Multiple WU's per GPU

[Pepi]

multibeam WU
I have 5670 and 5770. And both cannot run 2 WU in same time: Boinc show normal progress for first WU and no progress from second WU, But when first WU is finished then second starts. Can you help me
5670 has 512 MB ram
5770 has 1024 MB ram
so I think they have enough memory to process wu. And they are so slow compared to cuda...

you do have -instances_per_device 2 set in your app_info don't you?

Claggy

No I dont have it
I try to chage <count>1</count> to <count>0.5</count> ( and that is not same , right) ?

[Claggy]

multibeam WU
I have 5670 and 5770. And both cannot run 2 WU in same time: Boinc show normal progress for first WU and no progress from second WU, But when first WU is finished then second starts. Can you help me
5670 has 512 MB ram
5770 has 1024 MB ram
so I think they have enough memory to process wu. And they are so slow compared to cuda...

you do have -instances_per_device 2 set in your app_info don't you?

Claggy

No I dont have it
I try to chage <count>1</count> to <count>0.5</count> ( and that is not same , right) ?

You need to set both, read the opening post in the Beta thread:

ATI OpenCL MultiBeam beta testing

Claggy

[Pepi]

Same thing again ( with setup  you say to do)

first result have progress
second doesnot ( show 0,000%)

[Claggy]

Same thing again ( with setup  you say to do)

first result have progress
second doesnot ( show 0,000%)

I've just tried it on my HD5770, works here with count set to 0.5 (so Boinc will start two instances), and  <cmdline>-period_iterations_num 2 -instances_per_device 2</cmdline> set too (so the app will allow two instances to run)

Claggy   

Edit: anyway problems with the Beta ATI MB app should be posted in the Beta thread.

[Claggy]

and here's the two completed Wu's:

resultid=1748608140

<core_client_version>6.10.58</core_client_version>
<![CDATA[
<stderr_txt>
Number of period iterations for PulseFind setted to:2
Number of app instances per device setted to:2
Running on device number: 0
Priority of worker thread raised successfully
Priority of process adjusted successfully, below normal priority class used
OpenCL platform detected: NVIDIA Corporation
OpenCL platform detected: Advanced Micro Devices, Inc.
BOINC assigns 0 device, slots 0 to 1 (including) will be checked
Used slot is 0;   Info : Building Program (clBuildProgram):main kernels: OK code 0

resultid=1748608136

<core_client_version>6.10.58</core_client_version>
<![CDATA[
<stderr_txt>
Number of period iterations for PulseFind setted to:2
Number of app instances per device setted to:2
Running on device number: 0
Priority of worker thread raised successfully
Priority of process adjusted successfully, below normal priority class used
OpenCL platform detected: NVIDIA Corporation
OpenCL platform detected: Advanced Micro Devices, Inc.
BOINC assigns 0 device, slots 0 to 1 (including) will be checked
Used slot is 1;   Info : Building Program (clBuildProgram):main kernels: OK code 0

Please check your own results.

Claggy