• State Resolved
  • Locked Locked
  • Replies 1 reply
  • Subscribers 81 subscribers
  • Views 245 views
  • Users 0 members are here
Support feedback
Options
Options
Similar topics

This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

Compiler/TMS320F28335: fastest way to zero out array

Howard Zou
Genius 12365 points
Part Number: TMS320F28335

Tool/software: TI C/C++ Compiler

Hi,

my customer tested two methods 

1. 

memset(array, 0, sizeof(array[0][0]) * m * n)

2.

for(j = 0; j < n; j++)
{
    for(i = 0; i < m; i++)
    {  
        array[i][j] = 0;
    }

}

The second code will occupy more space, but it can run faster than the first code, right? We measured that the second code runs faster, but we are not sure if it's true.

  • 0
    TI__Guru**** 232640 points

    What is the type of one element of the array?  If it is a long, float, or double, then I would expect the second version to be faster.  memset works one 16-bit word at a time, without regard for the type of the elements in the array.  The second version works one element of the array at a time.  If that is bigger than a 16-bit word, it will be faster.

    Thanks and regards,

    -George