@Raistmer

Is the Catalyst 11.12 issue fixed or still present in the ATI builds in this v0.42 Installer?
http://setiweb.ssl.berkeley.edu/beta/forum_thread.php?id=2185

(Looking at the dates and rev. numbers I think it is still present)

Do people need warning about this?

---

 


- ALF - "Find out what you don't do well ..... then don't do it!" :)
 

Is workgroup size of 256+ now a requirement for ATI AP app as well as MB app?

I noticed my HD6370m spits out this error when I try r2399.

Error : Building Program (source, clBuildProgram):main kernels: not OK code -11
"C:\Users\\Temp\OCL760T5.cl", line 1370: error: work group
          size exceeds the maximum default value for the selected device
  __kernel __attribute__((reqd_work_group_size(256, 1, 1))) 

The GPU does have Max work group size: 128. So maybe it is nearing end of usefulness.

If not solved still try
-oclFFT 64 8 128
in command line.

If i`m not mistaken oclfft is available in AP7 only (r2568 and later)

HAL 9000

Try -tune 1 16 8 1 or -tune 1 32 4 1.

---

With each crime and every kindness we birth our future.

@Raistmer

Is the Catalyst 11.12 issue fixed or still present in the ATI builds in this v0.42 Installer?
http://setiweb.ssl.berkeley.edu/beta/forum_thread.php?id=2185

(Looking at the dates and rev. numbers I think it is still present)

Do people need warning about this?

Fix will be available in APv7. Maybe in separate pack or .42a release if any.

Forgot to ask :

Is there a table that lists known optimum/good cmdline_options for certain GPUs on the optimized AP/MB applications ?

So far I set -sbs 256 on all my ATI hardware, but I have no clue what specific settings to use for my new NVidia cards (GTX 750TI & GTX 780)... Not wanting to screw anything up, I left that untouched so far.
I'm normally an AMD guy and just aquired this CUDA 5.0 hardware today ;)

PS.
Installation of v0.42 over existing v0.41 installs worked like a charm, only had to reset <count> to run multiple tasks/GPU.

---

Forgot to ask :

Is there a table that lists known optimum/good cmdline_options for certain GPUs on the optimized AP/MB applications ?

So far I set -sbs 256 on all my ATI hardware, but I have no clue what specific settings to use for my new NVidia cards (GTX 750TI & GTX 780)...
I'm normally an AMD guy and just aquired this CUDA 5.0 hardware today ;)

No, there isn't one ... yet.

Maybe the crowd could crowd-source one?
(But not in this thread, please. Perhaps we could have a crowd-sourcing thread for each of ATI and NV? I don't think the Intel gpus are so variable - but I'm willing to be proved wrong.)

Forgot to ask :

Is there a table that lists known optimum/good cmdline_options for certain GPUs on the optimized AP/MB applications ?

So far I set -sbs 256 on all my ATI hardware, but I have no clue what specific settings to use for my new NVidia cards (GTX 750TI & GTX 780)...
I'm normally an AMD guy and just aquired this CUDA 5.0 hardware today ;)

No, there isn't one ... yet.

Maybe the crowd could crowd-source one?
(But not in this thread, please. Perhaps we could have a crowd-sourcing thread for each of ATI and NV? I don't think the Intel gpus are so variable - but I'm willing to be proved wrong.)

In the last release, were there not some basic recommendations or starting points for the options given in the readme?

---

"Time is simply the mechanism that keeps everything from happening all at once."

Is workgroup size of 256+ now a requirement for ATI AP app as well as MB app?

I noticed my HD6370m spits out this error when I try r2399.

Error : Building Program (source, clBuildProgram):main kernels: not OK code -11
"C:\Users\\Temp\OCL760T5.cl", line 1370: error: work group
          size exceeds the maximum default value for the selected device
  __kernel __attribute__((reqd_work_group_size(256, 1, 1))) 

The GPU does have Max work group size: 128. So maybe it is nearing end of usefulness.

If not solved still try
-oclFFT 64 8 128
in command line.

If i`m not mistaken oclfft is available in AP7 only (r2568 and later)

HAL 9000

Try -tune 1 16 8 1 or -tune 1 32 4 1.

Will give each of these a try when I get home from work and see what happens.

---

SETI@home classic workunits: 93,865 CPU time: 863,447 hours
Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[

Is workgroup size of 256+ now a requirement for ATI AP app as well as MB app?

I noticed my HD6370m spits out this error when I try r2399.

Error : Building Program (source, clBuildProgram):main kernels: not OK code -11
"C:\Users\\Temp\OCL760T5.cl", line 1370: error: work group
          size exceeds the maximum default value for the selected device
  __kernel __attribute__((reqd_work_group_size(256, 1, 1))) 

The GPU does have Max work group size: 128. So maybe it is nearing end of usefulness.

If not solved still try
-oclFFT 64 8 128
in command line.

If i`m not mistaken oclfft is available in AP7 only (r2568 and later)

HAL 9000

Try -tune 1 16 8 1 or -tune 1 32 4 1.

Will give each of these a try when I get home from work and see what happens.

You have "Volunteer tester" tag.
Does your host able to complete current ATi 7.02 tasks on beta?

Is workgroup size of 256+ now a requirement for ATI AP app as well as MB app?

I noticed my HD6370m spits out this error when I try r2399.

Error : Building Program (source, clBuildProgram):main kernels: not OK code -11
"C:\Users\\Temp\OCL760T5.cl", line 1370: error: work group
          size exceeds the maximum default value for the selected device
  __kernel __attribute__((reqd_work_group_size(256, 1, 1))) 

The GPU does have Max work group size: 128. So maybe it is nearing end of usefulness.

If not solved still try
-oclFFT 64 8 128
in command line.

If i`m not mistaken oclfft is available in AP7 only (r2568 and later)

HAL 9000

Try -tune 1 16 8 1 or -tune 1 32 4 1.

Will give each of these a try when I get home from work and see what happens.

You have "Volunteer tester" tag.
Does your host able to complete current ATi 7.02 tasks on beta?

I don't have that machine attached to beta. It might be good idea with current development of AP 7 applications.

---

SETI@home classic workunits: 93,865 CPU time: 863,447 hours
Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[

Is workgroup size of 256+ now a requirement for ATI AP app as well as MB app?

I noticed my HD6370m spits out this error when I try r2399.

Error : Building Program (source, clBuildProgram):main kernels: not OK code -11
"C:\Users\\Temp\OCL760T5.cl", line 1370: error: work group
          size exceeds the maximum default value for the selected device
  __kernel __attribute__((reqd_work_group_size(256, 1, 1))) 

The GPU does have Max work group size: 128. So maybe it is nearing end of usefulness.

If not solved still try
-oclFFT 64 8 128
in command line.

If i`m not mistaken oclfft is available in AP7 only (r2568 and later)

HAL 9000

Try -tune 1 16 8 1 or -tune 1 32 4 1.

Will give each of these a try when I get home from work and see what happens.

You have "Volunteer tester" tag.
Does your host able to complete current ATi 7.02 tasks on beta?

Did not have luck with the settings.
-oclFFT 64 8 128
-tune 1 32 4 1
-tune 1 16 8 1
-tune 2 16 8 1
Settings up Beta now.

---

SETI@home classic workunits: 93,865 CPU time: 863,447 hours
Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[

The error occurred before tune param is in place.

How did you set it up ?

text file ?
Which order ?

I`ve tested 2399 with cards whith WG size of 128 and it worked with tune param.

---

With each crime and every kindness we birth our future.

The error occurred before tune param is in place.

How did you set it up ?

text file ?
Which order ?

I`ve tested 2399 with cards whith WG size of 128 and it worked with tune param.

I modified the ap_cmdline.txt file.
I used line as such.
-hp -tune 1 32 4 1
Using -hp because of slower i3 CPU. I can reorder or remove -hp if it could be issue.

---

SETI@home classic workunits: 93,865 CPU time: 863,447 hours
Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[

The error occurred before tune param is in place.

How did you set it up ?

text file ?
Which order ?

I`ve tested 2399 with cards whith WG size of 128 and it worked with tune param.

I modified the ap_cmdline.txt file.
I used line as such.
-hp -tune 1 32 4 1
Using -hp because of slower i3 CPU. I can reorder or remove -hp if it could be issue.

Try it without hp switch.
If you need it put it after tune.
Also try it in appinfo because it should be earlier in place.

---

With each crime and every kindness we birth our future.

The error occurred before tune param is in place.

How did you set it up ?

text file ?
Which order ?

I`ve tested 2399 with cards whith WG size of 128 and it worked with tune param.

I modified the ap_cmdline.txt file.
I used line as such.
-hp -tune 1 32 4 1
Using -hp because of slower i3 CPU. I can reorder or remove -hp if it could be issue.

Could you post or upload that file: C:\Users\\Temp\OCL760T5.cl

The error occurred before tune param is in place.

How did you set it up ?

text file ?
Which order ?

I`ve tested 2399 with cards whith WG size of 128 and it worked with tune param.

I modified the ap_cmdline.txt file.
I used line as such.
-hp -tune 1 32 4 1
Using -hp because of slower i3 CPU. I can reorder or remove -hp if it could be issue.

Try it without hp switch.
If you need it put it after tune.
Also try it in appinfo because it should be earlier in place.

Looks like same error with <cmdline>-tune 1 32 4 1</cmdline> in app_info.xml and empty .txt file.

---

SETI@home classic workunits: 93,865 CPU time: 863,447 hours
Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[

The error occurred before tune param is in place.

How did you set it up ?

text file ?
Which order ?

I`ve tested 2399 with cards whith WG size of 128 and it worked with tune param.

I modified the ap_cmdline.txt file.
I used line as such.
-hp -tune 1 32 4 1
Using -hp because of slower i3 CPU. I can reorder or remove -hp if it could be issue.

Could you post or upload that file: C:\Users\\Temp\OCL760T5.cl

I had to fight system to get file. It was being deleted very quickly. I managed to capture it and have sent location in PM.

---

SETI@home classic workunits: 93,865 CPU time: 863,447 hours
Join the [url=http://tinyurl.com/8y46zvu]BP6/VP6 User Group[

In the past it was recommended that I use the non-HD5 ATi app over the HD5 version. Is that still the case for my Radeon HD 7970?

I wouldn't have thought so. I only ever used the non-HD5 version for my HD 4850.

We offer the MB application in two different variants, depending on card:
plain - for most HD4xxx owners and those with HD5xxx, HD6xxx cards and
HD7xxx cards who suffer from driver incompatibilities.
HD5 - for most if not all owners of HD5xxx, HD6xxx and HD7xxx GPUs.

---

Soli Deo Gloria

I've installed and up and am up and running but a question that I've not seen answered is it faster or better science or both?

---

-- edit --

Disregard, found it :)

---