NVIDIA has released a new set of drivers that add support for PhysX acceleration on all GeForce 8-series, 9-series and 200-series GPUs with a minimum of 256MB dedicated graphics memory. The PhysX System Software 8.08.01 is automatically installed with this driver package that explains the big size of the driver 😉
Here is a thesis that discusses the usage of NVIDIA’s CUDA in two applications:
– Einstein@Home: a distributed computing software
– OpenSteer: a game-like application.
CUDA exposes the GPU processing power in the C programming language and can be integrated in existing applications with ease. But in order to exploit the power a GPU can deliver, one has to design the data structures in order to become optimized for CUDA.
Here we are, the new beast of ATI is there! The Radeon HD 4870 X2 has been tested by the guru of 3D and the first results are… stunning! The Radeon HD 4870 X2 is, no doubt, the fastest performing product on the market right now.
The Radeon HD 4870 X2 is powered by the R700 GPU. R700 is actually made of two RV770. Here are some features of this new Radeon:
– GPU: R700 (2xRV770)
– transistors: 1930 million (2x965M) / fabrication process: 55nm
– shader processors: 1600 (2×800)
– memory: 2Gb GDDR5 (2x1Gb per GPU) / 512-bit
– texture units: 80 (2×40)
– ROPs: 32 (2×16)
– DirectX 10.1 / OpenGL 2.1 / Shader Model 4.1
Like the GeForce GTX 280, the Radeon HD 4870 X2 needs one 6-pin and one 8-pin PCI-Exp power connector
SIGGRAPH 2008: Khronos Group has announced the release of the OpenGL 3.0 API specification and the GLSL 1.30 shading language specification.
The OpenGL working group has defined a set of OpenGL 3.0 extensions that expose potential new functionality for the next version of OpenGL that is targeted for release in less than 12 months, and a set of extensions for OpenGL 2.1 to enable much of the new OpenGL functionality on older hardware.
According to Dr. Jon Peddie of Jon Peddie Research, a leading graphics market analyst based in California, the installed base of graphics hardware that will support OpenGL 3.0 exceeds 60 million units. AMD, Intel and NVIDIA have made major contributions to the design of OpenGL 3.0 and today all three companies announced their intent to provide full implementations within their product families
MSI’s Radeon HD 4870 X2 is ready and should be available very soon. Radeon HD 4870 X2 is based on R700 GPU (2xRV770) and features the monstrus number of 1600 stream processors with 2Gb of GDDR5 memory.
Humus has released a new Direct3D demo. Interior mapping is a technique that renders the interior of buildings without requiring additional geometry. Everything is done in the pixel shader. The advantage is that when you’re rendering large cities you can draw all those buildings as simple boxes. This demo requires DirectX 10.1 and Windows Vista SP1.
Water cooling is the most efficient way to cool the GPU that’s why EVGA has released an overclocked and water-cooled GeForce GTX 280. EVGA Hydro Copper 16 is equiped with a large copper block that replaces the reference cooling.
GTX 280 is the fastest single GPU card and EVGA most certainly pushed it even further with their overclocking. In order to make sure your card lasts for a long time, EVGA decided that water cooling is the way to go. So, they’ve made their own water block design made of pure copper, but also a bit heavy. The card is not heavy enough to damage your PCIe slot, but you should still make sure it’s screwed to the case nice and tightly.
Hardware Secrets has published an article about the SPDIF connector available on some GeForce. Here is this connector (the smallest one) on my GeForce GTX 280:
SPDIF is a standard used to transmit digital audio. The purpose of this small connector is very simple: it is used to allow digital audio to be routed to the HDMI output. All video cards have one or two DVI connectors, and any DVI connector can be converted into an HDMI connector by the use of a simple adaptor. The problem is that the DVI connector does not transmit audio signals, only video, while HDMI can transmit both audio and video.
Alongside its FireGL professional graphics cards, ATI has launched new 3D graphics accelerators: FirePro V3700 and FirePro V5700. FirePro V3700 is the entry level model (40 unified shader processors, 256Mb memory) and FirePro V5700 is the top level (320 unified shader processors, 512Mb memory). These graphics cards come with OpenGL optimized graphics drivers (for CAD and professional DCC applications) and support DirectX 10.1 and OpenGL 2.1.
TG Daily has interviewed Daniel Pohl, an engineer who is making some impressive progress in ray-tracing research, about Intel’s ray-tracing efforts.
Q: What is Larrabee from your perspective. What is the underlying architecture and the programming model?
A: Larrabee was primarily built as a rasterizering processor. Therefore you have support for DirectX and OpenGL. But it will also be a freely programmable x86-architecture. That means you could, for example, write your own rasterizer with your own API, a ray tracer, a voxel renderer or combinations of those. You could also use it for non-graphical applications that benefit from parallelization.
Q: What API is Intel using to showcase ray tracing demos?
A: We wrote our own API. The shading system uses a HLSL-like syntax that allows you also to shoot new rays within a shader. Using that API the programmer has no need to manually multi-thread the rendering and does not need to optimize the shading with SSE as this is done by the shading compiler automatically.