’s excellent web-site a try: http://www.agner.org/optimize/

This pdf explains the branch-prediction slot allocation in detail: http://www.agner.org/optimize/microarchitecture.pdf

More Related Contents:

  1. Will new return NULL in any case?
  2. Optimization code for a debug function (c++11 with templates) [closed]
  3. While loop using &&
  4. How to add additional libraries to Visual Studio project?
  5. Visual Studio support for new C / C++ standards?
  6. Constants and compiler optimization in C++
  7. Fastest way to get IPv4 address from string
  8. Setting the internal buffer used by a standard stream (pubsetbuf)
  9. while (1) Vs. for (;;) Is there a speed difference?
  10. Inherit interfaces which share a method name
  11. What does “#pragma comment” mean?
  12. How to create a UTF-8 string literal in Visual C++ 2008
  13. Why does Clang optimize away x * 1.0 but NOT x + 0.0?
  14. what is “stack alignment”?
  15. Linking to MSVC DLL from MinGW
  16. When do compilers inline C++ code?
  17. How does switch compile in Visual C++ and how optimized and fast is it?
  18. Is !! a safe way to convert to bool in C++?
  19. What the heque is going on with the memory overhead of std::deque?
  20. How to use _CRT_SECURE_NO_WARNINGS
  21. error LNK2005: xxx already defined in MSVCRT.lib(MSVCR100.dll) C:\something\LIBCMT.lib(setlocal.obj)
  22. Difference between managed C++ and C++ [closed]
  23. how to optimize matrix multiplication (matmul) code to run fast on a single processor core
  24. How do I convert from LPCTSTR to std::string?
  25. How do I iterate over a Constant Vector?
  26. Does GCC inline C++ functions without the ‘inline’ keyword?
  27. Expand macro inside string literal
  28. How do I get at the exception information when using MiniDumpWriteDump out-of-process?
  29. VS: unexpected optimization behavior with _BitScanReverse64 intrinsic
  30. Incompatible with parameter of type “LPCWSTR”

Leave a Comment