Questions and Answers :
GPU applications :
Curious about CPU vs GPU tasks.
Message board moderation
Author | Message |
---|---|
ensignandy Send message Joined: 23 Jan 16 Posts: 30 Credit: 974,656 RAC: 0 |
Hi all, This is my first time posting to the boards here. I have been running SETI for about a week and a bit. I noticed that one day my stats shot through the roof for RAC and then evened out. If I recall correctly, that might have been the day I received a ton of GPU tasks. I am usually running 6 CPU tasks, 1 GPU(+ 1 CPU core) task, and then leaving 1 core available for general use. I have a couple of questions. If I were to only allocate 1 core and 1 GPU to run SETI, would that increase my contribution? Also, if I were to do that, am I processing the same tasks as if I were using my original combination, or am I assigned different tasks based on the hardware(CPU vs GPU) I use? Are certain video card brands (ATI vs. NVidia) or architectures (Geforce, Quadro, Tegra, etc.) better to use for the program? What does it mean when a GPU task shows it as using CUDA 36, 42, or 50? Are there any other programs I can run simultaneously so that one task will credit towards both programs? I would also appreciate any other advice that might help increase my productivity, while also maintaining a semi feasible electricity bill. Thanks for any answers! |
BilBg Send message Joined: 27 May 07 Posts: 3720 Credit: 9,385,827 RAC: 0 |
If I were to only allocate 1 core and 1 GPU to run SETI, would that increase my contribution? No am I assigned different tasks based on the hardware(CPU vs GPU) I use? No, all tasks are the "same", any task can be done on any supported (have app for it) Hardware or Software/OS: http://setiathome.berkeley.edu/apps.php The only exception - vlar tasks are not sent to GPUs for "practical" reasons - GPU can do them but they make too much lag (mouse stutters) Click in "Work unit" column of your tasks list - you will see the same WU (same file) that you do by one app will in many cases be done by different app on another computer (every WU is sent to at least 2 computers) http://setiathome.berkeley.edu/results.php?hostid=7915162 What does it mean when a GPU task shows it as using CUDA 36, 42, or 50? Versions of CUDA (The same way like there are versions of DirectX, OpenGL, OpenCL, ...) https://en.wikipedia.org/wiki/CUDA (CUDA 4.2 app can run on GPU/driver that support CUDA 5.0 like DirectX 9 game can run on system which has DirectX 11) Server try which app will run fastest on your system - should be CUDA 5.0 for your GPU The server will learn in time to send mostly tasks for the best app http://setiathome.berkeley.edu/host_app_versions.php?hostid=7915162 Â - ALF - "Find out what you don't do well ..... then don't do it!" :) Â |
George 254 Send message Joined: 25 Jul 99 Posts: 155 Credit: 16,507,264 RAC: 19 |
I have a little Samsung NP-NC10 (bought off eBay £37) which has: GenuineIntel Intel(R) Atom(TM) CPU N270 @ 1.60GHz [Family 6 Model 28 Stepping 2] (2 processors) running: Microsoft Windows XP Home x86 Edition, Service Pack 3, (05.01.2600.00) The S/N: is ZBAN93AS600298A with other info: Memory 2038.36 MB Cache 512 KB Swap space 3413.11 MB Total disk space 71.04 GB Free Disk Space 52.33 GB My little Samsung (vintage 2009) has a GFLOPS rate of 1.85 whereas my other laptops have GFLOPS rates of around 9-10. (Astropulse GFLOP rates are 40+??? but never mind that). The daily average credit is consistent at 101-103 per day while the other bigger/newer laptops show 200+ -900+ per day. Installing SETIspirit on the Samsung showed their comment "no usable GPU!" (their exclamation mark). Could this explain the slow GFLOPS rate? TIA George |
Jord Send message Joined: 9 Jun 99 Posts: 15184 Credit: 4,362,181 RAC: 3 |
From http://www.notebookcheck.net/Intel-Atom-N270-Notebook-Processor.23718.0.html: The Intel Atom N270 is a typical netbook single core CPU which is clocked at 1.6 GHz. The Atom core was designed for a low power consumption and cheap production. The downside is the relative low performance per Watt (due to the in-order execution) compared to similar clocked Celeron processors, e.g.. Still the integrated Hyper-Threading (the operating system sees the CPU as a dual core CPU) decreases the penalty of the in-order execution a bit. Since it also lacks a general purpose graphics processing unit (GPGPU) it'll crunch data of Seti slowly on the CPU only. |
©2024 University of California
SETI@home and Astropulse are funded by grants from the National Science Foundation, NASA, and donations from SETI@home volunteers. AstroPulse is funded in part by the NSF through grant AST-0307956.