mbitsnbites

↗ HN profile [ 58.9 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Today's find: You can get a floating-point approximation of 1/x that's accurate to 3 bits with a single integer subtraction instruction. float fast_reciprocal(float x) { unsigned i = *(unsigned *) &x; i = 0x7effffffU -…