Folding Forum

Version 4 give me an error in Windows 8------

This app can't run on your PC.
To find a version for your PC, check with the software publisher. Please advise.

proteneer wrote:The core will be OpenCL only (and no it won't be hackable to load in CUDA ) mainly for reasons you've witnessed above in people trying to get the CUDA version to work. It's way too much work to enforce people to DL CudaSDK and to get people to download the right version of visual studio.

Just for clarification: are we talking about the upcoming FahCore_v17 (or something even newer) becoming OpenCL only, or this benchmark, or both? And if we're talking about the FahCore, will NVidia cards be able to run it with the NVidia OpenCL implementation, as is the case with this benchmark?

Here's what I'm getting for my system with a Core i5 3570K, HD 7870 GHz edition, and GT 640 at their stock clocks.

http://imgur.com/52wTaTZ

Explicit:
3.97548ns/day

Implicit:
20.7468ns/day

I'm guessing these scores are a tad low given the hardware used. I'm not really sure how the tests work so I'm not sure which GPU was stressed more or which ones were stressed at all.

IvantheDugtrio wrote:Here's what I'm getting for my system with a Core i5 3570K, HD 7870 GHz edition, and GT 640 at their stock clocks.

http://imgur.com/52wTaTZ

Explicit:
3.97548ns/day

Implicit:
20.7468ns/day

I'm guessing these scores are a tad low given the hardware used. I'm not really sure how the tests work so I'm not sure which GPU was stressed more or which ones were stressed at all.

Your screenshot shows you only did -deviceId 0, so that is only one card. From the numbers, that was probably your GT 640.

rjbelans wrote: Your screenshot shows you only did -deviceId 0, so that is only one card. From the numbers, that was probably your GT 640.

What's odd is that usually my 7870 is deviceID 0. In Folding@Home Control It always shows up in slot 0, where the GT 640 shows up in slot 1. Same with GPU-Z where the 7870 is always above the GT 640 in the list.

bruce wrote:Do you plan to port FAHBench to Linux or OSX any time soon?

yes - it would be fairly easy to actually

bruce wrote:

proteneer wrote:

Napoleon wrote:Do I actually have to install the whole CUDA5 Toolkit to try this? I've got Visual Studio Express already, as well as NVidia 310.90 WHQL driver, which does have CUDA5 support.

Unfortunately yes. The CUDA platform does a lot of JIT compilation and hence requires the nvcc compiler. We assume the user has the NVIDIA GPU COMPUTING TOOLKIT 5.0 installed (and hence why its able to find CUFF).

proteneer wrote:Updated the download with some additional libraries - please redownload. Should fix OpenMMOpenCL.dll errors.

Did this ever get resolved? I have 0.4 and without installing the toolkit I ran the http://www.dependencywalker on the OpenMMOpenCL.dll file that came with the benchmark. I don't know if you're still interested in the results.

Code: Select all

Error: At least one required implicit or forwarded dependency was not found.
Error: At least one module has an unresolved import due to a missing export function in an implicitly dependent module.
Error: Modules with different CPU types were found.
Warning: At least one delay-load dependency module was not found.
Warning: At least one module has an unresolved import due to a missing export function in a delay-load dependent module.

Three files could not be found:
CUFFT32_50-35.DLL
MVSCR90.DLL
IESHIMS.DLL

I'm not sure if you ever want to make FAHBench download all it's dependencies, but if you do, I though this might help.

I'll install the toolkit now.

In the meantime, plain vanilla (no overclock):

Code: Select all

C:\Users\bruce\FAHBench_0_4>FAHBench.exe --display-devices --disable-splash
[1] compatible platform(s):
  -- 0 --
  PROFILE = FULL_PROFILE
  VERSION = OpenCL 1.1 CUDA 4.2.1
  NAME = NVIDIA CUDA
  VENDOR = NVIDIA Corporation

(1) device(s) found on platform 0:
  -- 0 --
  DEVICE_NAME = GeForce GTX 650 Ti
  DEVICE_VENDOR = NVIDIA Corporation
  DEVICE_VERSION = OpenCL 1.1 CUDA

Invalid Platform (please use either OpenCL or CUDA)

C:\Users\bruce\FAHBench_0_4>FAHBench.exe -platformId 0 -deviceId 0 -platform OpenCL -precision single --disable-splash
Explicit:
Checking for accuracy...done
5.84779 ns/day
Implicit:
Checking for accuracy...done
38.4752 ns/day

C:\Users\bruce\FAHBench_0_4>FAHBench.exe -platformId 0 -deviceId 0 -platform OpenCL -precision double --disable-splash
Explicit:
Checking for accuracy...done
1.80511 ns/day
Implicit:
Checking for accuracy...done
2.57122 ns/day

Yes this makes sense,

CUFFT comes with CUDA 5.0 - I wanted to avoid packaging a CUFFT for compatibility reasons (each CUFFT is specific to a CUDA release)

Spongebob25 wrote:Version 4 give me an error in Windows 8------

This app can't run on your PC.
To find a version for your PC, check with the software publisher.

Code: Select all

Microsoft Windows [Version 6.2.9200]
(c) 2012 Microsoft Corporation. All rights reserved.

C:\Windows\system32>cd C:\Users\Spongebob\Desktop\FAHBench_0_4

C:\Users\Spongebob\Desktop\FAHBench_0_4>FAHBench.exe --display-devices --disable
-splash
Access is denied.

C:\Users\Spongebob\Desktop\FAHBench_0_4>

Please advise.

Hm that is really strange. You shouldn't need administrator privileges (I don't think anyone else is running as admin).

proteneer wrote:

bruce wrote:Do you plan to port FAHBench to Linux or OSX any time soon?

yes - it would be fairly easy to actually

If you can easily port FAHBench to Linux, Why has it been so hard to produce a GPU client for Linux? Doesn't FAHBench fold?

proteneer wrote:

Spongebob25 wrote:Version 4 give me an error in Windows 8------

This app can't run on your PC.
To find a version for your PC, check with the software publisher.

Code: Select all

Microsoft Windows [Version 6.2.9200]
(c) 2012 Microsoft Corporation. All rights reserved.

C:\Windows\system32>cd C:\Users\Spongebob\Desktop\FAHBench_0_4

C:\Users\Spongebob\Desktop\FAHBench_0_4>FAHBench.exe --display-devices --disable
-splash
Access is denied.

C:\Users\Spongebob\Desktop\FAHBench_0_4>

Please advise.

Hm that is really strange. You shouldn't need administrator privileges (I don't think anyone else is running as admin).

It gives me the same error no matter if I run it with or without admin privileges. Something has changed since ver. 3 that windows 8 does not like.

Spongebob25 wrote:

proteneer wrote:

Spongebob25 wrote:Version 4 give me an error in Windows 8------

This app can't run on your PC.
To find a version for your PC, check with the software publisher.

Code: Select all

Microsoft Windows [Version 6.2.9200]
(c) 2012 Microsoft Corporation. All rights reserved.

C:\Windows\system32>cd C:\Users\Spongebob\Desktop\FAHBench_0_4

C:\Users\Spongebob\Desktop\FAHBench_0_4>FAHBench.exe --display-devices --disable
-splash
Access is denied.

C:\Users\Spongebob\Desktop\FAHBench_0_4>

Please advise.

Hm that is really strange. You shouldn't need administrator privileges (I don't think anyone else is running as admin).

It gives me the same error no matter if I run it with or without admin privileges. Something has changed since ver. 3 that windows 8 does not like.

Weird nothing was changed in the --display-devices part of the code. Can you check permissions on the file/folder it's in - what happens when you don't pass any arguments?

Got it work. Had to delete it and re download it. One issue, running OpenCL on multiple cards only used 75% and 83% of the gpu.

29.9021 ns/day

Preliminary trouble report.

According to popular opinion, drivers 310.90 provide better FAH stability than previous versions so I have been running on them.
When downloading the CUDA TOOLKIT it wanted to install an earlier version and I declined. I did not reboot (yet). Since that time, I've had two GPU timeout aborts, which have been EXTREMELY rare. My plan is to reboot to do any cleanup after installing the Toolkit, then reinstall 310.90 to make sure all updates are compatible with the newer drivers. Then I'll try the CUDA benchmarks again.

NOTE: Installing 310.90 graphics drivers includes something called NVidia Update which probably revises some of the supporting .dlls that TOOLKIT delivered.

OpenCL works fine but now I'm back to having an error running cuda.--OpenMMCUDA.dll:126. I have the tool kit installed and VS.

Is the -platform OpenCL platformId independant? Can I run -deviceId 0,1 -platform OpenCL on a system with 1 AMD and 1 NVidia?

I get:
Explicit:
17.6456 ns/day

Implicit not supported on multiple devices.

AMD/NVidia
Win 7 64
FAHBench 0_4

I also get a no platformId specified.