Introduction, Specifications & The Cards
The performance and capabilities of 3D graphics cards for the PC have been increasing at an exponential rate these past few years. High-end video cards that debuted at $500 just over a year ago, are now being surpassed in features and performance by cards being introduced at prices at or below $200. This unyielding drive to push for more power at the high-end has an a very attractive incremental benefit, however. After months, or even years in development, the technology introduced in flagship GPUs, like the GeForce 6800 for example, is leveraged and eventually scaled down to bring out a product with essentially the same feature set at a much more affordable price point. And as is often the case, other technological advances that debut over any given product's life span allow for a myriad of new capabilities. In the case of NVIDIA's new GeForce 6200 with TurboCache technology, PCI Express was the introductory technology that allowed NVIDIA to bring out a new GPU with features that match their flagship video cards, that require no more than 16MB of local memory. This is possible because NVIDIA's "TurboCache" technology enabled direct rendering to system memory, eliminating the need for large amounts of local memory on the card itself. The GeForce 6200 with TurboCache is NVIDIA's latest entry-level video card, targeted squarely at uses looking to affordably upgrade from a sub-par integrated graphics solution.
|CINEFX 3.0 SHADING ARCHITECTURE
64-BIT TEXTURE FILTERING AND BLENDING
INTELLISAMPLE 3.0 TECHNOLOGY
|ULTRASHADOW II TECHNOLOGY
NVIDIA DIGITAL VIBRANCE CONTROL (DVC) 3.0
We'll actually be taking a look at two different GeForce 6200 cards with TurboCache in this showcase. One has a single discreet 16MB Samsung memory chip installed, the other has two 16MB chips installed for a total of 32MB of local memory. Other than that single difference though, both of the cards are physically identical. Our reference GeForce 6200 with TurboCache cards are native PCI Express parts, designed from the beginning for power efficiency and low-cost. The PCB is relatively devoid of components when compared to today's high-end video cards, and the GPU, which is built on a .11 micron manufacturing process, requires only passive cooling at its default speed of 350MHz. The local memory installed on the cards is clocked at 350MHz (700MHz DDR). At these speeds both of the GeForce 6200 cards with TurboCache have theoretical peak fillrates of 1.4GPixels/s, but calculating memory bandwidth is another story altogether.
Memory Bandwidth Calculations:
GeForce 6200s with TurboCache that have only a single memory chip, are limited to only a 32-bit memory bus. So, at 350MHz, this means a 16MB card has 2.8GB/s of bandwidth available to local memory. The 32MB card, because it is equipped with two chips, however, has a 64-bit memory bus for a total of 5.6GB/s of memory bandwidth to local memory. But because the nature of NVIDIA's TurboCache technology allows these cards to render directly to system memory as well, they also can take full advantage of the 8GB/s of bandwidth offered up by a PCI Express X16 graphics slot. Due to this capability, NVIDIA is marketing GeForce 6200 TurboCache 16-TC/128MB as having a peak of 10.8GB/s of memory bandwidth at its disposal. And the GeForce 6200 TurboCache 32-TC/128MB cards as having a total bandwidth of 13.6GB/s. This is important to note, because distinguishing cards in retail channels or on the store shelf may be difficult. GeForce 6200s with TurboCache support up to a 128MB frame buffer when installed on a system with 512MB of RAM (the minimum requirement). So cards will be branded as "Supporting 128MB", regardless of how much local memory is installed. They will be distinguishable however, by the total amount of peak bandwidth offered up by the different configurations.