cancel
Showing results for 
Search instead for 
Did you mean: 

Archives Discussions

zebra123
Journeyman III

Which AMD GPU up to 500€ for use with CodeXL under Ubuntu 12.04

edit: Recent CodeXL release doesn't support Ubuntu 12.04! Need to use Ubuntu 14.04.

Hey there,

I recently worked with Nvidia GPUs and OpenCL, but lately I want to switch to AMD GPUs because of better OpenCL support.

Right now I am interested in using CodeXL for debugging OpenCL code under Ubuntu 12.04.

Therefore I need to purchase an AMD GPU. The budget given to me is up to 500€.

As I want as less trouble as possible, I thougth to check here for an advice which AMD GPU up to 500€ would suite scientific computing under Ubuntu 12.04 using CodeXL best. And if needed I appreciate any information of what I should take into account as well. For me it is important to achieve proper debugging of OpenCL code and to have an up to date GPU.

Looking forward to your advice!

Best regards,

Zebra

0 Likes
3 Replies
dns_on_gpu
Adept II

Scientific computing often means double precision flops (fp64). If that is your case, then

the choice is rather obvious: 280X which is the renamed HD 7970 and costs a lot less

than 0.5K euro.

--

0 Likes
dns_on_gpu
Adept II

with your funds you are limited to gaming gpus

which in general are intentionally crippled in their

double precision compute rates (fp64). both

amd & nvidia do this presumably so as not to undercut

their sales of their "professional" products (firepro

in the case of amd) which sell for much more.

for older cards see how they compare in their fp64 rates

in the link below.

http://www.geeks3d.com/20140305/amd-radeon-and-nvidia-geforce-fp32-fp64-gflops-table-computing/

the amd tahiti core (hd 79xx renamed later as r9 280) the fp64

is quite generous. the new fury cards have lower nominal

fp64 compute rates. the max energy consumption of the tahiti

cores is relatively high, but if it is unlikely that you

will be maxing the gpus 24/7, it may still be acceptable.

i am writing opencl code for the 280x card (and hd 7950=r9 280)

on ubuntu 14.04 and i use the codexl on such system ok.

typical test is a matrix-matrix multiplication. i have written

my own tiled opencl routine and on the 280x i get 530 fp64 gflops

multiplying two 800x800 matrices which is quite decent as my routine

is not limited to powers of 2. this is 3x faster than mkl-dgemm of

intel running on one or more i7-3930k cores. for larger sizes i will

probably get higher gflop rates on the gpu while it drops on the

cpu.

other such tests are to be found in the links below.

http://www.sable.mcgill.ca/publications/techreports/2013-1/sable-tr-2013-1.pdf

http://kmtmt.net/www/docs/rmmcl_sc13_poster.pdf

the old HD 7990 card has two full tahiti cores and you can find

it in amazon.fr for just 550 euros.

if u have the old lga2011 socket system (x79 chipset), it has  40 pci-3

lanes (and cpu permitting)  it can easily handle two 280x cards

so you can interleave computations. this is the route i am taking.

--

0 Likes

Hello,

thanks for the detailed informations!

I think I don't really need the double precison performance.

Therefore the 380 and 390 GPUs are of interest.

390: faster businterface.

380: newer architecture.

edit: Chose the R9 390.

Best regards,

Zebra

0 Likes