[PREVIEW] PhysX Simulation on a 16-Core CPU With PhysX FluidMark

• March 6, 2010
• Written by Mark
• Leave a Comment
• Tweet

It was recently reported at Geeks3D that they are working on a new version of their PhysX FluidMark Benchmark that would be supporting Multi-Core CPU Support for running the PhysX calculations. Geeks3D has now posted an updated showing the new version of PhysX FluidMark running on 16 cores and a screenshot showing the new GUI that allows you to select the numbers of CPU cores your processor has before you run PhysX FluidMark.

This is definitely exciting stuff, PhysX FluidMark is a great program to test out your new PhysX setup quickly and run benchmark/stability tests on your dedicated PhysX Card. Keep checking in here at GamePhys and Geeks3D for more information.

From Geeks3D:

I’m still coding the new FluidMark with multi-core CPU support and in order to test with more than 4 cores (my dev station really sucks with its 2 CPU cores and my test bench is a little bit better with 4 CPU cores) I asked to David from french website PC Inpact to play with the unstable version of FluidMark on a 16-core CPU.

As you can see on the screenshot, the 16 cores are fully loaded

Currently I have some little problems with multi-core support and PhysX GPU (there are some crashes when hardware PhysX is used with multithreaded simulation) but I’m about to find a solution…

Stay tuned!

Read the rest here.

[PREVIEW] Multi-Core CPU Support in PhysX Coming To PhysX FluidMark

• February 16, 2010
• Written by Mark
• Leave a Comment
• Tweet

Geeks3D is reporting that they are working on a new version of their PhysX FluidMark benchmark that will support Multi-Core CPU Support for running the PhysX calculations. In recent news AMD called out NVIDIA claiming that they have purposely disabled multi-core CPU support for PhysX. NVIDIA then released a statement claiming that this was simply not true stating “Our PhysX SDK API is designed such that thread control is done explicitly by the application developer, not by the SDK functions themselves“. So this new update to PhysX FluidMark should answer this question once and for all and allow people to do some really interesting tests and benchmarks with PhysX running on the GPU or dedicated PhysX card and then benchmark with the CPU handling all the PhysX calculations.

From Geeks3D:

I’m currently updating Geeks3D’s PhysX FluidMark tool and from my last tests, multi-core CPU support in PhysX seems to be ok (that confirms what NVIDIA said in this news)… At least on my dev station with an ATI Radeon HD 5770 and an AMD X2 3800+.

Read the rest of the article here.

In case you are not familiar with PhysX FluidMark it is a free to download PhysX benchmarking and stability tool perfect for quickly testing out a new PhysX setup to make sure PhysX was installed and up and running correctly, you can download it here and a YouTube video showing it in action was embedded below.

From the PhysX FluidMark page:

PhysX FluidMark is a physics benchmark based on NVIDIA PhysX engine. This benchmark performs a fluid simulation by imitating the renderering of lava. Real physics parameters such as viscosity are used. SPH (Smoothed Particle Hydrodynamics) algorithm is enabled to increase the realism of the simulation.

This benchmark exploits OpenGL for graphics acceleration and requires an OpenGL 2.0 compliant graphics card: NVIDIA GeForce 5/6/7/8/9/GTX200 (and higher), AMD/ATI Radeon 9600+, 1k/2k/3k/4k (and higher) or a S3 Graphics Chrome 400 series.

What’s the Difference Between a CPU and a GPU? Better For Physics

• December 26, 2009
• Written by Mark
• 2 Comments
• Tweet

Over the past year with an increase in the number of games that are implementing PhysX and other video game physics technologies into games, people have been asking why we need a GPU to do all this when it looks like many of these features have been available in games and done on CPU for several years now. The NVIDIA nTersect Blog just posted an interesting article on why the GPU can perform tasks quicker and more efficiently than a normal CPU. The Parrallel Processing capabilities of the GPU will no doubt be needed in future games when they start to take more advantage of PhysX and begin to implement them on a larger scale such as fully destructible environments that mimic real work physics in real time.

from the NVIDIA nTersect Blog:

The GPU is in a class by itself – it goes far beyond basic graphics controller functions, and is a programmable and powerful computational device in its own right.

The GPU’s advanced capabilities were originally used primarily for 3D game rendering. But now those capabilities are being harnessed more broadly to accelerate computational workloads in areas such as financial modeling, cutting-edge scientific research and oil and gas exploration. In a recent BusinessWeek article, Insight64 principal analyst Nathan Brookwood described the unique capabilities of the GPU this way: “GPUs are optimized for taking huge batches of data and performing the same operation over and over very quickly, unlike PC microprocessors, which tend to skip all over the place.”

Architecturally, the CPU is composed of a only few cores with lots of cache memory that can handle a few software threads at a time. In contrast, a GPU is composed of hundreds of cores that can handle thousands of threads simultaneously. The ability of a GPU with 100+ cores to process thousands of threads can accelerate some software by 100x over a CPU alone. What’s more, the GPU achieves this acceleration while being more power- and cost-efficient than a CPU.

Read the rest of the article here.

Last year NVIDIA also hired the MythBusters to explain parallel processing and the difference between a CPU and GPU check it out below.

Here are two more videos that show the power of PhysX being calculated on the GPU instead of the CPU using 3Dmark Vantage and the nVidia PhysX fluid physics demo.