« on: March 01, 2011, 01:21:20 AM »
This section allows you to view all posts made by this member. Note that you can only see posts made in areas you currently have access to.
GDC issue of Intel® Visual Adrenaline magazine is here!
Whether you're a game developer, designer, or sound creator—or just can't peel the mouse from your hand and tear your eyes away from the game (yup—been there!), this issue is for you.
Our focus: Celebrating the awesome world of PC gaming—where imagination and expertise take flight with today's technology. Some highlights are:
• In Sharing the Load in Total War*: Shogun 2, Creative Assembly talks about art, war, Zen, and why multi-threaded processors mean more realism in the game.
• It's not all about the visuals—game's gotta have sound! Meet three of the guys that create the complex audio that powers your favorite games in Audio for Games Reimagined.
• How do you scale up game complexity for today's new gaming systems while also improving the rendering on mainstream graphics hardware? Read Complex World, Mainstream Graphics to learn how Codemasters did it with Operation Flashpoint* 3: Red River.
• If you eat core design, 3D graphics pipelines, and power efficiency with your breakfast cereal, the Preview of 2nd Generation Intel® Core™ Processor Architecture article is definitely one you can't miss.
Brought to you by your friendly Intel® Visual Adrenaline team.
AMD Radeon HD 6990 "Antilles" Sneek Peek
It is here in our hands and it screams. "Performance!" The wait is nearly over as AMD's next generation "Antilles" video card sporting two high performance GPUs on a single printed circuit board is in our hands. We comment on our gameplay experiences in Dragon Age II in Triple-Display Eyefinity.
LuxMark is a OpenCL benchmark tool. The idea for the program was conceived in 2009 by Jromang. It was intended as a promotional tool for LuxRender (to quote original Jromang's words: "LuxRender propaganda with OpenCL"). The idea was quite simple, wrap SLG inside an easy to use graphical user interface and use it as a benchmark for OpenCL. After Anandtech adoption of SLG as OpenCL benchmark, the code was finally written.
"SUMO 9640" = ati2mtag_Sumo_Desktop, PCI\VEN_1002&DEV_9640
"SUMO 9641" = ati2mtag_Sumo_Mobile, PCI\VEN_1002&DEV_9641
"SUMO 9642" = ati2mtag_Sumo_Desktop, PCI\VEN_1002&DEV_9642
"SUMO 9643" = ati2mtag_Sumo_Mobile, PCI\VEN_1002&DEV_9643
"SUMO 9644" = ati2mtag_Sumo_Desktop, PCI\VEN_1002&DEV_9644
"SUMO 9645" = ati2mtag_Sumo_Mobile, PCI\VEN_1002&DEV_9645
"AMD FireStream 9170" = ati2mtag_RV630, PCI\VEN_1002&DEV_9519
"AMD FireStream 9250" = ati2mtag_RV7X, PCI\VEN_1002&DEV_9452
"AMD FireStream 9270" = ati2mtag_RV7X, PCI\VEN_1002&DEV_9450
"AMD Radeon HD 6300M Series" = ati2mtag_ManhattanP, PCI\VEN_1002&DEV_68E4
"AMD Radeon HD 6300M Series " = ati2mtag_ManhattanP, PCI\VEN_1002&DEV_68E5
"AMD Radeon HD 6430M" = ati2mtag_Vancouver, PCI\VEN_1002&DEV_6761
"AMD Radeon HD 6470M" = ati2mtag_Vancouver, PCI\VEN_1002&DEV_6760
"ATI FirePro (FireGL) Graphics Adapter" = ati2mtag_EvergreenGL, PCI\VEN_1002&DEV_6888
"ATI FirePro (FireGL) Graphics Adapter " = ati2mtag_EvergreenGL, PCI\VEN_1002&DEV_68C8
"ATI FirePro (FireGL) Graphics Adapter " = ati2mtag_EvergreenGL, PCI\VEN_1002&DEV_6889
"ATI FirePro (FireGL) Graphics Adapter " = ati2mtag_EvergreenGL, PCI\VEN_1002&DEV_68A9
"ATI FirePro (FireGL) Graphics Adapter " = ati2mtag_EvergreenGL, PCI\VEN_1002&DEV_68C9
"ATI FirePro (FireGL) Graphics Adapter " = ati2mtag_EvergreenGL, PCI\VEN_1002&DEV_68F1
"ATI FirePro 2450" = ati2mtag_RV610, PCI\VEN_1002&DEV_95CD
"ATI FirePro M7740" = ati2mtag_M9x7, PCI\VEN_1002&DEV_94A3
"ATI FirePro RG220" = ati2mtag_R7XGL, PCI\VEN_1002&DEV_9557
"ATI FirePro V7750 (FireGL)" = ati2mtag_R7XGL, PCI\VEN_1002&DEV_949C
"ATI FirePro V8750 (FireGL)" = ati2mtag_RV7XGL, PCI\VEN_1002&DEV_9444
"ATI Mobility Radeon 4100" = ati2mtag_RS880M, PCI\VEN_1002&DEV_9713
"ATI Mobility Radeon HD 4200 Series" = ati2mtag_RS880M, PCI\VEN_1002&DEV_9712
"ATI Mobility Radeon HD 4300 Series" = ati2mtag_M9x, PCI\VEN_1002&DEV_9552
"ATI Mobility Radeon HD 4330" = ati2mtag_M9x, PCI\VEN_1002&DEV_955F
"ATI Mobility Radeon HD 4500 Series" = ati2mtag_M9x, PCI\VEN_1002&DEV_9555
"ATI Mobility Radeon HD 4650" = ati2mtag_M9x, PCI\VEN_1002&DEV_9480
"ATI Mobility Radeon HD 4670" = ati2mtag_M9x, PCI\VEN_1002&DEV_9488
"ATI Mobility Radeon HD 4830" = ati2mtag_M9x7, PCI\VEN_1002&DEV_94A0
"ATI Mobility Radeon HD 4850" = ati2mtag_M9x8, PCI\VEN_1002&DEV_944A
"ATI Mobility Radeon HD 4860" = ati2mtag_M9x7, PCI\VEN_1002&DEV_94A1
"ATI Mobility Radeon HD 5000" = ati2mtag_Manhattan, PCI\VEN_1002&DEV_68C0
"ATI Mobility Radeon HD 5000 Series" = ati2mtag_ManhattanP, PCI\VEN_1002&DEV_68E0
"ATI Mobility Radeon HD 5000 Series " = ati2mtag_Manhattan, PCI\VEN_1002&DEV_68C1
"ATI Mobility Radeon HD 5000 Series " = ati2mtag_ManhattanP, PCI\VEN_1002&DEV_68E1
"ATI Mobility Radeon HD 5800 Series" = ati2mtag_Manhattan, PCI\VEN_1002&DEV_68A1
"ATI Mobility Radeon HD 5800 Series " = ati2mtag_Manhattan, PCI\VEN_1002&DEV_68A0
"ATI Radeon 3000 Graphics" = ati2mtag_RS780, PCI\VEN_1002&DEV_9616
"ATI RADEON E4690" = ati2mtag_M9x, PCI\VEN_1002&DEV_9491
"ATI Radeon HD 3200 Graphics" = ati2mtag_RS780, PCI\VEN_1002&DEV_9615
"ATI Radeon HD 4200" = ati2mtag_RS880, PCI\VEN_1002&DEV_9710
"ATI Radeon HD 4250" = ati2mtag_RS880, PCI\VEN_1002&DEV_9715
"ATI Radeon HD 4300/4500 Series" = ati2mtag_R7X, PCI\VEN_1002&DEV_954F
"ATI Radeon HD 4500 Series" = ati2mtag_R7X, PCI\VEN_1002&DEV_9540
"ATI Radeon HD 4600 Series" = ati2mtag_R7X, PCI\VEN_1002&DEV_9498
"ATI Radeon HD 4700 Series" = ati2mtag_RV7X, PCI\VEN_1002&DEV_944E
"ATI Radeon HD 4700 Series " = ati2mtag_RV7X, PCI\VEN_1002&DEV_94B4
"ATI Radeon HD 4770" = ati2mtag_RV7X, PCI\VEN_1002&DEV_94B3
"ATI Radeon HD 4770 " = ati2mtag_RV7X, PCI\VEN_1002&DEV_94B5
"ATI Radeon HD 4800 Series" = ati2mtag_RV7X, PCI\VEN_1002&DEV_944C
"ATI Radeon HD 4800 Series " = ati2mtag_RV7X, PCI\VEN_1002&DEV_9460
"ATI Radeon HD 4800 Series " = ati2mtag_RV7X, PCI\VEN_1002&DEV_9462
"ATI Radeon HD 4850 X2" = ati2mtag_RV7X, PCI\VEN_1002&DEV_9443
"ATI Radeon HD 5400 Series" = ati2mtag_EvergreenC, PCI\VEN_1002&DEV_68F9
"ATI Radeon HD 5500 Series" = ati2mtag_Evergreen, PCI\VEN_1002&DEV_68D9
"ATI Radeon HD 5600 Series" = ati2mtag_Evergreen, PCI\VEN_1002&DEV_68D8
"ATI Radeon HD 5600 Series " = ati2mtag_Evergreen, PCI\VEN_1002&DEV_68B9
"ATI Radeon HD 5700 Series" = ati2mtag_Evergreen, PCI\VEN_1002&DEV_68B8
"ATI Radeon HD 5700 Series " = ati2mtag_Evergreen, PCI\VEN_1002&DEV_68BE
"ATI Radeon HD 5800 Series" = ati2mtag_Evergreen, PCI\VEN_1002&DEV_6898
"ATI Radeon HD 5800 Series " = ati2mtag_Evergreen, PCI\VEN_1002&DEV_6899
"ATI Radeon HD 5900 Series" = ati2mtag_EvergreenH, PCI\VEN_1002&DEV_689C
"Mobility Radeon HD 6000 series" = ati2mtag_Vancouver, PCI\VEN_1002&DEV_6764
"Mobility Radeon HD 6000 series " = ati2mtag_Vancouver, PCI\VEN_1002&DEV_6765
"WRESTLER 9802" = ati2mtag_Wrestler, PCI\VEN_1002&DEV_9802
"WRESTLER 9803" = ati2mtag_Wrestler, PCI\VEN_1002&DEV_9803
"WRESTLER 9804" = ati2mtag_Wrestler, PCI\VEN_1002&DEV_9804
"WRESTLER 9805" = ati2mtag_Wrestler, PCI\VEN_1002&DEV_9805
The OptiX team is pleased to announce that the second release candidate for version 2.1 of the NVIDIA OptiX ray tracing engine is now publicly available to all software developers.
Here are some of the highlights of the changes from version 2.1 RC1 (please see the Release Notes in the distribution for complete details)
* RtuTraverse API changes (your application will need to be recompiled) This API is currently in Beta.
o Automatic fallback to CPU when no NVIDIA GPU is present
o Sped up CPU fallback path
o See documentation for new capabilities, including optional return data for ray hits
o Added missing traversal sample
* The OptiX libraries no longer link against nvcuda.dll or nvcuda.so. This allows apps linking to OptiX to execute on machines that do not have an NVIDIA driver installed. This also enables the the CPU fallback option of rtuTraverse.
* Sped up SBVH builds up to 2x
* Fixed bug on G80 GPUs where it complained about cuMemAlloc
Version 3 of the Cg Toolkit adds capabilities and profiles to fully support all currently shipping graphics boards from NVIDIA.
The February 2011 version of Cg 3.0 added these improvements:
* Improved DX11 tessellation support
* Resolved an issue with nearly identical user defined types
* Resolved an issue with default values from unreferenced uniform parameters
* Support setting matrices beyond 96 float constants in the vp30 profile
* Application supplied compilation options now override those set by cgGLSetOptimalOptions
* Improved support for 'const' variables in the GLSL profiles
* Added sampler state documentation
New Line of Professional Mobile Graphics Solutions Built on NVIDIA Fermi Architecture and Optimus Technology
SANTA CLARA, Calif. — February 22, 2011 —NVIDIA announced today a new line of Quadro® professional graphics solutions for mobile workstations. Designed for engineers, industrial designers, animators, and film & video editors that need to take their work with them, these new Quadro graphics processing units (GPUs) leverage the NVIDIA Fermi architecture, which combines fast visualization performance with high performance computing capabilities. This massively parallel processing horsepower transforms laptop computers into mobile super computers.
Featuring twice the number of CUDATM cores and twice the graphics memory over previous generations, these new Quadro GPUs also incorporate NVIDIA OptimusTM technology, maximizing battery life by automatically powering the GPU only when needed. Optimus also provides users with the ability to drive up to four displays at the same time.
Building on a decade of innovation and leadership in professional mobile graphics, the new Quadro line of mobile graphics solutions includes:
* Quadro 5010M (Ultra-High End): 384 CUDA cores; 4 GB GDDR5 memory; designed for new 17.3-inch mobile workstations
* Quadro 4000M (High End): 336 CUDA cores; 2 GB GDDR5 memory; designed for new 17.3-inch mobile workstations
* Quadro 3000M (High End): 240 CUDA cores; 2 GB GDDR5 memory; designed for new 17.3-inch mobile workstations
* Quadro 2000M (Mid-Range): 192 CUDA cores; 2 GB DDR3 memory; designed for 15.6-inch mobile workstations
* Quadro 1000M (Mid-Range): 96 CUDA cores; 2 GB DDR3 memory; designed for 15.6-inch mobile workstations
“Year after year, NVIDIA innovations demonstrate true technology leadership,” said Dr. Jon Peddie, president of Jon Peddie Research. “Optimus is perfect for anyone who needs high performance, long battery life, and additional displays. With this new Quadro mobile lineup based on the Fermi architecture, NVIDIA is poised to continue its dominance in mobile workstation graphics.”
The new standard for mobile workstation graphics excellence—the NVIDIA Quadro 5010M
The flagship Quadro 5010M features Error Correction Code (ECC) and fast, 64-bit double precision capabilities to ensure the greatest accuracy and fidelity of results. From medical imaging to structural analysis applications, data integrity and precision is assured, without sacrificing performance.The Quadro 5010M features an unprecedented 4 GB of fast GDDR5 memory to enable interactivity on the largest projects. Shattering previous 3D graphics benchmarks, professionals on the go can achieve nearly a billion triangles per second with this ultra high-end Quadro mobile graphics solution.
NVIDIA Quadro technology creates mobile super computers
Similar to the NVIDIA Quadro 5000M, the groundbreaking NVIDIA Fermi-based mobile workstation graphics solution announced last year, and currently available in both the Dell Precision M6500 and HP EliteBook 8740w mobile workstations, additional features of these new NVIDIA Quadro mobile professional graphics solutions include:
* The NVIDIA CUDA parallel computing architecture – Quadro mobile GPUs deliver massive performance gains when running computationally intensive applications such as ray tracing, video processing and computational fluid dynamics.
* NVIDIA 3D VisionTM Pro – support for the highest quality, stereoscopic viewing experience is helping drive the development of 3D capable visualization applications from companies such as Autodesk, Dassault Systemes, Siemens and Agilent.
* NVIDIA Scalable Geometry EngineTM technology – dramatically improves performance across a broad range of CAD, DCC and scientific applications, enabling a user’s work to flow interactively with models and scenes that are an order of magnitude more complex than ever before.
* NVIDIA GPU Tessellation Engine technology – with support for OpenGL 4.1, Shader Model 5.0 and DirectX 11, tessellation automatically generates finely detailed geometry for cinematic quality environments and scenes without sacrificing performance.
* Application certification - support for the broadest spectrum of professional applications, including those utilizing OpenGL 4.1, Shader Model 5.0, and Microsoft DirectX 11, plus DirectCompute and OpenCL standards. Companies such as Adobe, Autodesk, and Dassault Systemes certify NVIDIA Quadro solutions for professionals whose livelihoods depend on maximum uptime with their applications.
Mobile workstation manufacturers have relied on NVIDIA GPUs for the past decade, and will integrate these Quadro solutions in their newest mobile workstations scheduled to be announced throughout 2011. For more information about NVIDIA and Quadro Mobile Graphics Solutions, please visit www.nvidia.com/quadromobile
Numerion Software unveils "Carbon"
Carbon™ is the next generation physics library in development at Numerion Software™. The goal is to provide a unified physics frame-work supporting the simulation of Soft and Rigid bodies with collision and motion constraints (such as Joints), in an easy to use, high performance package for games and movie developers.
The Carbon physics technology is particularly well suited to helping make games and animated movie characters more believable.
Carbon leverages non-linear constraint solvers to deliver a robustness not seen before in real-time simulations.
Carbon delivers very high performance, by combining a novel algorithmic approach with a number of multi-core performance enhancing techniques including; minimizing memory bandwidth and leveraging nested parallelism. The developer is also given full control of the trade-off between quality and performance, making Carbon well suited to applications with simulation requirements ranging from real-time to interactive and even production.
See Carbon @ GDC 2011
We'll be in San Francisco @ GDC Feb 28th - March 4th 2011 demonstrating Carbon. To book a meeting to see Carbon in the flesh click email@example.com .
Test Drive Carbon
Fancy test driving Carbon? We are looking for selected beta testers to test drive Carbon in a closed beta in April. If you'd like to try Carbon click firstname.lastname@example.org .