Why does optimisation kill this function?

by

In C++, pointer arguments are assumed not to alias (except char*) if they point to fundamentally different types (“strict aliasing” rules). This allows some optimizations.

Here, u64 tmp is never modified as u64.
A content of u32* is modified but may be unrelated to ‘u64 tmp‘ so may be seen as nop for u64 tmp.

More Related Contents:

  1. Optimization code for a debug function (c++11 with templates) [closed]
  2. What are copy elision and return value optimization?
  3. How do I convert between big-endian and little-endian values in C++?
  4. Which, if any, C++ compilers do tail-recursion optimization?
  5. What are the mechanics of short string optimization in libc++?
  6. Why is transposing a matrix of 512×512 much slower than transposing a matrix of 513×513?
  7. Is it better to use std::memcpy() or std::copy() in terms to performance?
  8. gcc optimization flag -O3 makes code slower than -O2
  9. C/C++: Force Bit Field Order and Alignment
  10. Strict aliasing rule and ‘char *’ pointers
  11. How to get IOStream to perform better?
  12. Which is better option to use for dividing an integer number by 2?
  13. will casting around sockaddr_storage and sockaddr_in break strict aliasing
  14. Why should I ever use inline code?
  15. Does a c/c++ compiler optimize constant divisions by power-of-two value into shifts?
  16. union for uint32_t and uint8_t[4] undefined behavior? [duplicate]
  17. How to use profile guided optimizations in g++?
  18. C++ error: ‘_mm_sin_ps’ was not declared in this scope
  19. Fast multiplication/division by 2 for floats and doubles (C/C++)
  20. Loop with a zero execution time
  21. std::vector reserve() and push_back() is faster than resize() and array index, why?
  22. Most insanely fast way to convert 9 char digits into an int or unsigned int
  23. reinterpret_cast between char* and std::uint8_t* – safe?
  24. Optimizations for pow() with const non-integer exponent?
  25. Does GCC inline C++ functions without the ‘inline’ keyword?
  26. Which is faster/preferred: memset or for loop to zero out an array of doubles?
  27. Is it a strict aliasing violation to alias a struct as its first member?
  28. How to implement “_mm_storeu_epi64” without aliasing problems?
  29. VS: unexpected optimization behavior with _BitScanReverse64 intrinsic
  30. List of common C++ Optimization Techniques [closed]

Leave a Comment