MWB
Reputation: 12577
How does GFortran handle stride=1 arrays?
When arrays have stride equal to 1 (a very common case), it seems that code compiled for the generic case (any nonzero stride) will often be suboptimal.
On the other hand, creating multiple versions of compiled functions and subroutines when some of the arguments are stride=1 scales exponentially with the number of arguments that are arrays.
What is the approach taken by GFortran here?
Upvotes: 3
Views: 185
Answers (0)
Related Questions
- How does fortran compilers optimize operations in routines' arguments
- gfortran compiler bug?
- Generation of array temporaries for pure functions in fortran
- Why does a subroutine with an array as an input give faster performance than the same subroutine with an automatic local array?
- Does this code demonstrate a bug in GFortran?
- Why the array arrangment affects speedup?
- Why does gfortran produce such a large stack size compared to C++ in this simple program?
- Obtaining the stride of an Fortran Array
- Reduction of output array dimension in Fortran77 procedure
- Could the compiler vectorize the looping with an array which consists of an array inside?