* *

Main Menu

Recent

Shoutbox

Last 5 Shouts:

Jason G

June 18, 2012, 11:27:38 AM
Could be.  Some say these are hard to get, so it depends mostly or your needs/wants/budget and confidence.  Their waranty & personal history does it for me.  They know it & is why they have the great reputation

Caprio

June 18, 2012, 10:46:08 AM
Hey theres now 2 units available at Jimms Evga GTX 680 2GB GDDR5 for 519? Maybe time to close the deal on one before midsummer?

Jason G

June 16, 2012, 06:12:11 AM
I'd personally stick with an eVGA 680, preferably signiature 2 model... If you can get it.  Best Warranty & parts binning IMO, and the 680 full part is preferable if you can stretch the budget.  My own 680 is a reference Gigabyte one, which runs very well too, though the warranty conditions are tigh

Caprio

June 08, 2012, 05:35:17 PM
Any ideas how easy one could get a 2 slot 680? Would Palit be an option? Or would it be better to get a 670?

Jason G

April 09, 2012, 09:27:36 PM
680 currently doing 6 tasks at a time.. No idea if that's optimal, but it looks cool  ;D

Show 50 latest

Author Topic: SETIv8 Linux Apps  (Read 2971 times)

0 Members and 1 Guest are viewing this topic.

TBar

  • Alpha Testers
  • Member
  • ***
  • Posts: 44
SETIv8 Linux Apps
« on: March 03, 2016, 10:38:21 AM »
CUDA 4.2 App with CPU App tuned to run on Intel CPUs with at least SSSE3.
Includes app_info.xml and CUDA Libraries. Tested in Ubuntu 14.04.
Please leave feedback in this thread; http://setiathome.berkeley.edu/forum_thread.php?id=78881

TBar

  • Alpha Testers
  • Member
  • ***
  • Posts: 44
Re: SETIv8 Linux Apps
« Reply #1 on: September 12, 2016, 07:24:37 AM »
Updated versions of Linux OpenCL Multibeam without the Sanity Check. Compiled and tested in Ubuntu 14.04.5
nVidia r3566 is the standard build, r3567 is modified to be easier on the system and may be slightly faster.
« Last Edit: November 21, 2016, 10:26:27 PM by TBar »

TBar

  • Alpha Testers
  • Member
  • ***
  • Posts: 44
Linux CUDA Special Apps
« Reply #2 on: December 05, 2016, 10:04:48 AM »
These Apps will only work on GPUs that are Compute Capability 3.2 or higher. Check the list of supported GPUs here, https://en.wikipedia.org/wiki/CUDA#GPUs_supported
Compiled & Tested in Ubuntu 14.04.5 with nVidia driver 375.39. The CUDA 8 package contains the AP Apps, MBv8 CPU App, and the source folder used for the compile. Read the README_x41p_zi3t2b.txt file in docs for best use and Library links.
The CUDA 6.5 Special App is for the older Kepler CC 3.5 GPUs that might not work well with CUDA 8.0.
« Last Edit: April 29, 2017, 01:00:47 PM by TBar »

 

Members
Stats
  • Total Posts: 4448
  • Total Topics: 180
  • Online Today: 5
  • Online Ever: 50
  • (June 03, 2013, 12:55:12 PM)
Users Online
Users: 0
Guests: 2
Total: 2
Welcome, Guest. Please login or register.
May 27, 2017, 03:31:23 PM

Login with username, password and session length