Donate To Seti@HomeSeti@Home optimized science apps and information
 
Welcome, Guest. Please login or register.
24 Jul 2014, 06:40:01 am

Login with username, password and session length
 
» Home
» Forums
» Downloads
» FAQ
» News

» Search site
 
 
 
If you've registered already but never got your activation email, please click here.
 
 
Seti@Home optimized science apps and information  |  Optimized Seti@Home apps  |  Windows  |  GPU crunching  |  Topic: AP6 r1363 for GPU 0 Members and 0 Guests are viewing this topic. « previous next »
Pages: [1] Go Down Print
Author Topic: AP6 r1363 for GPU  (Read 6025 times)
Raistmer
Working Code Wizard
Volunteer Developer
Knight who says 'Ni!'
*****
Offline Offline

Posts: 12238



AP6 r1363 for GPU
« on: 16 Jul 2012, 07:16:12 am »

New switch added:
-initial_ffa_sleep N M
where N - number of ms to sleep in short PC-FFA, M - number of ms to sleep in large FFA. This sleep will occur before polling for event loop in -use_sleep case (and this sleep independed from -use-sleep switch)

Recommended usage:

1) do test run with -v 2 -use_sleep options.
2) look into stderr.txt for usual sleeping times for short and large FFA (they will differ considerably)
3) Enter those usual values (or those -1ms) into this new switch parameters fialed.
4) additional run with this param "+" -v 2 -use_sleep can be done to check if sleep loop times now much smaller (1-2ms). Then -use_sleep can be omitted at all.

Take care, this switch requires exactly 2 params (2 integer numbers separated with space), not 1.

* AP6_r1363_GPU.7z (1756.7 KB - downloaded 541 times.)
Logged
Raistmer
Working Code Wizard
Volunteer Developer
Knight who says 'Ni!'
*****
Offline Offline

Posts: 12238



Re: AP6 r1363 for GPU
« Reply #1 on: 19 Jul 2012, 02:57:43 am »

Bench for GTX 260 + Core2Duo 6420 (Conroe), CPU idle, OS Windows Server 2003 x64, driver 263.06 attached; dependence from unroll param. More will come later.

* GHANI-20120718-1959-benchAP.rar (8.34 KB - downloaded 103 times.)
Logged
Fredericx51
Knight o' The Round Table
***
Offline Offline

Posts: 207


Knight Who Says Ni N!


Re: AP6 r1363 for GPU
« Reply #2 on: 24 Jul 2012, 09:24:30 am »

Bench for GTX 260 + Core2Duo 6420 (Conroe), CPU idle, OS Windows Server 2003 x64, driver 263.06 attached; dependence from unroll param. More will come later.

Is this new switch for all (NVidia & AMD?ATI) devices/GPUs or NVidia only.
Logged
Raistmer
Working Code Wizard
Volunteer Developer
Knight who says 'Ni!'
*****
Offline Offline

Posts: 12238



Re: AP6 r1363 for GPU
« Reply #3 on: 24 Jul 2012, 12:08:46 pm »

It's for all GPU AP builds.
[But how helpful it would be for particular vendor/device/driver config - need to test in each particular case]
Logged
skildude
Knight o' The Round Table
***
Offline Offline

Posts: 168


Re: AP6 r1363 for GPU
« Reply #4 on: 25 Jul 2012, 11:16:27 am »

Works very well on my 7970.  many non zeroed WU's completing in less than an hour.

No errors to report.
Logged
Fredericx51
Knight o' The Round Table
***
Offline Offline

Posts: 207


Knight Who Says Ni N!


Re: AP6 r1363 for GPU
« Reply #5 on: 01 Aug 2012, 04:39:47 pm »

It's for all GPU AP builds.
[But how helpful it would be for particular vendor/device/driver config - need to test in each particular case]


Raistmer, do you have  AMD/ATI  5000/6000/7000 series of GPU(s), since you're the man, doing most of the coding, testing, IIRC,  Jason Gee; Richard Haselgrove
and  forgot somebody, too but you're putting a lot of time in this project and should
have the necessary equipment, IMHO.

If not, you're have to get one, I think and willing to pay for one or part of?!  Just PM  Roll Eyes
(Also have a HD4850 & HD5770 lying and not using atm. cause my VISTA rig has
strange failliars, could be PSU related cause it's only 350Watt).

Hope, you don't mind asking this,
Fredericx51.
Logged
Raistmer
Working Code Wizard
Volunteer Developer
Knight who says 'Ni!'
*****
Offline Offline

Posts: 12238



Re: AP6 r1363 for GPU
« Reply #6 on: 01 Aug 2012, 04:58:28 pm »

Raistmer, do you have  AMD/ATI  5000/6000/7000 series of GPU(s),
Currently I have HD6950 installed in one host, bought on SETI project members donations and GTX 260, donated too and sent by Mike to me, installed in another host.
Also I have own HD4870, GSO9600, GT9500, 8600 (or8500?), but not installed. I bought PCI->PCI-e adaptor on eBay, tested it on some AMD64 host and perhaps will install it + some of these cards into another AMD64 host, Winchester based one.
But I currently develop on C-60 based netbook so most of debugging and testing going there (it's AMD's APU: CPU+OpenCL-capable GPU in single chip). All other architectures covered by our excellent alpha testers.
Logged
Morten
Knight o' The Round Table
***
Offline Offline

Posts: 165


Re: AP6 r1363 for GPU
« Reply #7 on: 02 Aug 2012, 09:14:57 am »

Hi Raistmer,

What would be the correct setting based on these values:?

In FFA -2048 before main loop buffer freeing
Awaited 40 ms for completion
PC_inner_ffa result is: 0
Awaited 27 ms for completion
PC_inner_ffa result is: 0
Awaited 27 ms for completion
PC_inner_ffa result is: 0
Awaited 26 ms for completion
PC_inner_ffa result is: 0
Before FFA buffer release, end of FFA -2048
In FFA 2048 before main loop buffer freeing
Awaited 38 ms for completion
PC_inner_ffa result is: 0
Awaited 28 ms for completion
PC_inner_ffa result is: 0
Awaited 27 ms for completion
PC_inner_ffa result is: 0
Awaited 26 ms for completion
PC_inner_ffa result is: 0
Before FFA buffer release, end of FFA 2048
In FFA -2064 before main loop buffer freeing
Awaited 40 ms for completion
PC_inner_ffa result is: 0
Awaited 28 ms for completion
PC_inner_ffa result is: 0
Awaited 27 ms for completion
PC_inner_ffa result is: 0
Awaited 26 ms for completion
PC_inner_ffa result is: 0
Before FFA buffer release, end of FFA -2064
In FFA 2064 before main loop buffer freeing


-initial_ffa_sleep 26 -2064 ?
or
-initial_ffa_sleep 40 2048 ?

As the crunching of the task progresses, these values are increasing, meaning that the negative and positive value gets larger, as well as the "Awaited xx ms" positive value.

At 50% crunched it's like this:
Before FFA buffer release, end of FFA -8448
In FFA 8448 before main loop buffer freeing
Awaited 120 ms for completion
PC_inner_ffa result is: 0
Awaited 108 ms for completion
PC_inner_ffa result is: 0
Awaited 106 ms for completion
PC_inner_ffa result is: 0
Awaited 104 ms for completion
PC_inner_ffa result is: 0
Awaited 103 ms for completion
PC_inner_ffa result is: 0
Awaited 100 ms for completion
PC_inner_ffa result is: 0
Awaited 96 ms for completion
PC_inner_ffa result is: 0
Awaited 95 ms for completion
PC_inner_ffa result is: 0
Awaited 95 ms for completion
PC_inner_ffa result is: 0
Awaited 92 ms for completion
PC_inner_ffa result is: 0
Awaited 89 ms for completion
PC_inner_ffa result is: 0
Awaited 88 ms for completion
PC_inner_ffa result is: 0
Awaited 88 ms for completion
PC_inner_ffa result is: 0
Awaited 87 ms for completion
PC_inner_ffa result is: 0
Awaited 56 ms for completion
PC_inner_ffa result is: 0
Before FFA buffer release, end of FFA 8448
Logged
Raistmer
Working Code Wizard
Volunteer Developer
Knight who says 'Ni!'
*****
Offline Offline

Posts: 12238



Re: AP6 r1363 for GPU
« Reply #8 on: 02 Aug 2012, 02:14:35 pm »

You can try -initial_ffa_sleep 26 95 then. And see if it saves any CPU time and how much it will increase elapsed time.

EDIT: and positive/negative number that increases over time is DM value, should be ignored for this particular purpose, it's not a time count.
« Last Edit: 02 Aug 2012, 03:04:38 pm by Raistmer » Logged
Zeus Fab3r
Squire
*
Offline Offline

Posts: 41



Re: AP6 r1363 for GPU
« Reply #9 on: 18 Nov 2012, 04:28:51 pm »

Hi Raistmer and everybody else,

I've decided to get back to AP crunching on my GTX260 in hope to bypass current server issues (and limits), so I have few questions:

- Is r1363 latest release?
- Do I need -initial_ffa_sleep N M switch to run this app?
- Can I use my old cmdline params
Code:
<cmdline>-ffa_block 6144 -ffa_block_fetch 1536 -unroll 10 -instances_per_device 1 -no_cpu_lock</cmdline>
/edit (I just saw from Raistmer's r1316 opening post, that I don't need -no cpu lock switch)
- In above mentioned post there is app_info section for ATI GPU's in which I couldn't find file_info and file_ref parts for AstroPulse_Kernels_r1363.cl file. I used to have these when I was running r521, so are they obsolete, or not needed in ATI setup?
- Can I stay with 266.58 drivers? (I don't like high cpu usage because I crunch AP wus on all four cores)

Thanks in advance Smiley
« Last Edit: 18 Nov 2012, 04:30:52 pm by Zeus Fab3r » Logged
Mike
Alpha Tester
Knight who says 'Ni!'
***
Offline Offline

Posts: 1529



Re: AP6 r1363 for GPU
« Reply #10 on: 18 Nov 2012, 04:47:34 pm »

Its latest official release yes.
And you can still  use old cmdline params.
Logged
Zeus Fab3r
Squire
*
Offline Offline

Posts: 41



Re: AP6 r1363 for GPU
« Reply #11 on: 18 Nov 2012, 05:19:19 pm »

Is this OK?

    <app>
        <name>astropulse_v6</name>
    </app>
    <file_info>
        <name>AP6_win_x86_SSE2_OpenCL_NV_r1363.exe</name>
        <executable/>
    </file_info>
    <file_info>
        <name>AstroPulse_Kernels_r1363.cl</name>
        <executable/>
    </file_info>
    <app_version>
        <app_name>astropulse_v6</app_name>
      <version_num>604</version_num>
      <avg_ncpus>0.04</avg_ncpus>
      <max_ncpus>0.20</max_ncpus>
      <plan_class>cuda</plan_class>
      <flops>475000000000</flops>
   <cmdline>-ffa_block 6144 -ffa_block_fetch 1536 -unroll 10 -instances_per_device 1</cmdline>
      <file_ref>
            <file_name>AP6_win_x86_SSE2_OpenCL_NV_r1363.exe</file_name>           
     <main_program/>
        </file_ref>
   <file_ref>
            <file_name>AstroPulse_Kernels_r1363.cl</file_name>           
     <copy_file/>
        </file_ref>
   <coproc>
        <type>CUDA</type>
        <count>1</count>
      </coproc>
    </app_version>
Logged
Mike
Alpha Tester
Knight who says 'Ni!'
***
Offline Offline

Posts: 1529



Re: AP6 r1363 for GPU
« Reply #12 on: 18 Nov 2012, 05:36:31 pm »

It should work.
But you dont need to mention the cl file any longer.
Evenso _instance_per_device 1 is needless.
Count 1 is enough now.

Mine looks like this.

<app>
       <name>astropulse_v6</name>
    </app>
    <file_info>
         <name>AP6_win_x86_SSE2_OpenCL_ATI_r1363.exe</name>
    <executable/>
    </file_info>
   <file_info>
         <name>ap_cmdline.txt</name>
   </file_info>
    <app_version>
        <app_name>astropulse_v6</app_name>
       <version_num>601</version_num>
        <avg_ncpus>0.04</avg_ncpus>
        <max_ncpus>0.2</max_ncpus>
        <plan_class>ati13ati</plan_class>
    <coproc>
      <type>ATI</type>
        <count>0.5</count>
    </coproc>
    <file_ref>
        <file_name>AP6_win_x86_SSE2_OpenCL_ATI_r1363.exe</file_name>
    <main_program/>
    </file_ref>
    <file_ref>
        <file_name>ap_cmdline.txt</file_name>
    </file_ref>
    </app_version>

ap_cmdline.txt includes the params.

Mike
Logged
Zeus Fab3r
Squire
*
Offline Offline

Posts: 41



Re: AP6 r1363 for GPU
« Reply #13 on: 18 Nov 2012, 06:01:14 pm »

It's working ! Thanks.
Still I'd like to know about -initial_ffa_sleep N M switch and which is recomended driver for my old GTX260  Wink

edit: Here is my first result with new app. Should I be worried about infos and warnings about opening some binary kernel files? I've noticed that those files were created in my data folder.
« Last Edit: 18 Nov 2012, 08:04:15 pm by Zeus Fab3r » Logged
Raistmer
Working Code Wizard
Volunteer Developer
Knight who says 'Ni!'
*****
Offline Offline

Posts: 12238



Re: AP6 r1363 for GPU
« Reply #14 on: 19 Nov 2012, 03:19:35 am »

If they were created - no reason to worry.
-initial_ffa_sleep N M is experimental switch provided in case someone finds it useful for own host.
Recommended driver (for OpenCL NV app) is: 263.06
Logged
Pages: [1] Go Up Print 
Seti@Home optimized science apps and information  |  Optimized Seti@Home apps  |  Windows  |  GPU crunching  |  Topic: AP6 r1363 for GPU « previous next »
Jump to:  


Quote!
Everything takes longer than you think.
- Murphy's Law

 
Site Statistics
Total Members:96
Total Posts:54,357
Total Topics:1,531
Downloads
..Some PHP stuff ToDo
Pages served
Today:963
Total:19,605,428
(since 6/26/2006)
Latest Member:
Just Will Lite
 
 
Seti@Home optimized science apps and information | Powered by Enigma 2.0 (RC1).
© 2003-2014, LSP Dev Team. All Rights Reserved.
Seti@Home optimized science apps and information Forums | Powered by SMF.
© 2005, Simple Machines LLC. All Rights Reserved.
Powered by MySQL Powered by PHP Valid XHTML 1.0! Valid CSS!