With the release of powerful new cards from both ATI and NVIDIA, it seems we have all forgotten about the classic X8x0 series of video cards from ATI. It gave the old NVIDIA 7800 series of cards a run for their money, and gave people the most value for several years to come. Thankfully, famous American online retailer Newegg has not forgotten the wonderful X850XT. To show their appreciation for this noble video card, Newegg is pricing their last two at a price fit for a king: $625.10 + shipping. These open box HIS X850XT PE's are clocked at 540/1180 MHz, come with a whopping sixteen ROP's, and have 256MB of 256-bit GDDR3. Anyone hoping to get a piece of true PC history had better hurry up, as they will most likely sell like hotcakes at such a competitive price point.

Sources from multiple graphics card vendors have confirmed that Intel has approached them to lay down plans to enter the discrete graphics card market for desktop PCs. The new products from Intel would be positioned as direct competitors to AMD's ATI Radeon and NVIDIA's GeForce series of cards. The processor giant will aim for the mid-range market in the initial stages with pricing targeted around US$300. In order to be competitive, the cards will need to match the features of products from AMD and NVIDIA such as support for DirectX 10 and equivalent memory densities. Whether or not Intel will implement a technology to support multi-card configurations similar to SLI and Crossfire is unknown at this stage but it is a possibility as most of Intel's mid-range and high-end chipsets support multiple PCI Express slots already. Intel is scheduled to deliver a more complete roadmap and specifications in the fourth quarter of this year, with expected launch of the new products around the second quarter of 2008.

Above, you can see the Zalman ZM-90 HP. The cooler is made from aluminum, and should be capable of cooling today's mid-range graphic cards.The VF1000 is an active cooler manufactured from aluminum using four heat-pipes. Don't be deceived by its apparently small size: it will be capable of cooling GeForce 8800 GTX.

NVIDIA Corporation, today announced a new version of the NVIDIA Quadro Plex visual computing system (VCS), which incorporates the unified architecture and GPU computing capability of NVIDIA Quadro FX 5600 GPUs. This new Quadro Plex VCS pushes visual computing to new extremes, boosting workstation and cluster performance for a wide range of high-performance, graphics-intensive styling and design, oil and gas, and scientific applications.

There's a lot to be told about the latest graphics card news. At first Sanjin Radoš from Fudzilla wrote a small preview about the Sapphire X1950 Pro Dual. This card, as the name already implies, is powered by two Radeon X1950 Pro chips attached to each other using a special bridge chip. Every GPU (clocked at 580 MHz) has 512MB of GDDR3 memory clocked at 1400 Mhz at its disposal, using the right motherboard (ATI or Intel chipset) you will be able to get a 2GB CrossFire setup that probably outperforms even NVIDIA's 8800GTX card. In the article are some 3DMark06 scores that might get your wallet fear you again - the cards price will be around 500 Euros. The previewed sample was made by Sapphire and this will be earlier on the market than ASUS' design.The next card in the row is another X1950 Pro card, this time a single chip one. It's from Jetway and it comes with GDDR4 memory clocked at 2200 MHz. Though price is still unknown but the more expensive GDDR4 memory will definitely improve the overall performance of the card.

Today it's all about highest end stuff, nearly. And as usual one of our main sources is Fuad Abazovic who is still very close to ATI it seems. Anyway, let's start:
The R600 powered cards will come in two flavours, one equipped with GDDR3 and the faster one with GDDR4 memory. The news is that the GDDR4 memory will be clocked at 2100MHz which is 100MHz faster than previously reported. The GPU core clock will remain at around 800MHz. But if you are keen on the GDDR4 board you will get a premium waiting time besides the premium price and performance - the GDDR3 card will be introduced first, a 'couple' of weeks earlier. As both GPU coolers for the two R600 variants will be the same its quite interesting to know that this advanced 2-slot air cooler is not louder than the Radeon X1950XTX cooling solution.

On February 16th of this year, NVIDIA went ahead and announced their new GPU computing client, CUDA. Over seven weeks later, we have yet to see so much as a beta of CUDA. And so, this means that NVIDIA, similar to the G80 Vista driver fiasco, has yet to deliver a product that they promised we'd see. The part about this that NVIDIA users probably hate the most is the lack of a GPU-based Folding@Home client. It seems that these days, everything except an NVIDIA system (even the PS3) can run a Folding@Home GPU client. This is an extreme opposite to ATI's GPU processing client, called "Stream", which has a large list of clients that can be used to accelerate programs using the GPU.

In the first part of Graphics card tidbits we covered TSMC's new 55nm process, NVIDIA's 32 hidden stream processors in its 8800 cards and the memory speed of the GDDR4 equipped R600 boards (2000MHz).
Now let's get it on: We learned that a tested R600 prototype is clocked at 800MHz (GPU) and scores 11400 3DMarks in 3DMark06 (probably the GDDR4 version). The PC this card was plugged into was equipped with a quad core Intel QX6700 and 2GB of memory. For the sake of comparison Fuad and his guys took a GeForce 8800 GTX in a similar system and got around 10600 3DMark out of it.
Another interesting news post at Fudzilla is about the GPU and memory speeds of the NVIDIA 8600 GT. While it's faster brother the 8600 GTS clocks at 675 MHz core / 2000 MHz memory the GT ends up at 540 MHz core and 1400 MHz memory. Both cards are based on the G84, come with a 128 bit memory controller, GDDR3 memory and will be introduced to the market at April 17th.
Last but not least one note about the G100, NVIDIA's future generation graphics chip. This one will support Cuda 2 which uses unified shaders for its scientific calculations.

On-Die also known as Direct-Die cooling got quite popular a couple of years ago. Watercooling addicts tried to get the best out of their selfmade cooling units and found water spilling around the CPU die itself to be competitive solution. But the obvious hurdles with leakage and complicated maintenance prevented companies from incorporating this technology.
However, I came across an interesting piece of information that reveals MSI has plans to sell special NVIDIA GeForce 8800GTX cards with an On-Die watercooling setup. Afterall it sounds quite unbelievable especially if you take a look at the second picture which shows the cooling unit at a higher resolution. But MSI clearly said so if the guys from HardTecs didn't mess with the translation. I will get in contact with them and see how they respond.
If we assume this is indeed an On-Die cooler then I would direct your attention to the last picture at the end of this post. This shows a watercooled R600 card and the pump, hoses and general appearance look very similar to the aforementioned 8800GTX board. Sadly both cards aren't available yet so the time will tell what exactly we are looking at here.

AMD/ATI has released this month's version of its display driver for the Radeon 9500 series and higher cards, taking the version number to 7.3. The driver is available for both Windows XP and Windows Vista, on 32-bit and 64-bit systems, with each requiring a different download. New features include OpenGL CrossFire support for Windows Vista, as well as other crossfire enhancements for Windows Vista which could see X1000 series cards gain performance improvements of up to 60%. There are obviously a number of other small issues that have been resolved in Vista and XP, but nothing too major.

Download links:

• Windows XP 32-bit
• Windows XP 64-bit
• Windows Vista 32-bit
• Windows Vista 64-bit

TSMC's 55nm Process and other Graphics card tidbits

The Taiwan Semiconductor Manufacturing Company (TSMC) announced yesterday that they readied there 55nm process technology. While a shrink from 65nm to 55nm doesn't sound much it still brings significant cost savings to companies like ATI who order thousands of GPUs. Using a new process technology in general means you can get more chips out of the same silicon wafer - that alone makes the chips cheaper. The switch to 55nm is a so called 'direct shrink' which will not require a whole redesign of the chip architecture. TSMC says chips would run with 10 to 20% less power at the same speed which in turn could be read as a higher working frequency at the same power level.

A recent interview with ATI/AMD at ExtremeTech shows some insight to future versions of Catalyst Control Center (CCC) software. AMD/ATI knows that previous versions have been lagging, complicated, and somewhat bloated. AMD made a good effort to fix this by a complete rewrite of CCC, but it still feels a bit lacking to some people. Instead of working on making the current CCC faster and more streamlined (like the old control panel), AMD/ATI is focusing on making one centralized application to manage all AMD/ATI products.

Says AMD representative Phil Rogers: "Longer term our goal is continue to improve the user experience and to move towards a single or central user interface where AMD customers can configure the majority of AMD product settings... It is our goal and vision to eventually have a single UI for all AMD products (graphics, CPU, chipset), but this is of course a major project, and it will be quite some time before we're able to release such a product"

This means that AMD hopes to make their control center much more featured, but this may prove to backfire upon release. With great power comes great responsibility, as Spiderman's Uncle Ben once said. And if AMD can't quite handle the responsibility, we may be looking at one complex, bloated driver interface.

At CeBIT, GECUBE demonstrated what it claims to be the fastest AGP board to date, the GC-HX195XTGA3-D3.

This board is based on a fully-fledged R580+ GPU, marketed as the Radeon X1950XT. However, the GPU clock has been changed from the default 625MHz to 648MHz. ATI Overdrive is supported, and this option in the Catalyst driver will increase clock all the way to 675MHz. The card uses 256MB of GDDR3 memory. Product manager Jeff Fu said the firm "will not abandon AGP users".

GECUBE also proudly announced what will make many AGP users very happy: AGP DX10.

PNY Technologies, the supplier and marketer of NVIDIA Quadro by PNY professional graphics boards announced today the immediate availability of next generation NVIDIA Quadro by PNY solutions based on new NVIDIA Quadro FX 4600 and FX 5600 graphics, and NVIDIA GSync genlock/frame lock and HD SDI options. These new ultra high-end professional graphics solutions meet the challenges of the most complex 3D design, DCC, visualization, scientific, and broadcast applications with a new unified architecture, Shader Model 4.0 technology, large frame buffers, and GPU computing for visualization technology. The new NVIDIA Quadro by PNY solutions include:

Following on from the launch of its X1950XT AGP 8X product, the Taiwanese graphics card company Info-Tek released today its GECUBE X1950XT X series for the PCI-Express 16X lane. The GECUBE X1950XT X series PCI-E also uses the ATI Radeon R580+(90nm) chip matched with 512MB of GDDR3 memory. The card is equipped with the company's proprietary Turbo Extreme Silent Fan, which is extremely quiet (18db when running in 3D mode). The GECUBE 1950XT X series is clocked at 628MHz core and supports the latest Shader Model 3.0 architecture. It also has 48 pixel pipelines, support for High Definition Content Protection (HDCP), Blu-ray, HD DVD, 1080i, and HDTV's high definition video output. This product has been certified by Windows Vista Premium WHQL (Windows Hardware Quality Labs), so you'll run the 3D Aero interface easily.

NVIDIA Corporation, the worldwide leader in programmable graphics processor technologies, yesterday unveiled a new line of professional graphics solutions: NVIDIA Quadro FX 4600, Quadro FX 5600, and NVIDIA Quadro Plex VCS Model IV. Armed with the largest increase in GPU power and functionality to date, these solutions are designed to help solve the world's most complex professional graphics challenges.

Tackling the extreme visualization challenges of the automotive styling and design, oil and gas exploration, medical imaging, visual simulation and training, scientific research, and advanced visual effects industries, these new Quadro solutions offer:

• Next-Generation Vertex and Pixel Programmability-Shader Model 4.0 enables a higher level of performance and ultra-realistic effects for OpenGL and DirectX 10 professional applications
• Largest Frame Buffers-Up to 1.5 GB frame buffers deliver throughput needed for interactive visualization and real-time processing of large textures and frames, enabling the superior quality and resolution for full-scene antialiasing (FSAA)
• New Unified Architecture-Industry-first unified architecture capable of dynamically allocating compute, geometry, shading and pixel processing power for optimized GPU performance
• GPU Computing for Visualization-Featuring NVIDIA CUDA technology, developers are, for the first time, able to tap into the high-performance computing power of Quadro to solve complex, visualization problems

While NVIDIA nearly got sued over their lack of Vista-ready drivers for their G80, ATI isn't exactly innocent. The Inquirer did a quick experiment to see if it was possible to configure a Vista workstation with an ATI FireGL graphics card. To their surprise, it wasn't. This is because ATI does not have any FireGL drivers compatible with Windows Vista. And unlike NVIDIA, they do not even have beta drivers out. While most of the gaming community is more likely to use an NVIDIA G80 than an ATI FireGL, this is still a major problem for anyone relying on a FireGL based workstation.

Zotac is one of the latest graphics card maker to enter the video market. It will appear at this year's CEBIT in Germany, at Booth B27 Hall 20. In fact, Zotac is subdivision company formed out of PC Partner, which will produce only NVIDIA GPU-based graphics cards. All our readers interested in the new Zotac brand, can click here and read the first Zotac GeForce 8800GTS 320MB review on the net.

Taipei, Taiwan - March 1, 2007 - TUL Corporation, a leading provider of graphic cards, today announced the PowerColor X1950 SCS3; the best performing noiseless graphic card in the world. While running passively, this model maintains the original specifications with core engine of 575MHz core, 1380MHz effective memory speed, 256MB GDDR3 and 36 pixel processors; it also comes equipped with VIVO, HDCP and Windows Vista ready.

Hong Kong 28th February, 2007 - InnoVISION Multimedia Limited introduce the Wave for passive cooling solutions to their Inno3D mainstream 7 series. It is the best solution for not only system integrators but also professional graphic designers who like to work in a quiet environment.

Club 3D, board partner for both ATI and NVIDIA, has launched a passively cooled Radeon X1950 Pro card with 256MB of onboard memory. The GPU core clock is set at 600 MHz, the memory ticks away at 1400 MHz. The card sports 2 DVI outputs.

As far as I am aware, the card uses Arctic Cooling's new heatsink, which has not been released to end consumers yet, so this is the only way to get your hands on one of them.

Samsung Touts 4 GHz Memory for Graphics Cards

Getting more speed is always nice - and Samsung is about to break the speed barrier yet again, pushing GDDR4 chips to 4 GHz and beyond. At the International Solid-State Circuits Conference (ISSCC), Samsung presented its new GDDR4 memory chips that operate at about 40% higher speed than GDDR4 was initially estimated to, but use more power.

4 GHz GDDR4 memory chips are only "available" in 512 MB capacities and were manufactured using 80 nm process technology. They were designed for a power supply voltage of 1.4 V - 2.1 V, reports PC Watch web-site. The data rate of 4 Gb/s (4 gigabit per second, or 4 GHz) was achieved with devices operating at 2.0 V, which is higher than Samsung's current-generation GDDR4 chips that can function at up to 1.9 V officially.

GDDR4 memory at 4.0 GHz delivers bandwidth of 16 GB/s and if such chips were used in today's graphics cards that have 256-bit memory bus, this would result in peak data bandwidth of 128 GB/s, two times more than the ATI Radeon X1950 XTX (the only graphics card on the market that uses GDDR4) can offer. For tomorrow's graphics boards that will have 512-bit memory access Samsung's new chips would give peak memory bandwidth of 256 GB/s, which is nearly three times more than 86.4 GB/s that the currently highest-performance graphics card - NVIDIA GeForce 8800 GTX - has.

Are we beginning to enter the era when GPU memory will be clocked many times higher than our CPUs?

AMD/ATI has released its latest version of the Catalyst drivers, which are used by the Radeon 9500 series and higher. There are 32-bit and 64-bit releases for both Windows XP and Windows Vista, and it is recommended that you upgrade to the latest version to solve any potential problems you may experience. You can download the drivers here. Please note that all versions of Windows require you to download a different driver.

POINT OF VIEW, well known for its range of NVIDIA based graphics cards, is launching today a special version of the GeForce 8800GTX graphics card. The Point of View GeForce 8800GTX - EXO EDITION is factory-overclocked version of GeForce 8800GTX with 768MB DDR3 memory running at 1900MHz and a core clock of 600MHz. This card is available from today, please click here to view the complete card specifications.

In celebration of the year of the pig, PowerColor is making a graphics card with a beautiful heatsink shaped like a pig. The midrange X1650Pro certainly isn't underpowered. Underneath the shiny pig heatsink is a RV535 clocked at 600MHz, paired with 256MB of GDDR3 clocked at 700MHz (DDR 1400MHz).