VizWorld.com

It’s amazing to see Physics Simulations moving out of the arena of SuperComputers into the realm of mere mortals with tools like GPU accelerators and fast physics engines like PhysX and Havok going mainstream.  ForCG.com has a great compilation of 20 impressive physics simulation videos, including the amazing one shown above.

Physics simulations are becoming more and more advanced and more spectacular each year. With processors that are becoming faster and faster computers are able to calculate complicated simulations ending up with really stunning effects. This collection consist of some beautiful physics simulations made using RayFire plug-in for 3D application or NVIDIA PhysX. Both of them enable designers to create very realistic 3D simulations.

via 20 Stunning Examples of Physics Simulations – ForCG.

Graphics, Science list, physx, rayfire

Autodesk and NVidia have once again collaborated to bring NVidia CUDA acceleration and PhysX physics simulation to the Autodesk Softimage 3D modeling and animation suite.

“By integrating CUDA and PhysX technologies into the new release of Softimage, Autodesk has opened up a new world of creative options for content creation professionals,” said Jeff Brown, general manager, Professional Solutions Group, NVIDIA. “With Quadro professional graphics, artists using Softimage can now achieve a higher level of realism, by adding physical simulations to their work.”

Primarily these new features are targeted towards users working in game development scenarios, offering improved interactivity and realistic effects.  Full press release after the break.

Read more…

Graphics autodesk, cuda, nvidia, physx, softimage

In an interview with Physxinfo.com, Mir Vadim talks about his amazing RayFire shatter and destruction simulation tool for 3dsMax and how it has grown from a simple idea into quite possibly the most powerful destructive simulation tool in the industry.

One and a half of the year has passed since that moment and now RayFire Tool became a default plugin for artists who need to create dynamic simulation, demolition, explosions or just prebreak objects. A lot of famous companies purchased it and use now in their production: first one and it will be here always is Blur Studio, among others are Blizzard, Disney, Fox, Electronic Arts, Rockstar, Ubisoft, Codemasters, Crytek, Rocksteady, Sega, Boeing and even US Military.

Towards the end he also discusses future directions of RayFire, and admirably denies adding in features that he considers “outside” of the focus of RayFire in favor of keeping it small, lean, and fast.

via PhysX From Inside Out: RayFire Tool | PhysXInfo.com – PhysX Articles.

Graphics, Science 3dsmax, interview, physx, rayfire

Lots of drama and news in the world of NVidia’s PhysX GPU-Accelerated physics simulation toolkit.  It all started earlier this month with an interview with AMD on game development and DirectX11 support where AMD has, of course, taken the lead since NVidia has no DirectX11 hardware available (yet).  The comment was something like this:

The other thing is that all these CPU cores we have are underutilised and I’m going to take another pop at Nvidia here. When they bought Ageia, they had a fairly respectable multicore implementation of PhysX. If you look at it now it basically runs predominantly on one, or at most, two cores. That’s pretty shabby! I wonder why Nvidia has done that? I wonder why Nvidia has failed to do all their QA on stuff they don’t care about – making it run efficiently on CPU cores – because the company doesn’t care about the consumer experience it just cares about selling you more graphics cards by coding it so the GPU appears faster than the CPU.

Basically they accuse NVidia of crippling PhysX, reducing it to a single CPU core so that it ‘appears’ faster when run in combination with a GPU.  NVidia was quick to refute the claims in a response by Nadeem Mohammad, PhysX director of product management.

I have been a member of the PhysX team, first with AEGIA, and then with Nvidia, and I can honestly say that since the merger with Nvidia there have been no changes to the SDK code which purposely reduces the software performance of PhysX or its use of CPU multi-cores.

Our PhysX SDK API is designed such that thread control is done explicitly by the application developer, not by the SDK functions themselves.  One of the best examples is 3DMarkVantage which can use 12 threads while running in software-only PhysX. This can easily be tested by anyone with a multi-core CPU system and a PhysX-capable GeForce GPU. This level of multi-core support and programming methodology has not changed since day one. And to anticipate another ridiculous claim, it would be nonsense to say we “tuned” PhysX multi-core support for this case.

So they basically say that thread management is left up to the developer, so whatever situation AMD witnessed was not NVidia’s fault but rather the fault of the programmer that developed it. (Probably hoping it was an internal AMD engineer).  Of course, the bulk of this entire argument is that AMD wants to break NVidia’s grip on GPU physics simulation so that their own Bullet product will have an easier path to market.

Sadly tho, Bullet is still unreleased and under development.  This means that developers will have to stick with what’s available, and in a new announcement from the developers of RayFire, the popular 3dsMax shatter & physics simulation tool, that means PhysX.

Hey everyone.
Well, what can I say, RayFire Tool 1.49 Beta with 64 bit PhysX support is ready to use.
Due to some new PhysX plugin restrictions some old features are not available atm, that is why it is 1.49 Beta. For now there is no Glueing and Imposible to use Grouped objects. But the most needed features like dynamic simulation and Interactive demolition work fine.

Can’t wait to see what it does when it’s fully released.

AMD Interview, via Bit-Tech

NVidia’s Response, refuting the claims via exPreview and TomsHardware

Graphics, Hardware amd, nvidia, physx, rayfire

NVidia has just released a new version of the PhysX physics simulation plugin for Autodesk 3dsMax with support for the newest versions of the product, and much tighter integration into the system.  This new plug-in has been rewritten from the ground up. A few highlights of the new release:

• Support for Max 2008, 2009, 2010, 32-bit and 64-bit.
• A first-class toolbar and menu for creating and controlling the simulation.
• A modifier-based approach to match workflow in 3ds Max, with greatly improved artist interface to the options.
• A physical material system for using and adjusting physics properties on many objects at once.
• Convenient constraint presets for common workflows.
• Improved constraint visualization and performance.
• Convenient ragdolls, deriving collision volumes from a skinned mesh.
• Bake simulation results to keyframes for offline rendering.
• Super simple samples

Sadly, tho, not all is rosy in the new version:

This great progress comes at a slight cost, however. Some PhysX features available in the previous plug-in are not (yet) exposed on the new version. Fluids, cloth, force fields, and soft bodies are not supported with this release. As demanded and deemed important, we will be adding features and improving the plug-in for the next releases. (Look in particular for the inclusion of awesome APEX Clothing in an upcoming release.)

So if you were using CUDA-accelerated fluid and cloth simulations, you might want to wait before upgrading.

via [ANN] PhysX Plug-in for 3ds Max v2.01 now available! – NVIDIA Developer Forums.

Graphics 3dsmax, autodesk, nvidia, physx

While the individual components are nothing new, I hadn’t heard of NVidia calling the whole system “AXE”, for Application Acceleration Engines.

NVIDIA® application acceleration engines are highly optimized software modules enabling developers to take maximum advantage of the GPU with valuable, high performance capabilities that are license free to develop with and deploy.

NVIDIA is committed to ensuring engines continue advancing to take maximum advantage of the latest NVIDIA GPU innovations while also maintaining their leading-edge capabilities. Applications employing acceleration engines can rapidly exploit GPU advancements as consistent engine APIs evolve to leverage new methods. In doing so, NVIDIA is empowering developers to deliver the latest capabilities to their users in the shortest amount of time.

The complete suite consists of SceniX (scene graph), CompleX (GPU scaling system), PhysX (GPU accelerated Physics), and OptiX (ray-tracing), along with the usual CgFX and CUDA.

via NVIDIA® Application Acceleration Engines.

Science axe, complex, gpgpu, library, nvidia, optix, physx, scenix

The Particle Flow Tools Box from Orbaz has been PhysX accelerated for some time, but only in the 32-bit version of 3ds Max.  The latest version, version 1.05, now supports the true 64-bit version.

“1.05 version of Box#2 Pro uses 64-bit PhysX SDK v.2.8.3. That allowed us to switch completely to native PhysX libs for both 32- and 64-bit versions. The new version works without restrictions on 64-bit flavors of Win XP, Vista and Windows 7. The update is not a beta, and it is available to all licensed users of Box#2 Pro.

via Particle Flow Tools Box 2: now with true 64-bit PhysX | PhysXInfo.com – PhysX News.

Graphics 3dsmax, nvidia, orbaz, particleflow, physx

EVGA’s Halloween Announcement came and went, as just like predicted they announced a new “CoOp” card that combined dual NVidia GPU’s for graphics & PhysX processing.

The card combines a GeForce GTX 275 (240 processing cores, 633/2268/1296MHz core/memory/shader) and a GeForce GTS 250 (128 processing cores, 738/2200/1836MHz), with the latter one only being used when in-game PhysX processing is required.

via EVGA GeForce GTX275 CO-OP PhysX Edition Makes Official Debut – Expreview.com.

Hardware evga, nvidia, physx

Some NVidia engineers have been trawling internet forums and posting some interesting responses to common complaints popping up recently.  A particularly good response comes from “NickStam” on the Hexus Forums.  A few choice quotes:

What is NVIDIA’s answer to ATI Eyefinity technology?

ANSWER: With GeForce you would need to use more than one graphics board to support more than two active monitors. If this is a feature our customers want, we will look in to adding it for GeForce. Our focus has been on other display technologies like 3D stereo, and our 3D Vision products, but we understand multi-mon gaming with many monitors could be a cool addition.

Why does NVIDIA detect AMD GPUs in Batman: AA and turn off AntiAliasing?

“In the case of Batman’s AA support, NVIDIA essentially built the AA engine explicitly for Eidos – AA didn’t exist in the game engine before that. NVIDIA knew that this title was going to be a big seller on the PC and spent the money / time to get it working on their hardware. Eidos told us in an email conversation that the offer was made to AMD for them to send engineers to their studios and do the same work NVIDIA did for its own hardware, but AMD declined.”

Why do new NVIDIA drivers punish AMD GPU owners who want to leverage an NVIDIA card to compute PhysX?

Answer: We’re not trying to punish gamers. Our GPU and PhysX drivers are interconnected to optimize performance. In the future we expect this interdependence to deepen. This alone makes it difficult to support a third party GPU.

In order to make sure our customers have a great experience, we QA every release of our PhysX and Graphics drivers by testing approximately 14 NVIDIA GPUs for graphics processing with 8 GPUs for PhysX processing on 6 common platforms with 6 OS’s using 6 combinations of CPU and memory. This is over 24000 possible configurations. While we don’t test every possible combination, the work and cost is substantial. Adding AMD GPUs would significantly increase the necessary work and cost for NVIDIA so we decided not to support this.

He also discusses some of the recent SLI Restrictions, the Vista Driver debacle, and support for DX10.1 and DX11.

Opinions – A look back at NVIDIA’s GTC – Page 4 – HEXUS.community discussion forums.

Hardware amd, nvidia, physx

In the latest “nTeresting Newsletter” from Brian Burke, PR guy for NVidia, he discusses the recent forays by AMD/ATI into GPU Accelerated Physics. I disagree that there hasn’t been “a peep” from AMD, as we covered the GPGPU accelerated Havok back in March and then the demonstration video.  But I do agree that NVidia has a far lead in OpenCL develoment over.. well, over everyone.

Right before mourning ‘the death of GPU physics’, AMD had the great idea that they would partner up with the Intel owned Havok Physics engine (I told you that was a bad idea).  Since then over a year has past and not a peep.  Until now.  Now their plan is “Bullet”.

“Bullet Physics Library is an open source physics library that is now getting translated into OpenCL, thanks to the effort of companies such as AMD [who offered support to developers]. Somehow, we feel that this announcement was the highlight of the launch event for the upcoming Evergreen generation of graphics cards.”

Reality is that AMD has no GPU driver for OpenCL and NVIDIA has had one for some time.  What does that really mean to people developing Bullet Physics for OpenCL?  Fudzilla asked the creator of the Bullet Physics, Erwin Coumans:

“Bullet’s GPU acceleration via OpenCL will work with any compliant drivers, we use NVIDIA GeForce cards for our development and even use code from their OpenCL SDK, they are a great technology partner.”

NVIDIA is the leader for stereoscopic 3D, GPU physics, OpenCL, DirectCompute and GPU Computing. #1 with a Bullet.

NVidia is getting rave reviews for their amazing graphics & the PhysX support in Batman: Arkham Asylum.  I got to give NVidia credit for actually having their product (PhysX) in a game that’s actually available.  What’s your thoughts?

Hardware amd, havok, nvidia, opencl, physx