Faster Incoherent Ray Traversal Using 8-Wide AVX Instruction

Must read and other references.
Post Reply
voxelium
Posts: 15
Joined: Fri Apr 27, 2012 11:10 am
Contact:
Contact voxelium

Faster Incoherent Ray Traversal Using 8-Wide AVX Instruction

Postby voxelium » Thu Sep 05, 2013 10:59 am

http://voxelium.wordpress.com/2013/08/14/faster-incoherent-ray-traversal-using-8-wide-avx-instructions/

Unfortunately the improvement is small compared to SSE, but at least it's consistently faster and easy to implement.
Top
spectral
Posts: 382
Joined: Wed Nov 30, 2011 2:27 pm
Contact:
Contact spectral

Re: Faster Incoherent Ray Traversal Using 8-Wide AVX Instruc

Postby spectral » Fri Sep 06, 2013 7:51 am

Looks nice,

Will go deeper... but do you think that such strategy can also help on the GPU ?
Spectral
OMPF 2 global moderator
Top
voxelium
Posts: 15
Joined: Fri Apr 27, 2012 11:10 am
Contact:
Contact voxelium

Re: Faster Incoherent Ray Traversal Using 8-Wide AVX Instruc

Postby voxelium » Fri Sep 06, 2013 10:58 am

Thanks! Not sure about the GPU, I think it's worth investigating, but going beyond 8-way branching is probably not a good idea.
Top
Post Reply

Return to “Links & Papers”

Who is online

Users browsing this forum: No registered users and 8 guests