cancel
Showing results for 
Search instead for 
Did you mean: 

Archives Discussions

msalko
Journeyman III

Does r9 380x support double precision float?

Hi.

I'm working on a neural network in openCL and I'd like to use double.

Does amd r9 380x support that??

martin.

0 Likes
1 Solution
bridgman
Staff

AFAICS it does support double precision FP.

View solution in original post

0 Likes
5 Replies

Hi. I've added you to the developers white list and moved this message to the OpenCL forum. You can now post in any of the developer forums.

0 Likes
bridgman
Staff

AFAICS it does support double precision FP.

0 Likes
nibal
Challenger

My lowly R9 270 has them:  cl_khr_fp64 cl_amd_fp64. So, a superior r9 380x should have them as well.

BR,

Nikos

0 Likes

Hi,

AMD Radeon Rx 300 series - Wikipedia, the free encyclopedia

The R9 380 has 1/16 double prerformance rate.

There are a few options:

- Get a new workstation gpu, those have good double performance, but also they aren't cheap.

- Get an older GCN gpu: As I remember, the HD7970 was at 1/4 rate.

- Get a fast new gaming card but use big numbers realized with the fast 32bit float instructions and their integer variants: v_mad_i32_i24 for example. Maybe the task can be done with this at the required precision, and if it is faster than the 1/16 rate, it can be a solution. (Note: If you need NAN/INF handling too, then this is a no go.)

thanks.

I'm creating a neural network, and i was considering going for "fake decimal" but i suppose it's too much work for now since i haven't even finished the neural network

0 Likes