Gigabyte GeForce GTX 260 SO review

The GeForce GTX series 200 GPUs

Gigabyte announced the latest addition to its new Super Overclock Series. Built with an NVIDIA GTX 260 GPU, the GIGABYTE GV-N260SO-896I features 896MB GDDR3 memory with a 448-bit memory interface.

The standard clock frequencies for the GTX 260 and Core 216 version is 576MHz on the GPU, and 999MHz for the GDDR3 memory. All that on a 448-bit memory interface. The core clock for their SO model is 680 MHz, the shader processors at 1512 MHz and the memory is clocked at 2484 MHz.

The card is the 216SP version, an updated 55nm GPU based GeForce GTX 260. The 216SP versions, obviously referring to the 216 shader processors that are active and crunching data for you in that GPU, which is 24 shader processors more than the regular GTX 260 originally had. That's okay  really.

Each GPU for the Super Overclock series is cherry-picked for top performance, power efficiency and reliability using something that Gigabyte calls GPU Gantlet Sorting Process. Using advanced technical selection with combined with Ultra Durable VGA boards these boards should be top notch.

GPU Gauntlet Sorting
First, GIGABYTE's database analysis system evaluates the GPU core engine, shader engine and memory. If a processor doesn't meet the pre-defined standard, it will not qualify for the Super Overclock Series.

In addition, GIGABYTE's proprietary testing toolkit allows engineers to inspect and select the GPUs with the highest frequency. This program operates for 30 minutes and provides important data on the maximum overclocking ability when compared to a stock GPU. Once the Super Overclock point has been determined, engineers will boost the frequency to offer the highest factory default clock setting in the market.

Next, each Super Overclock Series GPU faces the Graphics benchmarks, FurMark and 3DMark Vantage, to measure performance and stability under an intense graphics load. A GPU that passes this stage will perform at a lower temperature and fan speed compared to a standard GPU.

Last but not least, engineers test the power switching and stability. The GPUs with the best power efficiency and lowest power consumption qualify for the Super Overclock Series. And GIGABYTE understands that premium graphics cards should not sound like a cement truck rolling down the freeway, so a large cooling fan provides for a quiet computing environment.

Thanks to Ultra Durable VGA 5 quality components, 2 oz copper PCB, first tier memory, Japanese solid capacitors, ferrite core cokes and low RDS on MOSFET, the Super Overclock Series provides for top performance.

NVIDIA's GeForce GTX series 200 includes both the standard GeForce GTX 260 and the GTX 260 SP216, all in several flavors as well.

The GTX series 200 GPUs are big, they have roughly 1400 million transistors. It was the biggest chip that NVIDIA has ever built. To compare, the GeForce 8800 only had roughly 700 Million processors. So that's roughly doubling up the previous transistor count. Obviously a big chunk of the transistors are being utilized for the shader cores. And shader cores this product surely has:

• 240 of them on the GeForce GTX 280.
• 216 cores on the GeForce GTX 260 SP216
• 192 cores on the GeForce GTX 260

The increased shader (stream) processor count, should provide a little boost to the shader compute power, other GPU denominators such as clock speeds remain the same.

The GeForce GTX 260 SP216 SKUs will feature 72 texturing units and 28 ROPs. The updated GPU is technically called G200-103-A2 (the older core was G200-100-A2). The card has a 448-bit (7x64-bit) wide GDDR3 memory bus with 896 MB of framebuffer/memory. It typically comes with 1.0 ns memory chips unless you stumble into OC models from difference board partners. So the extra 24 shader processor cores will give the product a little more bite. Especially in this price-range.

The power for the GTX 260 is fed by two six-pin connectors. Power consumption for this 10.5-inch board is 182W.