We are currently in the process of converting the website to the new design. Some pages, like this one, are still broken. We appreciate your patience.
GCC: MSVC: MSVC shows worse numbers than GCC here because it decides to not inline qrot/grot funct…
Try removing if (unlikely(dot==1.0f)) return (v3){0,0,0}; /* a == b */
Benchmark for transforming a lot of vectors against the same quaternion or gibbs rotation: GCC 7.…
Actually wait, I forgot send me a link yesterday: , They are as fast or maybe slightly faster th…
For Skylake the performance of MULPS and DIVPS is the same as for MULSS and DIVSS.
I think it'll be fair to compare 1 div to 2 muls (given 3 divs of Gibbs vector vs 7 muls of quater…
I'm glad you are at least having fun with it! These are all pretty interesting issues you've broug…
Hi Sorry about the crash! It does sound like it might be an out of memory situation. The data st…
I've had another perforce user ask a similar sort of question. Although I have to admit I'm a bit…
I like the transition between unsure "may be" to confident "it is" :) Is it because you checked t…
At some point it needs to be rotated 180° compared to the starting position. At that point your …
I'm not going to continue this thread until you Last remark, most GPUs require 16 byte alignment …
Before talking about the performance cost I want to get back to this statement of yours: Should I…
I like the transition between unsure "may be" to confident "it is" :) Is it because you checked t…
I like the transition between unsure "may be" to confident "it is" :) Is it because you checked t…
What I should have said is "you cannot represent all angles uniquely". "3 divides may be more expe…
Excuse me? Length of a vector, not lost but assumed to be one. I lost exactly 1 advantage, rota…
At some point it needs to be rotated 180° compared to the starting position. At that point your …
3 divides may be more expensive than 7 multiplies. Show me the empirical evidence, not theoretical…
Yes, and for Gibbs vectors this information is . Because , it equals to , these are versors. So w…
Which is kind of my point. RPs cannot be used to store an orientation which can then be used as a …
[/quote] zero rotation is 0,0,0,1 and full 360 rotation is 0,0,0,-1. There is no axis information…
Quaternions are used for storing an orientation, not just rotations. RPs cannot do this. I'll repe…
ratchetfreak's problem is not a problem for unit quaternions (and Gibbs vectors are of unit lengt…
First off, how do you encode an zero rotation, half a turn or a full turn around a particular axis…
It is not, until proven otherwise. I can't make dot product return 1, if you know how let us know…
It actually is a problem. RPs can be zero unlike quaternions. Other than curiosity, I see no benef…
ratchetfreak's problem is not a problem for unit quaternions (and Gibbs vectors are of unit lengt…
Brian —
Hey everyone, I'm in my senior year at a university working towards a BS in computer information …
is a multi-award winning, CQC-registered, technology-enabled homecare provider focused on disrup…