Beyond3D Forum

mhouston · 19-Aug-2007, 01:52

Most slide decks are now posted:

http://www.gpgpu.org/s2007/

You can also buy the audio+slides from the SIGGRAPH course (and all SIGGRAPH presentations as well) at http://encore.siggraph.org.

Humus · 19-Aug-2007, 02:35

I've only read the introduction so far, but this looks like very cool material!

santyhammer · 29-Aug-2007, 01:27

I'm interestered in the 12. GPGPU and Raytracing(Jens Krueger), but not avail! Any idea if is going to be available or when pls?

Thanks for collecting the papers and putting the links there btw, very interesting reads as usually!

CouldntResist · 29-Aug-2007, 01:45

What is that "CAL API", mentioned in "AMD CTM Performance"?

Jawed · 29-Aug-2007, 02:11

Compute Abstraction Layer, to abstract devices - i.e. R580 and R600 would be programmed the same way. Though, ahem, you might tweak the HLSL shader code to produce assembly code optimised for a specific GPU, or for that GPU's branching characteristics.

It supports multiple GPUs transparently too and unifies the memory space (including the CPU's memory). See the CTM Overview presentation.

Jawed

mhouston · 29-Aug-2007, 05:35

CAL actually goes a little beyond that. In theory, it could also drive a multi-core with the same data parallel abstraction. The better way to think of CAL vs HAL is that they split the higher level CTM stuff into CAL and are making it slightly more higher level and general, and HAL now represents the hardware abstraction for different hardware underneath (i.e. it handles the actual command buffer submission, required state setting, and ELF handoff to the hardware).

As for Jens, I'll harass him again for slides. The raytracing and GPGPU talk was mainly an overview of the different options available based on previous published work, like the Horn et al. I3D paper on kd-trees, or some of the new BVH stuff, as well as more blurry lines between raster and raytrace.

Rufus · 01-Sep-2007, 17:49

Quote:

Originally Posted by santyhammer

I'm interestered in the 12. GPGPU and Raytracing(Jens Krueger), but not avail! Any idea if is going to be available or when pls?

All of the papers are available directly from ACM:

http://portal.acm.org/toc.cfm?id=128...184618#1281641

purpledog · 05-Sep-2007, 17:00

In one of those slides (don't remember which one) I especially liked this idea:

"rendering is a killer app for gpgpu"

Funny really, you create some hardware to do graphics, then you stuck a general purpose api on top of it, then you realize "wait, I can go graphics with that!".

I does make sense thought.

19-Aug-2007, 02:35	#2
Humus Crazy coder Join Date: Feb 2002 Location: Stockholm, Sweden Posts: 3,216	I've only read the introduction so far, but this looks like very cool material! __________________ [ Visit my site ] I speak for myself and only myself.

Thread Tools
Show Printable Version Email this Page
Display Modes
Linear Mode Switch to Hybrid Mode Switch to Threaded Mode

19-Aug-2007, 01:52	#1
mhouston A little of this and that Join Date: Oct 2005 Location: Cupertino Posts: 342	SIGGRAPH GPGPU supplemental course material is up Most slide decks are now posted: http://www.gpgpu.org/s2007/ You can also buy the audio+slides from the SIGGRAPH course (and all SIGGRAPH presentations as well) at http://encore.siggraph.org.

29-Aug-2007, 01:27	#3
santyhammer Junior Member Join Date: Apr 2006 Location: Behind you Posts: 85	I'm interestered in the 12. GPGPU and Raytracing(Jens Krueger), but not avail! Any idea if is going to be available or when pls? Thanks for collecting the papers and putting the links there btw, very interesting reads as usually!

29-Aug-2007, 01:45	#4
CouldntResist Member Join Date: Aug 2004 Posts: 244	What is that "CAL API", mentioned in "AMD CTM Performance"?

29-Aug-2007, 02:11	#5
Jawed Regular Join Date: Oct 2004 Location: London Posts: 9,862	Compute Abstraction Layer, to abstract devices - i.e. R580 and R600 would be programmed the same way. Though, ahem, you might tweak the HLSL shader code to produce assembly code optimised for a specific GPU, or for that GPU's branching characteristics. It supports multiple GPUs transparently too and unifies the memory space (including the CPU's memory). See the CTM Overview presentation. Jawed

29-Aug-2007, 05:35	#6
mhouston A little of this and that Join Date: Oct 2005 Location: Cupertino Posts: 342	CAL actually goes a little beyond that. In theory, it could also drive a multi-core with the same data parallel abstraction. The better way to think of CAL vs HAL is that they split the higher level CTM stuff into CAL and are making it slightly more higher level and general, and HAL now represents the hardware abstraction for different hardware underneath (i.e. it handles the actual command buffer submission, required state setting, and ELF handoff to the hardware). As for Jens, I'll harass him again for slides. The raytracing and GPGPU talk was mainly an overview of the different options available based on previous published work, like the Horn et al. I3D paper on kd-trees, or some of the new BVH stuff, as well as more blurry lines between raster and raytrace.

05-Sep-2007, 17:00	#8
purpledog Member Join Date: Nov 2005 Posts: 108	In one of those slides (don't remember which one) I especially liked this idea: "rendering is a killer app for gpgpu" Funny really, you create some hardware to do graphics, then you stuck a general purpose api on top of it, then you realize "wait, I can go graphics with that!". I does make sense thought.

Beyond3D Forum

Welcome, Unregistered.