First Look: GeForce GTX 780
GeForce GTX 780 is a premium discrete graphics card for desktop computer systems, available for $649.99 online. NVIDIA has built the GeForce GTX 780 for high-performance hardware enthusiasts and hard-core gamers wanting to play PC video games at their maximum graphics quality settings using the highest screen resolution possible. It’s a small niche market that few can claim, but also one that every PC gamer dreams of enjoying.
Like the GeForce GTX TITAN it’s modeled after, GeForce GTX 780 is a dual-slot video card that measures 10.5″ long and 4.4″ wide. Sharing a nearly identical appearance, GTX 780 also features the same GK110 GPU used in the top-end GeForce GTX TITAN. Similarly, GTX 780 also supports the following NVIDIA technologies: GPU Boost 2.0, 3D Vision, CUDA, DirectX 11, PhysX, TXAA, Adaptive VSync, FXAA, 3D Vision Surround, and SLI.
In addition to a new and improved NVIDIA GPU Boost 2.0 technology, GeForce GTX 780 also delivers refinements to the user experience. Smoother FXAA and adaptive vSync technology results in less chop, stutter, and tearing in on-screen motion. Adaptive vSync technology adjusts the monitor’s refresh rate whenever the FPS rate becomes too low to properly sustain vertical sync (when enabled), thereby reducing stutter and tearing artifacts. Finally, NVIDIA TXAA offers gamers a film-style anti-aliasing technique with a mix of hardware post-processing, custom CG file style AA resolve, and an optional temporal component for better image quality.
Fashioned from technology developed for the NVIDIA GeForce GTX TITAN, engineers adapted a slightly tweaked design for GeForce GTX 780. The two cards look virtually identical, save for the model name branded near the header. A single rearward 60mm (2.4″) blower motor fan is offset from the cards surface to take advantage of a chamfered depression, helping GTX 780 to draw cool air into the angled fan shroud. This design allows more air to reach the intake whenever two or more video cards are combined in close-proximity SLI configurations. Add-in card partners with engineering resources may incorporate their own cooling solution into GTX 780, although there seems little benefit from eschewing NVIDIA’s cool-running reference design.
GeForce GTX 780 offers two simultaneously functional dual-link DVI (DL-DVI) connections, a full-size HDMI 1.4a output, and a DisplayPort 1.2 connection. Add-in partners may elect to remove or possibly further extend any of these video interfaces, but most will likely retain the original reference board engineering. Only one of these video cards is necessary to drive triple-displays and NVIDIA 3D-Vision Surround functionality, when using both DL-DVI and either the HDMI or DP connection for third output. All of these video interfaces consume exhaust-vent real estate, but this has very little impact on cooling because the 28nm Kepler GPU generates much less heat than past GeForce processors, and also because NVIDIA intentionally distances the heatsink far enough from these vents to equalize exhaust pressure.
As with past-generation GeForce GTX series graphics cards, the GeForce GTX 780 is capable of two-card “Quad-SLI” configurations. Because GeForce GTX 780 is PCI-Express 3.0 compliant device, the added bandwidth could potentially come into demand as future games and applications make use of these resources. Most games will be capable of utilizing the highest possible graphics quality settings using only a single GeForce GTX 780 video card, but multi-card SLI/Quad-SLI configurations are perfect for extreme gamers wanting to experience ultra-performance video games played at their highest quality settings with all the bells and whistles enabled across multiple monitors.
Specified at 250W Thermal Design Power output, the Kepler GPU in GeForce GTX 780 operates much more efficiently than NVIDIA’s previous generation GPUs. Since TDP demands have been reduced GTX 780 runs cooler during normal operation, and has move power available for Boost 2.0 requests. NVIDIA has added a “GeForce GTX” logo along the exposed side video card, and the LED backlit letters glow green when the system is powered on. GeForce GTX 780 requires an 8-pin and 6-pin PCIe power connectors for operation, allowing NVIDIA to recommend a modest 600W power supply for computer systems equipped with one of these video cards.
By tradition, NVIDIA’s GeForce GTX series offers enthusiast-level performance with features like multi-card SLI pairing. More recently, the GTX family has included GPU Boost application-driven variable overclocking technology – now into GPU Boost 2.0. The GeForce GTX 780 graphics card keeps with tradition in terms of performance by producing single-GPU frame rates second to only GTX TITAN. Of course, NVIDIA’s Kepler GPU architecture adds proprietary features to both versions, such as: 3D Vision, Adaptive Vertical Sync, multi-display Surround, PhysX, and TXAA antialiasing.
GeForce GTX 780’s GK110 graphics processor ships with 12 SMX units: good for 2304 CUDA cores clocked to 863 MHz that boost to 902 MHz. The Boost Clock speed is based on the average GeForce GTX 780 card running a wide variety of games and applications. The memory subsystem of GeForce GTX 780 consists of six 64-bit memory controllers combined to create a 384-bit lane, which produce 288.4 GB/s bandwidth from 3GB of GDDR5 memory operating at 6008MHz data rate. GTX 780’s fill rate reaches 165.7 GigaTexels per second across the backwards-compatible PCI-Express 3.0 compliant graphics interface.
GTX 780’s exposed printed circuit board reveals an otherwise sparse PCB backside with few exciting features. Many of NVIDIA’s latest products have used less and less PCB real estate, with GTX models occasionally needing nothing more than space for the fan. Because of the optimized Kepler GPU, GeForce GTX 780 does not benefit from any surface heatsink or cooling plates.
In the next section, we detail our test methodology and give specifications for all of the benchmarks and equipment used in our testing process…