Recent content by Anteru

Dark theme will come over the long weekend, barring any catastrophic events :) Thanks for the integration, @Rys! If anyone has suggestions how to improve the DB, please don't hesitate to contact me.

FWIW, you can actually run analyze and look at the generated ISA. For a ray-tracing kernel, I observed the following: Instruction encoding with Tonga is longer compared to Hawaii (2152 bytes on Hawaii vs. 2232 bytes on Tonga). This is (as far as I can tell) only due to buffer loads, which are...

Shameless plug, but there is a 3D voxel modelling tool from a company I co-founded: VOTA (see https://volumerics.com/en-us/vota.) Not sure if that is exactly what you had in mind, but to my knowledge at least, it's the only really scalable voxel editor there is (going up to volumes with 2048³...

I believe so. I mean, if all I have to do is to set up one buffer entry for each draw call on the CPU side, and the shader can pull everything out of this buffer, the number of CPU side state changes etc. basically drops down to next to zero. Biggest problem for me for combining many draw calls...

That's my impression, too. Logic blend modes have been in OpenGL, and the "UAV everywhere" just got into OpenGL 4.2, so the hardware definitely is there already. I don't see anything yet which wouldn't run on a GTX480 or so, except maybe the pre-emption stuff. There's some XPS rendering stuff as...

Yeah, I also wonder if someone has found a downloadable version. Lots of lots of snippets showing the iPhone part, but where is the real thing?

Just for the record, on an optimized terrain renderer, the HD5870 reaches 810-840M triangles/second -- this is plain static geometry, no tesselation going on. Which is definitely impressive, as for instance a Quadro FX5800 doesn't go above 350M triangles/second on the same scene. So the...

Well, the 5870 I have is quite loud when running at full throttle -- surely louder than for instance a Quadro FX 5800 at peak. I assume that the GTX 480 will run at a similar noise level, which gives them quite some headroom ;) Of course, in idle, it's silent, but under full load it's clearly...

Let's assume a page is 128x128 pixel in size. It should cover (with stretching, etc.) something like 32x32 pixels on screen (at least.) So if your feedback buffer is 1/32th the resolution, you still get one pixel touched per page (as your original worst-case minified page has 1x1 px then -- an...

Not necessarily if you do the culling in the PM engine as well. You could simply generate for instance 8 triangles/clock, and cull 4, so you still get only 4 triangles per clock that have to be fed into the rasterizers. In case not all PMs are busy, it could be also important to create more 1...

Very nice! With my 8800 GT, I'm getting 430k samples/second :( Moreover, the driver locks up after 50 passes (roughly). This is under Vista x64. OpenCL Platform 0: NVIDIA Corporation OpenCL Device 0: Type = TYPE_GPU OpenCL Device 0: Name = GeForce 8800 GT OpenCL Device 0: Compute units = 14...

Sure, it's easy to add more channels to your virtual texture, and there is nothing which prevents you from including displacement maps. In order to get good performance, you have to do the tesselation/displacement after animating, but this should be no problem.

It could be also because all of the Intel software tools (ICC, VTune, etc.) are aimed towards x86, and they didn't have time to write a new backend for ICC etc. I guess there are also many optimisation programmers at Intel who are adept with the Pentium core, and less so with ARM/whatever. From...

Seems that Larabee has been presented at SC09 with 1006 GFLOPS of SGEMM performance, however it was overclocked for this. Source (in German): http://www.heise.de/newsticker/meldung/SC09-Intel-demonstriert-Larrabee-mit-ueber-1-Teraflops-862305.html "Normal" performance is supposed to be 417 and...

Surely as it's the spritiual successor of the VSA-100 chip, and actually, what we see here ladies and gentlemen ... is the Voodoo Rampage! nVidia has been holding it back until a real emergency, and now is the time.