• Advertisement
Sign in to follow this  
  • entries
  • comments
  • views

Video Encoding Part 2

Sign in to follow this  


This'll be short as I'm tired, but after my rant the other day about XviD being a pos I got into trying Ogg Theora... however I hit upon a problem pretty quickly; it only wants YUV planes of data, I only have a RGBA interleaved plane of data.

Enter the RGB->YUV conversion code.
I pulled the formula from a website to do it and wrote the C++ todo so pretty quickly.

However, it occured to me this might be a little slow for my needs and frankly this was a good excuse to play with SSE intrinics to see what I could do [grin]

Well, 5 days and about 4 versions of code later I've arrived at a point where my SSE code is now just over 2x as fast as the C++ code [grin]

I'll give more details later, infact I'm considering writing it up as an article, the process I went through to get where I was, which is why I kept pretty detailed note along the way.

Was it a productive use of the last 5 days?
Probably not [grin]
Did I learn alot and enjoy the experiance?
Hell yeah!

I'll say this much, the Intel IA-32 Arch Soft Dev Manuals I got some time ago certainly came in handy when it came to explaining all the SSE functions.

And now, I sleep, I was working on this for about 7h straight today!
Sign in to follow this  

1 Comment

Recommended Comments

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!

Register a new account

Sign in

Already have an account? Sign in here.

Sign In Now

  • Advertisement