where can i find a list of stock apps for each os

thanks Richard but i think what i need to know is what os's can run mb on gpu i'm tring linux and can't get gpu mb work on gpu . if linux can't do mb on gpu it would be nice to know so we don't trash work tring to get it to work . sorry just getting a little frustrated here don't like win10 nsa

It's all on that page, but you have to interpret it - and you have to specify which type of GPU. Look for the description in brackets in the version column.

For Windows, all GPUs are supported:

NVidia (cudaxx)
ATI (any flavour of opencl_ati)
Intel (opencl_intel_gpu_sah)

For Linux, only ATI is currently supported as a stock application.

well i just got a AP and it's running so ...... i would just like to know what will run on linux stock and what won't . it would be nice if there was a list of what will run on a platform and what won't . what truely is supported and whats not

It's all on that page.

ok thanks but it's all a little greek to me. so i guess that meens no stock mb app for linux nvidia . thanks for the info Richard . i've only just started on linux so learning at over 60 can be slow thanks again have a good one!

ok thanks but it's all a little greek to me. so i guess that meens no stock mb app for linux nvidia . thanks for the info Richard . i've only just started on linux so learning at over 60 can be slow thanks again have a good one!

It seems you have it figured out now. However here is the applications list with some descriptions for the MB apps & AP apps if you find it helpful.

---

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

Kinda de-greekified. :-)

cuda22, cuda23, cuda32, cuda42, cuda50: different Multibeam CUDA (Compute Unified Device Architecture) versions, running on Nvidia GPUs only, under Windows.
opencl_ati_sah, opencl_ati_cat132, opencl_ati_nocal: different Multibeam OpenCL versions, running on ATI/AMD GPUs only under Windows. SAH = normal app; cat132 = requires Catalysts 13.2 or above to run; nocal = version for AMD GPUs that do no longer support and detect CAL (Compute Abstraction Layer).
opencl_ati5_sah, opencl_ati5_cat132, opencl_ati5_nocal: different Multibeam OpenCL versions as above, but for ATI HD5xxx GPUs and better.
opencl_intel_gpu_sah: OpenCL for the built in HD Graphics Intel GPU.
opencl_ati_linux, opencl_ati_linux_nocal: Multibeam OpenCL application for ATI/AMD GPUs under Linux.
opencl_ati5_linux, opencl_ati5_linux_nocal: Multibeam OpenCL application for HD 5xxx and better ATI/AMD GPUs under Linux.
opencl_ati_mac, opencl_ati5_mac, opencl_ati5zc_mac: Multibeam OpenCL application for ATI/AMD GPUs running on Macintosh computers. ATI5CZ = newest (2015) version of the application).

sse, sse2, sse3: different Astropulse applications running on the CPU, using Streaming SimD Extensions, availavle dependent on CPU make and model.
cuda_opencl_100, cuda_opencl_cc1, opencl_nvidia_100, opencl_nvidia_cc1: CUDA and OpenCL versions of the Astropulse application running on the Nvidia GPU under Windows. (*)
opencl_ati_100: Astropulse OpenCL application for ATI/AMD GPUs running under Windows.
opencl_intel_gpu_102: Astropulse OpenCL application for Intel HD Graphics GPUs running under Windows.
opencl_intel_gpu_mac, opencl_nvidia_mac: Astropulse OpenCL application for Intel HD Graphics and Nvidia GPUs running on a Macintosh computer.

armv6-vfp, armv6-neon, armv7-vfpv3, armv7-vfpv3d16, armv7-vfpv4: different Multibeam applications running on ARM CPUs, depending on CPU capabilities.
armv6-vfp-nopie, armv6-neon-nopie, armv7-vfpv3-nopie, armv7-vfpv3d16-nopie, armv7-vfpv4-nopie: different Multibeam applications running on ARM CPUs, depending on CPU capabilities on Android v5 and above that require use of PIE (Position Independent Executables).

(*) Not a clue what CC1 is, anyone?

---

Is it like Raistmer said?

just different plan class. Same binary.

---

Probably, but I meant more, what does it stand for?

---

Only Raistmer knows for sure.

Could pop him a PM and ask?

Most probably Compute Capability 1.0, for the older cards that cannot do higher CCs.

---

yes. In beta we found that different compute capability requires different limitations by supported drivers. Hence separate plan classes needed. They provide same binary but check against different allowable driver versions ranges at task allocation.