Intel GPU compute only mode? - linux

I was wondering if it is possible to force the Intel GPU to be in a "OpenCL-only" mode in a Linux environment, only making OpenCL work.
We already have disabled X server and graphical software, but we would like to completly disable "video work" on this card.

Related

Error: couldn't find RGB GLX visual or fbconfig | Prime on demand Nvidia card

I have a Lenovo G580 computer with intel CPU and a Nvidia 610M GPU. Running Linux Lite OS (Ubuntu based).
I would like to use Nvidia prime to run programs with the GPU.
I installed some packages about Nvidia drivers, version 390 according to this page.
With the Nvidia X Server Settings I can switch to on demand mode. On th UI there is only one settings for prime, no mention about the GPU settings.
My problem is that when the on demand mode is enable, many programs (games and glx debug programs) throw this error : (even without asking to use GPU)
Error: couldn't find RGB GLX visual or fbconfig
I know there is other posts like mine on internet however I can't understand the problem or identify a missing package on my computer. Have you already install prime on this GPU ? I can send logs or system info if needed.

Android studio error running emulator screen shot provided

Keep getting this error and have tried pretty much everything I have found on this website and no luck.SS
It means that the hardware acceleration is either disabled or not available for your cpu.
Most intel chips and amd chips have this feature. All AMD Ryzen cpus have this feature. Check the website for your cpu if it is available.
Now if it is disabled then you can go to bios to enable it.
If you are on amd cpu then it won't work with windows os. Windows os can support only intel cpus for hardware acceleration using haxm or recently on Ryzen cpus with windows 10 latest april update and hyper-v enabled.
If you are using amd cpus before the ryzen series, you can switch to any linux distro which will be fine, at it has kvm for hardware acceleration.

Linux + Windows booting options

What I've done in the past is simply Dual boot, but I would like to not have to reboot my computer in order to switch OS's. Specifically, what I'd like is:
Computer would mainly run Linux,
When I want to play a Windows only game I can switch over to Windows, for that period of time then return to Linux.
Both Linux and Windows need to run up to native in speed.
I'm looking for suggestions in setting this up.
I've looked into Xen, however, I hear that Xen doesn't support 3D graphics? is this accurate. I've also looked into WineD3D and VMGL. However, Wine won't play every game, so I'd still need the Windows VM, and VMGL doesn't seem to work universally either.
I'm running two different machines that I plan to put this setup on:
Laptop:
Intel i7 4720HQ
16GB Ram
NVIDIA GeForce GTX 965M
Desktop:
AMD FX-8350
16GB Ram
EVGA GeForce GTX 960
I just joined and the "Tour" said, don't ask questions that could lead to a discussion than an answer. Anyway, If gaming is your primary goal, have windows as primary boot & dive into linux as VM. Otherwise you need to find a hyper-visor that provides 3D services or pass-through to your actual GPU.
There is a discussion here

Is there any way to create emulator for Linux KVM

I want to test Linux KVM functionality. So to test, Instead of creating the Linux KVM (Hypervisor), I want to setup the emulator for that, which reduces the cost of hardware/resources.
Please let me know if is there any way to create emulator for Linux KVM ?
As you are looking for the emulation then BOCHS is your choice. One of the KVM's requirements is the Virtualization support by the host CPU.
According to the chip support list it emulates AMD Phenom X3 8650 among other AMD and Intel models. The real AMD Phenom X3 8650 does support AMD-V technology. However, I can't tell you to what extent the implementation is complete. Anyway, you could try all emulated AMD models that supports AMD-V and Intel models that supports VT-x and see what happens.
However, do not expect it to be sufficiently fast as you are going to run KVM guest inside KVM host running inside BOCHS emulator.

Can I run CUDA on Intel's integrated graphics processor?

I have a very simple Toshiba Laptop with i3 processor. Also, I do not have any expensive graphics card. In the display settings, I see Intel(HD) Graphics as display adapter. I am planning to learn some cuda programming. But, I am not sure, if I can do that on my laptop as it does not have any nvidia's cuda enabled GPU.
In fact, I doubt, if I even have a GPU o_o
So, I would appreciate if someone can tell me if I can do CUDA programming with the current configuration and if possible also let me know what does Intel(HD) Graphics mean?
At the present time, Intel graphics chips do not support CUDA. It is possible that, in the nearest future, these chips will support OpenCL (which is a standard that is very similar to CUDA), but this is not guaranteed and their current drivers do not support OpenCL either. (There is an Intel OpenCL SDK available, but, at the present time, it does not give you access to the GPU.)
Newest Intel processors (Sandy Bridge) have a GPU integrated into the CPU core. Your processor may be a previous-generation version, in which case "Intel(HD) graphics" is an independent chip.
Portland group have a commercial product called CUDA x86, it is hybrid compiler which creates CUDA C/ C++ code which can either run on GPU or use SIMD on CPU, this is done fully automated without any intervention for the developer. Hope this helps.
Link: http://www.pgroup.com/products/pgiworkstation.htm
If you're interested in learning a language which supports massive parallelism better go for OpenCL since you don't have an NVIDIA GPU. You can run OpenCL on Intel CPUs, but at best you can learn to program SIMDs.
Optimization on CPU and GPU are different. I really don't think you can use Intel card for GPGPU.
Intel HD Graphics is usually the on-CPU graphics chip in newer Core i3/i5/i7 processors.
As far as I know it doesn't support CUDA (which is a proprietary NVidia technology), but OpenCL is supported by NVidia, ATi and Intel.
in 2020 ZLUDA was created which provides CUDA API for Intel GPUs. It is not production ready yet though.

Resources