There are many people running 8xAMD GPUs in a box (or more), a couple of examples: - http://luxmark.info/node/836 - http://luxmark.info/node/1398...
LuxMark v3.1 has been released: http://www.luxrender.net/forum/viewtopic.php?f=34&t=12359 What is new in v3.1 ? - The new LuxRender v1.5 render...
The FireRender AMD web page: http://developer.amd.com/tools-and-sdks/graphics-development/firepro-sdk/amd-firerender-technology/
A couple of video, this is FireRender in action at SIGGRAPH 2015: https://twitter.com/AntoineReymond/status/631521617772855297 And this is...
May be but the very first requirement is to understand what is different from a 4870/5870/7970/290X (i.e AMD GPUs I have directly tested and have...
It is a very strange result, they have scaled the number of ALUs but not some other kind of resources (cache size, etc.). It looks like an hint of...
You can use the "Search results" link available on the upper-right of the web page (note: it is available only after the login):...
LuxMark v3.1beta1 has been released and it is available here: http://www.luxrender.net/forum/viewtopic.php?f=34&t=12223 This version includes...
From the paper: "Many OpenCL implementations are not robust Many of the configurations we tested exhibit basic compiler bugs (see Figure 1),...
Many years ago, I had a 68000, a Blitter, a Copper and some other co-processors too. Today I have a i7, a PCIe extender and many GPUs. The...
Exactly, I don't understand why Xeon Phi can not run OpenCL as well as any other GPU. ISPC works well (at least in my field of interest) but who...
Nope but no ray tracer would render such effect.
The definition of "accurate" really depend on the field of application and it may be enough or not but, for instance, Advanced Concepts Team of...
Developing a cross platform/vendor benchmark based on a proprietary API doesn't sound like a good idea to me. To be sincere, I find hard to see...
NVIDIA seems to have fixed the recent issues with the last driver release. LuxMark v3.0 has been:...
Unfortunately, I don't have a NVIDIA GPU to do a test but others LuxRender developers and users are using NVIDIA GPUs (GTX560, GTX780, GTX970 to...
LuxRender has 3 rendering modes: - CPU-only (aka C++ mode in LuxMark): it uses only the CPU and the CPU ram. - Hybrid CPU/OpenCL: it uses the...
Not really, the differences between v1.1 and v1.2 are really microscopic. Yes. OpenCL v2.0 is a totally different topic: for performance (in...
Yup, it should be (i.e. it is placed wherever Boost library thinks is the temporary directory for your OS) Yes, you can use 3 types of cache:...
LuxMark includes a reference (i.e. noise free) image of the rendering used for a comparison with your result. The benchmark runs only for 2...
Ah, sorry, I forgot NVIDIA is OpenCL v1.1 only and it is not able to run any executable compiled with newer OpenCL SDKs. I recompiled the binary...
Introduction LuxMark is a OpenCL cross-platform benchmark tool and has become, over past years, one of the most used (if not the most used)...
It is going to be pretty much awesome for anyone not writing 10 lines long kernels. I can easily predict huge LuxMark scores and good results...
About the "render fast" topics, the first and major decision cross-roads is if you are going to use GPU rendering engine like VRay RT (OpenCL),...
LuxMark has a several thousands of line long kernel, how big is Folding@home kernel ? You are probably comparing two very different kind of...
NVIDIA is back where it was before the release of CUDA 4.0. It would be interesting to understand if it is the result of some LuxMark specific...
I agree, it would be very useful for developers and they could sell also few cards for some niche markets like rendering, etc. However they...
32bit Vs. 64bit related problem :?:
I have uploaded a demo video of LuxVR working with Oculus Rift HMD (http://www.oculusvr.com): http://www.youtube.com/watch?v=QiW24tahE7I P.S....
Tim, first of all, thank you for sharing your thoughts. So do you claim a RenderScript kernel will perform well universally ? I'm a bit...
It should work if you install latest Intel drivers. Try to run LuxMark, it will show you a CPU device, the Intel GPU device and any number of...
HD5800 chips my have the support full double precision but they dont' have the support OpenCL compliant double precision. For instance, some...
cl_amd_fp64 inludes the support only for few basic math operators (like *, /, +, - and not very much more). It was introduced to expose the...
OpenCL has OpenCL/OpenGL and OpenCL/DX11 interoperability extensions for this kind problems. I'm pretty sure CUDA has something similar.
cl_amd_fp64 is a subset (i.e. include basic math operations and not much more) of cl_khr_fp64; it was introduced by AMD in order to run OpenCL...
Probably yes, if you factor the software development time/cost :idea:
If you have the software written with a data parallel model (like with OpenCL Kernels), the compiler can easily generate the code to keep the...
SGI had a line of workstations too: I remember the personal Iris 35. I guess old SGI trademarks are not valid anymore, there is a software named...
I'm looking forward to this feature, it will make the task of passing complex data structures to GPUs soooo much easier.
I have collected some of my old OpenCL demo at http://code.google.com/p/ocltoys. It is a collection of Computer Graphics and Ray Tracing related...
I accept bets that a 28nm Fermi would out perform, in GPGPU tasks, Kepler by miles. I'm old enough to know that old times were just horrible :wink:
It is somewhat an old idea, probably based on the fact that ray/triangles intersection algorithm is O(log triangles_count). I'm not sure if this...
I have uploaded a video about an ambitious project I'm working on at http://youtu.be/JrvyjqYX6o8 LuxVR is a LuxRender project to introduce the...
I should receive soon an Arndale board: http://www.howchip.com/shop/content.php?co_id=ArndaleBoard_en Mali OpenCL should works there too and the...
Can we debunk this myth ? All Kepler family lacks of good performance in most FP32 GPGPU applications. Just try to run Blender Cycles or Octane...
It may be still an installation-only issue. You could try to just create a "/etc/OpenCL/vendors/arm.icd" file; the content must be just one line...
Try to check /etc/OpenCL/vendors directory: there should a text file with the name of the library (i.e. driver) the ICD has to load.
ARM has released OpenCL SDK for Mali-T600 family few days ago: http://malideveloper.arm.com/develop-for-mali/sdks/mali-opencl-sdk/ Isn't Nexus 10...
Amiga had the OS GUI written around this concept: you had multiple screens and you were able to pan up/down or to swap them. Copper was an mazing...
The major new feature, I would like to use, is OpenCL 1.1 float3 data type. I can not think to anything else in 1.1/1.2 that could make a...