I myself wrote:

(...)
I made a quick test with Fred's SetiPerformance (I added manually the cuda42 app) (count 1.0):
x41zc_cuda50: 755 Seconds (12 Minutes, 35 Seconds)
x41zc_cuda42: 784 Seconds (13 Minutes, 4 Seconds)

So it looks like the cuda50 app is faster (at least on my system).
(...)

Like I wrote, I added the cuda42 app to Fred's tool »SetiPerformance«*.
Just for to look if cuda42 or cuda50 is faster on my GT730.
[* with this tool you can test which value of simultaneously WUs give highest performance (RAC) on your GPU.]

cuda50 is fastest on my GT730 (PC system).

If you add an app_config.xml file to the setiathome.berkeley.edu folder with above mentioned (0.04 for <cpu_usage>) BOINC will let run the cuda app which is fastest on your GPU (PC system). The app with highest 'Host/Application details/Average processing rate' GFLOPS value.

But, if you let run WUs also on your Intel HD Graphics (4 compute units) and Intel HD2500 (6 compute units) you should let run (test first) just 1 WU/GPU there.
Look in GPU-Z 'GPU Load' how much the values are.
On my Intel HD Graphics I let run just 1 SETI or AP WU (95-100% GPU Load).

<app_config>
   <app_version>
       <app_name>setiathome_v7</app_name>
       <plan_class>cuda50</plan_class>
       <avg_ncpus>0.04</avg_ncpus>
       <ngpus>0.5</ngpus>
   </app_version>
</app_config>

This app_config.xml file make that 2 SETI WUs/NVidia GPU run simultaneously.
AFAIK, then 1 AP WU/NV GPU and 1 SETI or 1 AP on Intel iGPU automatically.

it gives me error:

7/2/2015 12:31:20 PM | SETI@home | Entry in app_config.xml for app 'setiathome_v7', plan class 'cuda50' doesn't match any app versions
7/2/2015 12:31:20 PM | SETI@home | Entry in app_config.xml for app 'setiathome_v7', plan class 'cuda32' doesn't match any app versions

& this is my app_config.xml:

<app_config>
   <app>
      <name>setiathome_v7</name>
      <gpu_versions>
          <gpu_usage>1.0</gpu_usage>
          <cpu_usage>0.1</cpu_usage>
      </gpu_versions>
    </app>
   <app_version>
       <app_name>setiathome_v7</app_name>
       <plan_class>opencl_intel_gpu_sah</plan_class>
       <avg_ncpus>0.1</avg_ncpus>
       <ngpus>1.0</ngpus>
       <cmdline></cmdline>
   </app_version>
   <app>
      <name>setiathome_v7</name>
      <gpu_versions>
          <gpu_usage>0.5</gpu_usage>
          <cpu_usage>0.1</cpu_usage>
      </gpu_versions>
    </app>
   <app_version>
       <app_name>setiathome_v7</app_name>
       <plan_class>cuda50</plan_class>
       <avg_ncpus>0.1</avg_ncpus>
       <ngpus>0.5</ngpus>
       <cmdline></cmdline>
   </app_version>
   <app_version>
       <app_name>setiathome_v7</app_name>
       <plan_class>cuda42</plan_class>
       <avg_ncpus>0.1</avg_ncpus>
       <ngpus>0.5</ngpus>
   </app_version>
   <app_version>
       <app_name>setiathome_v7</app_name>
       <plan_class>cuda32</plan_class>
       <avg_ncpus>0.1</avg_ncpus>
       <ngpus>0.5</ngpus>
   </app_version>
   <app>
      <name>astropulse_v7</name>
      <gpu_versions>
          <gpu_usage>1.0</gpu_usage>
          <cpu_usage>0.2</cpu_usage>
      </gpu_versions>
    </app>
   <app_version>
       <app_name>astropulse_v7</app_name>
       <plan_class>opencl_intel_gpu_102</plan_class>
       <avg_ncpus>0.2</avg_ncpus>
       <ngpus>1.0</ngpus>
       <cmdline></cmdline>
   </app_version>
   <app>
      <name>astropulse_v7</name>
      <gpu_versions>
          <gpu_usage>1.0</gpu_usage>
          <cpu_usage>0.2</cpu_usage>
      </gpu_versions>
    </app>
   <app_version>
       <app_name>astropulse_v7</app_name>
       <plan_class>opencl_nvidia_100</plan_class>
       <avg_ncpus>0.2</avg_ncpus>
       <ngpus>1.0</ngpus>
       <cmdline></cmdline>
   </app_version>
</app_config>

what is wrong?

---

non-profit org. Play4Life in Zagreb, Croatia, EU

You tried this example of »message 1697683«?

AFAIK, if you let run 1 WU/GPU, not needed an entry. Just for the app which should run 2 WUs/GPU.

So AFAIK the entries of above mentioned message should work...

I guess better it's without cuda22 and cuda23 (IIRC now), a PC get this apps just if very old drivers...

So this entries could/should work...

<app_config>
   <app_version>
       <app_name>setiathome_v7</app_name>
       <plan_class>cuda50</plan_class>
       <avg_ncpus>0.04</avg_ncpus>
       <ngpus>0.5</ngpus>
   </app_version>
   <app_version>
       <app_name>setiathome_v7</app_name>
       <plan_class>cuda42</plan_class>
       <avg_ncpus>0.04</avg_ncpus>
       <ngpus>0.5</ngpus>
   </app_version>
   <app_version>
       <app_name>setiathome_v7</app_name>
       <plan_class>cuda32</plan_class>
       <avg_ncpus>0.04</avg_ncpus>
       <ngpus>0.5</ngpus>
   </app_version>
</app_config>

Just give it a try and report back. :-)

I'm little bit confused...

Your: NVIDIA GeForce GT 730 (2048MB) driver: 353.30 OpenCL: 1.2
My: NVIDIA GeForce GT 730 (1024MB) driver: 347.52 OpenCL: 1.1

AFAIK, OpenCL is a hardware thing not driver thing...
So why your GT730 can do 1.2? ;-)

I have »this« VGA card.
Which card do you have?

---

AFAIK, OpenCL is a hardware thing not driver thing...
So why your GT730 can do 1.2? ;-)

Not quite, OpenCL is a specification. As long as you can supply something to fulfill that specification, and grease the right palms to be certified, then you can put an OpenCL logo on it.

It, hardware, drivers and software, needs to do what's needed, but also go through a process.

---

"Living by the wisdom of computer science doesn't sound so bad after all. And unlike most advice, it's backed up by proofs." -- Algorithms to live by: The computer science of human decisions.

Dirk,

The OpenCL is part of the driver for the card. After Nvidia driver 347.88 they change it from OpenCL 1.1 to 1.2

It will only affect Astropulses at this time in that there was a problem with the "Naming" in the used for running the APs. There are at least 3 different threads about this here in Number Crunching.

The kernal.cl file is in conflict with this new OpenCL 1.2 so it needs to be edited to change the bool2 as per Petri instructions.

If you don't upgrade, it won't affect you (for now)

Looks like the newer apps they want to release will make use of this OpenCl 1.2 so at some point you will need to update those drivers.

But hopefully they will make a new installer that will already have the changes in the .cl when that time comes so you won't have to make them yourself.

You tried this example of »message 1697683«?

AFAIK, if you let run 1 WU/GPU, not needed an entry. Just for the app which should run 2 WUs/GPU.

So AFAIK the entries of above mentioned message should work...

I guess better it's without cuda22 and cuda23 (IIRC now), a PC get this apps just if very old drivers...

So this entries could/should work...

<app_config>
   <app_version>
       <app_name>setiathome_v7</app_name>
       <plan_class>cuda50</plan_class>
       <avg_ncpus>0.04</avg_ncpus>
       <ngpus>0.5</ngpus>
   </app_version>
   <app_version>
       <app_name>setiathome_v7</app_name>
       <plan_class>cuda42</plan_class>
       <avg_ncpus>0.04</avg_ncpus>
       <ngpus>0.5</ngpus>
   </app_version>
   <app_version>
       <app_name>setiathome_v7</app_name>
       <plan_class>cuda32</plan_class>
       <avg_ncpus>0.04</avg_ncpus>
       <ngpus>0.5</ngpus>
   </app_version>
</app_config>

Just give it a try and report back. :-)

tried that...doesn't work...still have notices about not available programs 4 other cuda's...
do I have to add it manually?
:/

I'm little bit confused...

Your: NVIDIA GeForce GT 730 (2048MB) driver: 353.30 OpenCL: 1.2
My: NVIDIA GeForce GT 730 (1024MB) driver: 347.52 OpenCL: 1.1

AFAIK, OpenCL is a hardware thing not driver thing...
So why your GT730 can do 1.2? ;-)

I have »this« VGA card.
Which card do you have?

this one is mine: https://www.asus.com/Graphics_Cards/GT730SL2GD3BRK/

maybe it's about CPU?
here is mine: http://ark.intel.com/products/30797/Intel-Xeon-Processor-X3230-8M-Cache-2_66-GHz-1066-MHz-FSB
d fastest I can get 4: http://www.supermicro.com/products/motherboard/Xeon3000/3000/PDSMA_.cfm (I think)
;)

---

non-profit org. Play4Life in Zagreb, Croatia, EU

This app_config.xml file make that 2 SETI WUs/NVidia GPU run simultaneously.
AFAIK, then 1 AP WU/NV GPU and 1 SETI or 1 AP on Intel iGPU automatically.

it gives me error:

7/2/2015 12:31:20 PM | SETI@home | Entry in app_config.xml for app 'setiathome_v7', plan class 'cuda50' doesn't match any app versions
7/2/2015 12:31:20 PM | SETI@home | Entry in app_config.xml for app 'setiathome_v7', plan class 'cuda32' doesn't match any app versions

what is wrong?

That is not an error, It doesn't say error does it, It is an Informational warning, All it means is the scheduler hasn't sent you any work for the Cuda32 or Cuda50 app versions yet, don't worry about it.

Claggy