Jump to content

  • Log In with Google      Sign In   
  • Create Account


Member Since 18 Jun 2010
Offline Last Active Dec 21 2015 08:53 PM

Posts I've Made

In Topic: Problem computing GJK support points

08 November 2012 - 08:45 AM

Maybe I'm missing something, but what is wrong with (0, 20)? Although it is not one of the vertices, it is on the bounds of the minkowski difference. My understanding of the GJK algorithm is that it should still work correctly.

Greggles maybe I'm misunderstanding you, what you say is correct but the vertex (0,20) or any support point is indeed one of the vertices... if you mean the vertices of the Minkowski difference.

In Topic: SSE optimizations not so optimized

15 September 2011 - 02:55 AM

Thanks for the help i could fix the problem. First try like Hodgman suggested, make operations in a small working set so i had locality in the data. This made the SSE operations as fast as expected. Then i put more operations in each loop like japro told, with that i got great results. The only thing strange is that the compiler didnt unroll my loop even if i put a bound known at compile time(iterations is a define):

for(unsigned int i=0; i < (iterations-1) ;++i)//not unrolling so i put a lot of operations in each loop
//15 SSE operations

I thougth this kind of things was always optimized....

Other thing, more as a curiosity than anything else, is that the operations between inf with the fpu is EXTREMELY SLOW(i had a case when the data had an overflow, i already fixed that). I dont know if it is because some flags are set because of the inf or is something else... in the same condition the SSE operations are exactly as fast as before.

Posted Image

Posted Image

PS: thanks for the links Hodgman, they are really useful.