| Info | Message |
|---|---|
| 1) Message boards : Questions and problems : App_Config per GPU
Message 89094 Posted 2 Dec 2018 by contalis |
Thanks. Where would you specify which application is assigned to which GPU? Is this something you can add as a feature request? |
| 2) Message boards : Questions and problems : App_Config per GPU
Message 89088 Posted 1 Dec 2018 by contalis |
Is there a way to assign App_Config settings to individual GPUs? For example: <app> <name>Application_Name</name> GPU 0: <gpu_versions> <gpu_usage>.5</gpu_usage> <cpu_usage>.4</cpu_usage> </gpu_versions> GPU 1: <gpu_versions> <gpu_usage>1</gpu_usage> <cpu_usage>1</cpu_usage> </gpu_versions> </app> |
| 3) Message boards : BOINC client : Usage Limits while Computer in Use
Message 83392 Posted 30 Nov 2017 by contalis |
Would it be possible to add a setting to configure different Usage Limits depending on whether the computer is in use or not? For example, when "In Use" the CPU time could be 35% but when no "In Use" the CPU time could be 85%. The reason is that my machines have plenty of spare processing available, so I tend to leave boinc running all the time but at a low CPU time mainly to keep fan noise low. When I walk away from my machine for awhile, I wouldn't care if boinc ramped up. |
| 4) Message boards : Questions and problems : Using integrated GPU with Discrete GPU installed
Message 70973 Posted 21 Jul 2016 by contalis |
Output from CLInfo.log Number of platforms: 2 Platform Profile: FULL_PROFILE Platform Version: OpenCL 1.2 Platform Name: Intel(R) OpenCL Platform Vendor: Intel(R) Corporation Platform Extensions: cl_khr_icd cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_byte_addressable_store cl_khr_spir cl_intel_exec_by_local_thread cl_khr_depth_images cl_khr_3d_image_writes cl_khr_fp64 cl_intel_dx9_media_sharing cl_khr_dx9_media_sharing cl_khr_d3d11_sharing cl_khr_gl_sharing Platform Profile: FULL_PROFILE Platform Version: OpenCL 1.2 CUDA 8.0.0 Platform Name: NVIDIA CUDA Platform Vendor: NVIDIA Corporation Platform Extensions: cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_fp64 cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_d3d9_sharing cl_nv_d3d10_sharing cl_khr_d3d10_sharing cl_nv_d3d11_sharing cl_nv_copy_opts Platform Name: Intel(R) OpenCL Number of devices: 1 Device Type: CL_DEVICE_TYPE_CPU Device ID: 32902 Max compute units: 8 Max work items dimensions: 3 Max work items[0]: 8192 Max work items[1]: 8192 Max work items[2]: 8192 Max work group size: 8192 Preferred vector width char: 1 Preferred vector width short: 1 Preferred vector width int: 1 Preferred vector width long: 1 Preferred vector width float: 1 Preferred vector width double: 1 Max clock frequency: 3500Mhz Address bits: 14757395255531667488 Max memory allocation: 536838144 Image support: Yes Max number of images read arguments: 480 Max number of images write arguments: 480 Max image 2D width: 16384 Max image 2D height: 16384 Max image 3D width: 2048 Max image 3D height: 2048 Max image 3D depth: 2048 Max samplers within kernel: 480 Max size of kernel argument: 3840 Alignment (bits) of base address: 1024 Minimum alignment (bytes) for any datatype: 128 Single precision floating point capability Denorms: Yes Quiet NaNs: Yes Round to nearest even: Yes Round to zero: No Round to +ve and infinity: No IEEE754-2008 fused multiply-add: No Cache type: Read/Write Cache line size: 64 Cache size: 262144 Global memory size: 2147352576 Constant buffer size: 131072 Max number of constant args: 480 Local memory type: Global Local memory size: 32768 Error correction support: 0 Profiling timer resolution: 293 Device endianess: Little Available: Yes Compiler available: Yes Execution capabilities: Execute OpenCL kernels: Yes Execute native function: Yes Queue properties: Out-of-Order: Yes Profiling : Yes Platform ID: 005AF3D0 Name: Intel(R) Xeon(R) CPU E3-1275 v3 @ 3.50GHz Vendor: Intel(R) Corporation Driver version: 4.2.0.148 Profile: FULL_PROFILE Version: OpenCL 1.2 (Build 148) Extensions: cl_khr_icd cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_byte_addressable_store cl_khr_spir cl_intel_exec_by_local_thread cl_khr_depth_images cl_khr_3d_image_writes cl_khr_fp64 cl_intel_dx9_media_sharing cl_khr_dx9_media_sharing cl_khr_d3d11_sharing cl_khr_gl_sharing Platform Name: NVIDIA CUDA Number of devices: 1 Device Type: CL_DEVICE_TYPE_GPU Device ID: 4318 Max compute units: 5 Max work items dimensions: 3 Max work items[0]: 1024 Max work items[1]: 1024 Max work items[2]: 64 Max work group size: 1024 Preferred vector width char: 1 Preferred vector width short: 1 Preferred vector width int: 1 Preferred vector width long: 1 Preferred vector width float: 1 Preferred vector width double: 1 Max clock frequency: 1032Mhz Address bits: 14757395255531667488 Max memory allocation: 805306368 Image support: Yes Max number of images read arguments: 256 Max number of images write arguments: 16 Max image 2D width: 16384 Max image 2D height: 16384 Max image 3D width: 4096 Max image 3D height: 4096 Max image 3D depth: 4096 Max samplers within kernel: 32 Max size of kernel argument: 4352 Alignment (bits) of base address: 4096 Minimum alignment (bytes) for any datatype: 128 Single precision floating point capability Denorms: Yes Quiet NaNs: Yes Round to nearest even: Yes Round to zero: Yes Round to +ve and infinity: Yes IEEE754-2008 fused multiply-add: Yes Cache type: Read/Write Cache line size: 128 Cache size: 81920 Global memory size: 3221225472 Constant buffer size: 65536 Max number of constant args: 9 Local memory type: Scratchpad Local memory size: 49152 Error correction support: 0 Profiling timer resolution: 1000 Device endianess: Little Available: Yes Compiler available: Yes Execution capabilities: Execute OpenCL kernels: Yes Execute native function: No Queue properties: Out-of-Order: Yes Profiling : Yes Platform ID: 029E0468 Name: GeForce GTX 660 Vendor: NVIDIA Corporation Driver version: 368.39 Profile: FULL_PROFILE Version: OpenCL 1.2 CUDA Extensions: cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_fp64 cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_d3d9_sharing cl_nv_d3d10_sharing cl_khr_d3d10_sharing cl_nv_d3d11_sharing cl_nv_copy_opts |
| 5) Message boards : Questions and problems : Using integrated GPU with Discrete GPU installed
Message 70955 Posted 20 Jul 2016 by contalis |
I'm running an Intel E3-1275v3 that has an integrated p4600 GPU. Also installed is an NVIDIA GeForce GTX 660. Without the NVIDIA installed, the P4600 will run GPU work units fine (SETI@home work units.) With the NVIDIA installed, the PC no longer recognizes the P4600 but the BOINC event log displays:"OpenCL CPU: Intel(R) Xeon(R) CPU E3-1275 v3 @ 3.50GHz (OpenCL driver vendor: Intel(R) Corporation, driver version 4.2.0.148, device version OpenCL 1.2 (Build 148))" In a post on the intel support forums, I read that Intel disables the P4600 GPU when the chipset detects a discrete GPU EXCEPT for certain software that might be able to make use of the GPU. Is BOINC one of the softwares that can use the GPU in these situations? Does the message above indicate that BOINC is detecting the P4600?
|
| 6) Message boards : Questions and problems : Use GPU always, CPU when idle
Message 70954 Posted 20 Jul 2016 by contalis |
OK. That makes sense. I tried adjusting the preferences as you suggested, but no luck. I think I'll experiment with leaving the CPU time to some low setting, say 5%. |
| 7) Message boards : Questions and problems : Use GPU always, CPU when idle
Message 70910 Posted 16 Jul 2016 by contalis |
Is it possible to configure BOINC to compute on a specific GPU always, but only use the CPU when idle? Currently, I have my computing settings set to "suspend when computer is in use" which applies to all processors. I see an option to "Suspend GPU computing when in use", but I'm looking for an option to just suspend the CPU. I have a spare GPU in my PC that I'm not using. |
| 8) Message boards : BOINC client : Docker
Message 53328 Posted 26 Mar 2014 by contalis |
This looks like something that might be helpful with BOINC, at least once it matures and possibly supports more OSs: https://www.docker.io/ Docker is an open-source project to easily create lightweight, portable, self-sufficient containers from any application. |
| 9) Message boards : News : New BOINC installer includes VirtualBox
Message 51463 Posted 22 Nov 2013 by contalis |
http://boinc.berkeley.edu/wiki/VirtualBox |
| 10) Message boards : Questions and problems : VirtualBox
Message 51347 Posted 17 Nov 2013 by contalis |
Thanks. Can I suggest that you add http://boinc.berkeley.edu/wiki/VirtualBox to the download page? Also, I assume if I already have VB installed then BOINC will find it so I don't need to download the VB version of BOINC? |
| 11) Message boards : Questions and problems : VirtualBox
Message 51345 Posted 17 Nov 2013 by contalis |
Can someone provide an explanation as to the benefits and any consequences of using VirtualBox with BOINC? For example, I assume VB provides application sandboxing but also uses more system resources. What are the science apps that are using it & why? Or, does BOINC run all apps in the VM for security purposes? Does VB affect access to GPUs? Will it run the screen saver? Is it running a linux distro? |
| 12) Message boards : BOINC Manager : Feature Suggestion: List Projects in Boinc Manager Client
Message 50175 Posted 11 Aug 2013 by contalis |
OK, I guess I've been using boinc with bam so long I never noticed it. What prompted me to suggest this was the new android client. When I installed it, the client asked for a project URL and I didn't see anyway to sync with bam. |
| 13) Message boards : Promotion : Science Museums & QR codes
Message 50169 Posted 10 Aug 2013 by contalis |
Here's my suggestion: Contact your local science museums to request they add a distributed computing exhibit, which would consist of a computer running BOINC. The monitor showing a project screen saver would be an eye-catcher. Then, add some descriptive text about what the computer is doing, along with a QR code to download the android client to a smart phone. The point of the exhibit isn't so much to crunch data itself, but to promote BOINC to visitors, who I assume would be inclined to participating themselves given they are visiting a science museum. Therefore, the computer probably ought to be low power so as not to drive up operating costs. I'm guessing there are some folks on these board who have the creative skills to design such an exhibit, that could be easily built by some enterprising volunteers. |
| 14) Message boards : BOINC Manager : Feature Suggestion: List Projects in Boinc Manager Client
Message 50167 Posted 10 Aug 2013 by contalis |
I'd just like to suggest a feature that I think would make BOINC much more user friendly. Rather than attaching a project using a project URL, provide a list of projects to chose from within the client, and allow to join with a click. I think this would be helpful for new users, particularly on the android client. |
| 15) Message boards : Questions and problems : Unable to connect to localhost after installing 7.0.64
Message 48911 Posted 1 May 2013 by contalis |
Are you running rosetta, by chance? I had the same issue after installing the new version. After uninstall, deleted data folders, reinstalled, synced w bam and quickly suspended rosetta. So far, so good |
| 16) Message boards : Questions and problems : Unable to connect to localhost after installing 7.0.64
Message 48910 Posted 1 May 2013 by contalis |
Are you running rosetta, by chance? I had the same issue after installing the new version. After uninstall, deleted data folders, reinstalled, synced w bam and quickly suspended rosetta. So far, so good |
| 17) Message boards : Web interfaces : Improved Project Communications
Message 48134 Posted 10 Mar 2013 by contalis |
Retention issues have been brought-up in the past. Although BOINC has the ability for projects to send email newsletters, the feature doesn't seem to be used much. Since there are already options to control notification in the BOINC website community preferences, please consider enhancing the notification system to automatically "PUSH" project status updates by default. It could be as simple as emailing the latest "news" post by project staff, or a more complex summary of latest stats and popular message board posts... but automatically generated so project staff doesn't have to take the time. |
| 18) Message boards : BOINC client : Boinc On Vista - Projects Don't Suspend
Message 11423 Posted 30 Jun 2007 by contalis |
Tried version 5.10.8, but still having this problem also. Has the alpha list provided any suggestions? |
| 19) Message boards : BOINC client : Boinc On Vista - Projects Don't Suspend
Message 10574 Posted 31 May 2007 by contalis |
<idle_time_to_run>3</idle_time_to_run> There isn't an entry for <run_if_user_active>, nor do I see anything similar. Activity has been & is set for "Run based on preferences". |
| 20) Message boards : BOINC client : Boinc On Vista - Projects Don't Suspend
Message 10552 Posted 30 May 2007 by contalis |
The clean install didn't solve the problem. BOINC still runs unabated. There is a "global_prefs.xml" in the BOINC folder. This is after a clean install. I won't be able to check-in for a day or two. If you have any further questions, I respond ASAP. |
Copyright © 2024 University of California.
Permission is granted to copy, distribute and/or modify this document
under the terms of the GNU Free Documentation License,
Version 1.2 or any later version published by the Free Software Foundation.