VizWorld.com

Researchers at Lawrence Berkeley National Lab (LBNL) collaborated with the Department of Energy Nanoscale Science Research Centers and MIT to create some new hardware and software for imaging nanoscale structures smaller than the wavelength of light.

In parallel with Schuck’s experimental findings, Jeff Neaton, Director of the Molecular Foundry ’s Theory of Nanostructured Materials Facility and Alex McLeod, an undergraduate student working at the Foundry, developed a web-based toolkit, designed to calculate images of plasmonic devices with open-source software developed at Massachusetts Institute of Technology. For this study, the researchers simulated adjusting the structure of a double bowtie antenna by a few nanometers to study how changing the size and symmetry of a plasmonic antenna affects its optical properties.

The article is a bit light on any more details, but they’ve created an interesting looking web-based visualization tool to see the results, combined with some interesting imaging hardware.  They have a paper publishing their results in Physical Review Letters called “Non-perturbative visualization of nanoscale plasmonic field distributions via photon localization microscopy” that you can get here (purchase required).

If you find the paper elsewhere, let me know!

via Berkeley Lab Team Uses New Imaging Concept to Visualize Plasmonic Fields at Nanoscale. and the LBL Website

Science doe, imaging, nanotechnology, research, whitepaper

A new whitepaper from Intel brings in some statistics and stories from Luxology, Luxion, and Modo on the power of CPU’s for ray-tracing and how they can smoke any GPU on the market with CPU-only solutions.

“Modern GPUs offer a brute force solution to ray tracing, but the memory available to GPUs is relatively limited compared to the system memory available to 64-bit CPUs such as Intel Core i7 and Xeon processors. That means that GPUs typically can’t handle the huge scene files required in full-scale production rendering, which may involve tens of millions of polygons and hundreds of high-resolution texture maps. And CPUs offer greater flexibility in terms of shading complexity and plug-in shaders, which may or may not have been ported to run on a GPU.”

These are the same arguments I’ve been hearing for the last year or so.  And I have to admit they’re right, if not a bit short-sighted.  It’s my belief that most of the arguments they use are going to fall apart soon.

• They always talk about the power of Moore’s law in CPU’s.  Well, that same law applies to GPU’s too, they’re going to get faster just like CPU’s will.  Even more so, most likely, as they not only optimize individual cores but add more cores as a rate exponential to CPU’s.
• They always talk about Memory limitations.  There was a time where CPU’s had rather restrictive memory limitations (the fabled “640k is enough for anyone” comment?).  GPU’s will continue to grow in memory.  In fact, Sandy Bridge and Fusion offer the first step towards eliminating the distinction between GPU and CPU memory.
• They always talk about the limited instruction set.  This one isn’t likely to change, and will always be a hindrance to GPU computing.  However, newer algorithms come along at a steady pace showing that you don’t really need the type of complex branching mechanisms of CPU’s, since the GPU has enough horsepower to just compute both sides of the condition and drop the unnecessary one.

In fact, I think within the next 5 years we may see the distinction between CPU and GPU disappear almost entirely, as they both wind up on the same die (similar to how Processor and Math Co-Processor eventually merged several years ago).

It’s a good whitepaper tho, full of some concrete numbers on attempts to GPU-ize code unsuccessfully and benefits achieved from using some of Intel’s newest CPU-optimization technology.

Check it out, and see what you think?

via Why CPU is better than GPU for rendering from Intel with Luxology, Keyshot and Maxwell. – SolidSmack.com.

Science cpu, gpu, intel, luxion, luxology, modo, whitepaper

Autostereoscopic 3D Displays are regarded by many as the “holy grail” of 3D.  No glasses, multiple viewers, multiple angles, and high-resolution.  So far, various displays can hit certain aspects of this but none has hit all of them.  Zecotek has a new display that uses a ‘time sequencing’ approach to enable 40-90 simultaneous views through a 50-degree viewing angle.  I can’t find many details on what ‘time sequencing’ is, other than it apparently requires a display capable of a 2000Hz refresh rate or greater.

Nonetheless, they have a great whitepaper up on their site detailing the advantages and disadvantages of various technologies like Parallax barriers and shutter glasses, complete with some nice charts and visuals.

You can get the whitepaper here.

Hardware, Science 3d, stereoscopic, whitepaper, zecotek

AMD has published a “whitepaper” (it irks me that they call these Whitepapers when they’re actually powerpoint presentations) discussing optimizations for Image Convolution algorithms on both CPU and GPU.  They start with an algorithm and add some optimizations for the memory overlap, and then naively port it to a Radeon 5870 to run in 1511 ms.  Then, with some careful optimizations, work it down to a mere 182ms!

Download the PDF, or view it Online.

Science algorithm, amd, opencl, whitepaper

AMD has published a new pair of new “whitepapers” covering the new Device Fission Extensions and an algorithm for Particle Hydrodynamics.  The papers are actually PDF’s of powerpoint presentations, but contain all the necessary code snippets and math to recreate the work.

• Device Fission Extensions (View Online)
• Particle Hydrodynamics (View Online)

Check em out and see what you think.

Science amd, opencl, whitepaper

Daden Limited is no stranger to virtual worlds, having already created several products and won a few awards for their work in existing systems.  In a new whitepaper entitled “The Future of Virtual Worlds” they look 20 to 30 years out and what they think is coming, and I have to admit it’s an impressive bit of work.  In particular, I like the graph above showing how the space has exploding into little submarkets that they believe will re-coalesce into something useful in the near future.

Over the next two decades the boundaries between these will become blurred, and related systems such as messaging, entertainment, on-line games and even the web and desktop will be drawn into the maelstrom. The eventual model may be one where the “systems” will largely coalesce around a new 2 x 2 matrix defined by private and public access, and information and experience spaces – not by technology or even applications – although the Information axis is likely to be dominated by “web” like systems, and the Experience axis by virtual world like systems.

I also love that they very clearly and early make the definitive statement that Virtual Worlds ARE NOT the 3D Web.

One thing that we are quite clear on is that Virtual Worlds ARE NOT the 3D Web, and the future of the Web is not Virtual Worlds. A web page full of text and graphical imagery is an incredibly information rich environment. The Web will remain, for the short to medium, and maybe all but very long term, the most efficient way to view, assess and interact with most transactional information and services. Virtual worlds are about immersion and community. The two are quite fundamentally different. Virtual Worlds convey experience, the Web conveys information.

The entire paper is only 19 pages long, but it’s a good piece.  They cover the background of the technology, and how the movement into “serious games” and “Games as simulations” are the first steps toward Virtual Worlds.  They also cover some of the current problems like file formats, geometry formats, and some of the infrastructure that will have to be built to make this a reality.

You can go download it (fill out the form at the top of the page) here.

Science daden, virtual worlds, whitepaper

A new article from AMD published in the “Embedded Control Europe” magazine called “Combining Hardware and Software for Advanced Embedded Graphics” seems to lobby a round soundly in the direction of Nvidia’s Tegra with statements like this:

Developers no longer need to spend so much time optimizing code to fit into small solid-state storage devices.  Even handheld-sized embedded devices with low-power processors can operate a fully-fledged Windows 7 operating system.  Thus, fully featured x86 computers can more easily adapt to fit the shape and size requirements of the embedded applications, lending themselves to becoming truly embedded and ubiquitous devices.

It may not be immediately obvious to read it, but there’s a strong underlying subtext here: Use AMD technology and you can run your existing Windows applications on mobile devices, instead of rewriting/recompiling them for Apple’s IOS or a Tegra-based device (Based on ARM).  This is a big win for developers who can recycle their existing code and development strategies, but one has to wonder: Will anyone really want to run Windows7 on a mobile device?  Apple kinda reinvented the mobile-device market by abandoning most of the desktop paradigms for a completely new experience.  Games like ‘Trism’ and Apps like ‘Google Goggles’ aren’t really suited well for desktop environments, how would they work in a Desktop Environment shrunken down to Mobile size?

Get the paper here (3 page PDF), or read it online.

Update: And if you really are serious about embedded development, you can try out AMD’s High Performance Embedded Graphics Reference Design Kit: An AMD A3 Processor combined with a Radeon E4960, 1GB Ethernet, and 2 HDMI, 2USB, and 2 SATA ports.

Hardware amd, whitepaper

Nicolas Vizerie took a look at Intel’s paper on MorphoLogical Anti-Aliasing (MLAA) recently and became intrigued, but noticed that the original algorithm wasn’t well suited for use with GPU Pixel Shaders.  He did some work, and now has a demonstration working on an nVidia 8700MGT.

The original technique is not very suitable to GPU with pixel shaders alone, so some adaptation was needed. The reason is that the algorithm scans edges and patches pixel based on the edge length, and the configuration at edge extremities (to sum up). Edges extremities can be far from the current pixel, so using a pixel shader (pure parallel model) requires each pixel to recompute the distance from itself to the edge extremities. For an edge of length N, the complexity becomes O(N^2), which can lead to performance problems. The obvious solution is to compute a bilateral distance texture. T

via MLAA (MorphoLogical AntiAliasing) on the GPU using Direct3D9.0 – GameDev.Net Discussion Forums.

Science algorithm, intel, whitepaper

NVidia has published a whitepaper of their upcoming Fermi (GT300) architecture detailing the new features and various case-study results.  The cliff-notes version:

• 32 CUDA Cores per Streaming Multiprocessor
• 8x double precision performance over GT200
• Unified Address Space with full C++ Support
• Full IEEE 754-2008 32-bit and 64-bit Precision
• Predication
• ECC Memory SUpport
• 10x faster context switching
• Out-of-Order thread block execution
• 3Billion Transistors
• 768K L2 Cache (didn’t exist in GT200)
• Up to 16 concurrent kernels (Didn’t exist in GT200)

Looks like Fermi is going to be an awesome processor to work with. Read the full report on their site.

NVIDIA_Fermi_Compute_Architecture_Whitepaper.pdf (application/pdf Object).

Hardware fermi, nvidia, whitepaper

Centrifuge Systems, makers of an interactive data analysis and visualization package for the intelligence community, has released a new whitepaper entitled “The White Noise of Intelligence: Finding Relevance with Interactive Analytics”.  From the press release:

This white paper describes how Interactive Analytics works and includes case studies in the areas of Threat Finance and Cyber Security Analysis. Examples of domain relevant visualizations in the form of heat maps, relationship graphs, timelines and maps are displayed for each case study. The use of collaborative analysis is also highlighted in the paper.

Of course, they talk about the specific benefits and uses of their own product, but it also contains some information about how effective visualization can be in collaboration and analysis of intelligence data.

Requires short signup to get the paper.

via Centrifuge Systems Publishes New White Paper on Intelligence Analysis.

Science centrifuge, intelligence, whitepaper