By Olin Coles
Manufacturer: NVIDIA Corporation
Product Name: GeForce GTX 780 Graphics Card
Price: Starting at $649.99 (Amazon | Newegg)
Full Disclosure: The product sample used in this article has been provided by NVIDIA.
NVIDIA’s GeForce GTX TITAN allowed gamers to challenge any video game they choose with the highest quality settings possible, but in limited supply and high price tag ($1020 Newegg). For many players, their games really only needed half as much power and memory from a video card. Enter NVIDIA GeForce GTX 780: built from GTX TITAN to deliver 3GB of GDDR5 video frame buffer memory, and 2304 CUDA cores from the GK110 GPU that reach 900 MHz using NVIDIA Boost 2.0 technology. In this article, Benchmark Reviews tests and compares the NVIDIA GeForce GTX 780 graphics card using several highly-demanding DX11 video games, such as Metro: Last Light, Batman: Arkham City, and Battlefield 3.
NVIDIA’s GeForce GTX 780 is built using the same GK110 GPU found inside GTX TITAN, along with 3072MB of GDDR5 memory running at the same clock speeds. GTX TITAN delivered 2688 cores clocked at 836/876 boost, which NVIDIA revised to 2304 cores at 863/900 for GeForce GTX 780. Both cards share the same supplementary power connector requirements: 8-pin + 6-pin, as well as the identical 250-watt TDP. Coincidentally, GeForce GTX 780 features twice as many CUDA cores and GDDR5 memory. GeForce GTX 780 has been designed with enough GPU speed and power to outperform the GTX 580 by 70% and GTX 680 by almost 38%.
There are three platforms to enjoy video games: portable, console, and PC. While smartphone and tablet devices can play games, graphics rarely go beyond simple 2D. Gaming consoles take detail quality a few steps farther, but pale in comparison to the hyper-realistic gaming experience available to high-end PC graphics cards. While game developers might not consider PC gaming as lucrative as entertainment consoles, companies like NVIDIA use desktop graphics technology to set the benchmark for smaller more compact GPU designs that make it into notebooks, tablets, and smartphone devices.
Source: NVIDIA
The GeForce GTX 780 features the same GK110 GPU that was used in the record-breaking GeForce GTX TITAN. With 2304 CUDA Cores at its disposal, the GeForce GTX 780 features 50% more CUDA Cores than the GeForce GTX 680, and thanks to its 3GB frame buffer, 50% more memory as well. And to ensure high frame rates at the maximum screen resolution of your monitor, GeForce GTX 780’s 384-bit memory interface provides up to 288.4GB/sec of peak memory bandwidth to the GPU. The GeForce GTX 780 offers a tremendous performance upgrade. Gamers upgrading from a GeForce GTX 580 will experience up to a 70% performance improvement, and the GTX 780 is even up to 34% faster than last year’s GeForce GTX 680.
GeForce GTX 780 ships with 12 SMX units providing 2304 CUDA Cores. The memory subsystem of GeForce GTX 780 consists of six 64-bit memory controllers (384-bit) with 3GB of GDDR5 memory. The base clock speed of the GeForce GTX 780 is 863MHz. The typical Boost Clock speed is 900MHz. The Boost Clock speed is based on the average GeForce GTX 780 card running a wide variety of games and applications. Note that the actual Boost clock will vary from game-to-game depending on actual system conditions. GeForce GTX 780’s memory speed is 6008MHz data rate.
The GeForce GTX 780 reference board measures 10.5″ in length. Display outputs include two dual-link DVIs, one HDMI and one DisplayPort connector. One 8-pin PCIe power connector and one 6-pin PCIe power connector are required for operation.
NVIDIA GPU Boost technology automatically increases the GPU’s clock frequency in order to improve performance. GPU Boost works in the background, dynamically adjusting the GPU’s graphics clock speed based on GPU operating conditions.
Originally GPU Boost was designed to reach the highest possible clock speed while remaining within a predefined power target. However, after careful evaluation NVIDIA engineers determined that GPU temperature is often a bigger inhibitor of performance than GPU power. Therefore for Boost 2.0, we’ve switched from boosting clock speeds based on a GPU power target, to a GPU temperature target. This new temperature target is 80 degrees Celsius.
As a result of this change, the GPU will automatically boost to the highest clock frequency it can achieve as long as the GPU temperature remains at 80C. Boost 2.0 constantly monitors GPU temperature, adjusting the GPU’s clock and its voltage on-the-fly to maintain this temperature.
In addition to switching from a power-based boost target to a temperature-based target, with GPU Boost 2.0 we’re also providing end users with more advanced controls for tweaking GPU Boost behavior. Using software tools provided by NVIDIA add-in card partners, end users can adjust the GPU temperature target precisely to their liking. If a user wants his GeForce GTX 780 board to boost to higher clocks for example, he can simply adjust the temperature target higher (for example from 80C, to 85C). The GPU will then boost to higher clock speeds until it reaches the new temperature target.
Besides adjusting the temperature target, Boost 2.0 also provides users with more powerful fan control. The GPU’s fan curve is completely adjustable, so you can adjust the GPU’s fan to operate at different speeds based on your own preferences.
Adaptive Temperature Controller
With GPU Boost 2.0, the GPU will boost to the highest clock speed it can achieve while operating at 80C. Boost 2.0 will dynamically adjust the GPU fan speed up or down as needed to attempt to maintain this temperature. While we’ve attempted to minimize fan speed variation as much as possible in prior GPUs, fan speeds did occasionally fluctuate.
For GeForce GTX 780, we’ve developed an all-new fan controller that uses an adaptive temperature filter with an RPM and temperature targeted control algorithm to eliminate the unnecessary fan fluctuations that contribute to fan noise, providing a smoother acoustic experience.
GeForce Experience is a new application from NVIDIA that optimizes your PC in two key ways. First, it maximizes your game performance and game compatibility by automatically downloading the latest GeForce Game Ready drivers. Second, GeForce Experience intelligently optimizes graphics settings for all your favorite games based on your hardware configuration.
Shadow Play
Utilizing the H.264 video encoder built-in to every Kepler GPU, ShadowPlay works in the background, seamlessly recording your last 20 minutes of gameplay footage, or if you’d like to record your latest StarCraft match, ShadowPlay can record that too.
Compared to software-based video encoders like FRAPS, ShadowPlay takes less of a performance hit, so you can enjoy your games while you’re recording.
Download NVIDIA GeForce Experience here: geforce.com/drivers/geforce-experience/download
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…
The Microsoft DirectX-11 graphics API is native to the Microsoft Windows 7 Operating System, and will be the primary O/S for our test platform. DX11 is also available as a Microsoft Update for the Windows Vista O/S, so our test results apply to both versions of the Operating System. The majority of benchmark tests used in this article are comparative to DX11 performance, however some high-demand DX10 tests have also been included.
In each benchmark test there is one ‘cache run’ that is conducted, followed by five recorded test runs. Results are collected at each setting with the highest and lowest results discarded. The remaining three results are averaged, and displayed in the performance charts on the following pages.
A combination of synthetic and video game benchmark tests have been used in this article to illustrate relative performance among graphics solutions. Our benchmark frame rate results are not intended to represent real-world graphics performance, as this experience would change based on supporting hardware and the perception of individuals playing the video game.
- Motherboard: ASUS P9X79 Deluxe Motherboard (Intel X79 Express)
- Processor: Intel Core i7-3960X Extreme Edition (six cores/3300 MHz)
- System Memory: G.SKILL Ripjaws-Z 32GB DDR3-1600
- Power Supply Unit: OCZ Z-Series Gold 850W OCZZ850
- Monitor: ASUS VG278H 27″ Widescreen Monitor
- Crysis Warhead v1.1 with HOC Benchmark
- Settings: Airfield Demo, Very High Quality, 4x AA, 16x AF
- 3DMark11 Professional Edition by Futuremark
- Settings: Performance Level Preset, 1280×720, 1x AA, Trilinear Filtering, Tessellation level 5)
- Aliens vs Predator Benchmark 1.0
- Settings: Very High Quality, 4x AA, 16x AF, SSAO, Tessellation, Advanced Shadows
- Batman: Arkham City
- Settings: 8x AA, 16x AF, MVSS+HBAO, High Tessellation, Extreme Detail, PhysX Disabled
- BattleField 3
- Settings: Ultra Graphics Quality, FOV 90, 180-second Fraps Scene
- Lost Planet 2 Benchmark 1.0
- Settings: Benchmark B, 4x AA, Blur Off, High Shadow Detail, High Texture, High Render, High DirectX 11 Features
- Metro 2033 Benchmark
- Settings: Very-High Quality, 4x AA, 16x AF, Tessellation, PhysX Disabled
- Unigine Heaven Benchmark 3.0
- Settings: DirectX 11, High Quality, Extreme Tessellation, 16x AF, 4x AA
| Graphics Processing Clusters | 4 or 5 |
| Streaming Multiprocessors | 12 |
| CUDA Cores | 2304 |
| Texture Units | 192 |
| ROP Units | 48 |
| Base Clock | 863 MHz |
| Boost Clock | 900 MHz |
| Memory Clock (Data rate) | 6008 MHz |
| L2 Cache Size | 1536K |
| Total Video Memory | 3072MB GDDR5 |
| Memory Interface | 384-bit |
| Total Memory Bandwidth | 288.4 GB/s |
| Texture Filtering Rate (Bilinear) | 165.7 GigaTexels/sec |
| Fabrication Process | 28 nm |
| Transistor Count | 7.1 Billion |
| Connectors | 2 x Dual-Link DVI1 x HDMI 1 x DisplayPort |
| Form Factor | Dual Slot |
| Power Connectors | One 8-pin and one 6-pin |
| Recommended Power Supply | 600 Watts |
| Thermal Design Power (TDP) | 250 Watts |
| Thermal Threshold | 95° C |
| Graphics Card | Radeon HD6970 | GeForce GTX670 | Radeon HD7970 | GeForce GTX680 | GeForce GTX780 | GeForce GTX590 | Radeon HD6990 | GeForce GTX690 |
| GPU Cores | 1536 | 1344 | 2048 | 1536 | 2304 | 1024 | 3072 Total | 3072 |
| Core Clock (MHz) | 880 | 915 | 925 | 1006 | 863 | 608 | 830/880 | 915 |
| Shader Clock (MHz) | N/A | 980 Boost | N/A | Boost 1058 | Boost 902 | 1215 | N/A | Boost 1020 |
| Memory Clock (MHz) | 1375 | 1502 | 1375 | 1502 | 1502 | 854 | 1250 | 1502 |
| Memory Amount | 2048MB GDDR5 | 2048MB GDDR5 | 3072MB GDDR5 | 2048MB GDDR5 | 3072MB GDDR5 | 3072 GDDR5 | 4096MB GDDR5 | 4096MB GDDR5 |
| Memory Interface | 256-bit | 256-bit | 384-bit | 256-bit | 384-bit | 384-bit | 256-bit | 256-bit |
- AMD Radeon HD 6970 (880 MHz GPU/1375 MHz vRAM – AMD Catalyst 13.3)
- NVIDIA GeForce GTX 670 (915 MHz GPU/980 MHz Boost/1502 MHz vRAM – Forceware 306.23)
- NVIDIA GeForce GTX 680 (1006 MHz GPU/1059 MHz Boost/1502 MHz vRAM – Forceware 301.10)
- AMD Radeon HD 7970 (925 MHz GPU/1375 MHz vRAM – AMD Catalyst 13.6 Beta 2)
- NVIDIA GeForce GTX 590 (772 MHz GPU/1544 MHz Shader/1002 MHz vRAM – Forceware 301.10)
- AMD Radeon HD 6990 (830/880 MHz GPU/1250 MHz vRAM – AMD Catalyst 13.3)
- NVIDIA GeForce GTX 780 (869 MHz GPU/902 MHz Boost/1502 MHz vRAM – Forceware 320.18)
- NVIDIA GeForce GTX 690 (915 MHz GPU/1020 MHz Boost/1502 MHz vRAM – Forceware 301.33)
Crysis Warhead is an expansion pack based on the original Crysis video game. Crysis Warhead is based in the future, where an ancient alien spacecraft has been discovered beneath the Earth on an island east of the Philippines. Crysis Warhead uses a refined version of the CryENGINE2 graphics engine. Like Crysis, Warhead uses the Microsoft Direct3D 10 (DirectX-10) API for graphics rendering.
Benchmark Reviews uses the HOC Crysis Warhead benchmark tool to test and measure graphic performance using the Airfield 1 demo scene. This short test places a high amount of stress on a graphics card because of detailed terrain and textures, but also for the test settings used. Using the DirectX-10 test with Very High Quality settings, the Airfield 1 demo scene receives 4x anti-aliasing and 16x anisotropic filtering to create maximum graphic load and separate the products according to their performance.
Using the highest quality DirectX-10 settings with 4x AA and 16x AF, only the most powerful graphics cards are expected to perform well in our Crysis Warhead benchmark tests. DirectX-11 extensions are not supported in Crysis: Warhead, and SSAO is not an available option.
- Crysis Warhead v1.1 with HOC Benchmark
- Settings: Airfield Demo, Very High Quality, 4x AA, 16x AF
Crysis Warhead Benchmark Test Results
| Graphics Card | Radeon HD6970 | GeForce GTX670 | Radeon HD7970 | GeForce GTX680 | GeForce GTX780 | GeForce GTX590 | Radeon HD6990 | GeForce GTX690 |
| GPU Cores | 1536 | 1344 | 2048 | 1536 | 2304 | 1024 | 3072 Total | 3072 |
| Core Clock (MHz) | 880 | 915 | 925 | 1006 | 863 | 608 | 830/880 | 915 |
| Shader Clock (MHz) | N/A | 980 Boost | N/A | Boost 1058 | Boost 902 | 1215 | N/A | Boost 1020 |
| Memory Clock (MHz) | 1375 | 1502 | 1375 | 1502 | 1502 | 854 | 1250 | 1502 |
| Memory Amount | 2048MB GDDR5 | 2048MB GDDR5 | 3072MB GDDR5 | 2048MB GDDR5 | 3072MB GDDR5 | 3072 GDDR5 | 4096MB GDDR5 | 4096MB GDDR5 |
| Memory Interface | 256-bit | 256-bit | 384-bit | 256-bit | 384-bit | 384-bit | 256-bit | 256-bit |
FutureMark 3DMark11 is the latest addition the 3DMark benchmark series built by FutureMark corporation. 3DMark11 is a PC benchmark suite designed to test the DirectX-11 graphics card performance without vendor preference. Although 3DMark11 includes the unbiased Bullet Open Source Physics Library instead of NVIDIA PhysX for the CPU/Physics tests, Benchmark Reviews concentrates on the four graphics-only tests in 3DMark11 and uses them with medium-level ‘Performance’ presets.
The ‘Performance’ level setting applies 1x multi-sample anti-aliasing and trilinear texture filtering to a 1280x720p resolution. The tessellation detail, when called upon by a test, is preset to level 5, with a maximum tessellation factor of 10. The shadow map size is limited to 5 and the shadow cascade count is set to 4, while the surface shadow sample count is at the maximum value of 16. Ambient occlusion is enabled, and preset to a quality level of 5.
- Futuremark 3DMark11 Professional Edition
- Settings: Performance Level Preset, 1280×720, 1x AA, Trilinear Filtering, Tessellation level 5)
3DMark11 Benchmark Test Results
| Graphics Card | Radeon HD6970 | GeForce GTX670 | Radeon HD7970 | GeForce GTX680 | GeForce GTX780 | GeForce GTX590 | Radeon HD6990 | GeForce GTX690 |
| GPU Cores | 1536 | 1344 | 2048 | 1536 | 2304 | 1024 | 3072 Total | 3072 |
| Core Clock (MHz) | 880 | 915 | 925 | 1006 | 863 | 608 | 830/880 | 915 |
| Shader Clock (MHz) | N/A | 980 Boost | N/A | Boost 1058 | Boost 902 | 1215 | N/A | Boost 1020 |
| Memory Clock (MHz) | 1375 | 1502 | 1375 | 1502 | 1502 | 854 | 1250 | 1502 |
| Memory Amount | 2048MB GDDR5 | 2048MB GDDR5 | 3072MB GDDR5 | 2048MB GDDR5 | 3072MB GDDR5 | 3072 GDDR5 | 4096MB GDDR5 | 4096MB GDDR5 |
| Memory Interface | 256-bit | 256-bit | 384-bit | 256-bit | 384-bit | 384-bit | 256-bit | 256-bit |
Aliens vs. Predator is a science fiction first-person shooter video game, developed by Rebellion, and published by Sega for Microsoft Windows, Sony PlayStation 3, and Microsoft Xbox 360. Aliens vs. Predator utilizes Rebellion’s proprietary Asura game engine, which had previously found its way into Call of Duty: World at War and Rogue Warrior. The self-contained benchmark tool is used for our DirectX-11 tests, which push the Asura game engine to its limit.
In our benchmark tests, Aliens vs. Predator was configured to use the highest quality settings with 4x AA and 16x AF. DirectX-11 features such as Screen Space Ambient Occlusion (SSAO) and tessellation have also been included, along with advanced shadows.
- Aliens vs Predator
- Settings: Very High Quality, 4x AA, 16x AF, SSAO, Tessellation, Advanced Shadows
Aliens vs Predator Benchmark Test Results
| Graphics Card | Radeon HD6970 | GeForce GTX670 | Radeon HD7970 | GeForce GTX680 | GeForce GTX780 | GeForce GTX590 | Radeon HD6990 | GeForce GTX690 |
| GPU Cores | 1536 | 1344 | 2048 | 1536 | 2304 | 1024 | 3072 Total | 3072 |
| Core Clock (MHz) | 880 | 915 | 925 | 1006 | 863 | 608 | 830/880 | 915 |
| Shader Clock (MHz) | N/A | 980 Boost | N/A | Boost 1058 | Boost 902 | 1215 | N/A | Boost 1020 |
| Memory Clock (MHz) | 1375 | 1502 | 1375 | 1502 | 1502 | 854 | 1250 | 1502 |
| Memory Amount | 2048MB GDDR5 | 2048MB GDDR5 | 3072MB GDDR5 | 2048MB GDDR5 | 3072MB GDDR5 | 3072 GDDR5 | 4096MB GDDR5 | 4096MB GDDR5 |
| Memory Interface | 256-bit | 256-bit | 384-bit | 256-bit | 384-bit | 384-bit | 256-bit | 256-bit |
Batman: Arkham City is a 3d-person action game that adheres to story line previously set forth in Batman: Arkham Asylum, which launched for game consoles and PC back in 2009. Based on an updated Unreal Engine 3 game engine, Batman: Arkham City enjoys DirectX 11 graphics which uses multi-threaded rendering to produce life-like tessellation effects. While gaming console versions of Batman: Arkham City deliver high-definition graphics at either 720p or 1080i, you’ll only get the high-quality graphics and special effects on PC.
In an age when developers give game consoles priority over PC, it’s becoming difficult to find games that show off the stunning visual effects and lifelike quality possible from modern graphics cards. Fortunately Batman: Arkham City is a game that does amazingly well on both platforms, while at the same time making it possible to cripple the most advanced graphics card on the planet by offering extremely demanding NVIDIA 32x CSAA and full PhysX capability. Also available to PC users (with NVIDIA graphics) is FXAA, a shader based image filter that achieves similar results to MSAA yet requires less memory and processing power.
Batman: Arkham City offers varying levels of PhysX effects, each with its own set of hardware requirements. You can turn PhysX off, or enable ‘Normal levels which introduce GPU-accelerated PhysX elements such as Debris Particles, Volumetric Smoke, and Destructible Environments into the game, while the ‘High’ setting adds real-time cloth and paper simulation. Particles exist everywhere in real life, and this PhysX effect is seen in many aspects of game to add back that same sense of realism. For PC gamers who are enthusiastic about graphics quality, don’t skimp on PhysX. DirectX 11 makes it possible to enjoy many of these effects, and PhysX helps bring them to life in the game.
- Batman: Arkham City
- Settings: 8x AA, 16x AF, MVSS+HBAO, High Tessellation, Extreme Detail, PhysX Disabled
Batman: Arkham City Benchmark Test Results
| Graphics Card | Radeon HD6970 | GeForce GTX670 | Radeon HD7970 | GeForce GTX680 | GeForce GTX780 | GeForce GTX590 | Radeon HD6990 | GeForce GTX690 |
| GPU Cores | 1536 | 1344 | 2048 | 1536 | 2304 | 1024 | 3072 Total | 3072 |
| Core Clock (MHz) | 880 | 915 | 925 | 1006 | 863 | 608 | 830/880 | 915 |
| Shader Clock (MHz) | N/A | 980 Boost | N/A | Boost 1058 | Boost 902 | 1215 | N/A | Boost 1020 |
| Memory Clock (MHz) | 1375 | 1502 | 1375 | 1502 | 1502 | 854 | 1250 | 1502 |
| Memory Amount | 2048MB GDDR5 | 2048MB GDDR5 | 3072MB GDDR5 | 2048MB GDDR5 | 3072MB GDDR5 | 3072 GDDR5 | 4096MB GDDR5 | 4096MB GDDR5 |
| Memory Interface | 256-bit | 256-bit | 384-bit | 256-bit | 384-bit | 384-bit | 256-bit | 256-bit |
In Battlefield 3, players step into the role of the Elite U.S. Marines. As the first boots on the ground, players will experience heart-pounding missions across diverse locations including Paris, Tehran and New York. As a U.S. Marine in the field, periods of tension and anticipation are punctuated by moments of complete chaos. As bullets whiz by, walls crumble, and explosions force players to the grounds, the battlefield feels more alive and interactive than ever before.
The graphics engine behind Battlefield 3 is called Frostbite 2, which delivers realistic global illumination lighting along with dynamic destructible environments. The game uses a hardware terrain tessellation method that allows a high number of detailed triangles to be rendered entirely on the GPU when near the terrain. This allows for a very low memory footprint and relies on the GPU alone to expand the low res data to highly realistic detail.
Using Fraps to record frame rates, our Battlefield 3 benchmark test uses a three-minute capture on the ‘Secure Parking Lot’ stage of Operation Swordbreaker. Relative to the online multiplayer action, these frame rate results are nearly identical to daytime maps with the same video settings.
- BattleField 3
- Settings: Ultra Graphics Quality, FOV 90, 180-second Fraps Scene
Battlefield 3 Benchmark Test Results
| Graphics Card | Radeon HD6970 | GeForce GTX670 | Radeon HD7970 | GeForce GTX680 | GeForce GTX780 | GeForce GTX590 | Radeon HD6990 | GeForce GTX690 |
| GPU Cores | 1536 | 1344 | 2048 | 1536 | 2304 | 1024 | 3072 Total | 3072 |
| Core Clock (MHz) | 880 | 915 | 925 | 1006 | 863 | 608 | 830/880 | 915 |
| Shader Clock (MHz) | N/A | 980 Boost | N/A | Boost 1058 | Boost 902 | 1215 | N/A | Boost 1020 |
| Memory Clock (MHz) | 1375 | 1502 | 1375 | 1502 | 1502 | 854 | 1250 | 1502 |
| Memory Amount | 2048MB GDDR5 | 2048MB GDDR5 | 3072MB GDDR5 | 2048MB GDDR5 | 3072MB GDDR5 | 3072 GDDR5 | 4096MB GDDR5 | 4096MB GDDR5 |
| Memory Interface | 256-bit | 256-bit | 384-bit | 256-bit | 384-bit | 384-bit | 256-bit | 256-bit |
Lost Planet 2 is the second installment in the saga of the planet E.D.N. III, ten years after the story of Lost Planet: Extreme Condition. The snow has melted and the lush jungle life of the planet has emerged with angry and luscious flora and fauna. With the new environment comes the addition of DirectX-11 technology to the game.
Lost Planet 2 takes advantage of DX11 features including tessellation and displacement mapping on water, level bosses, and player characters. In addition, soft body compute shaders are used on ‘Boss’ characters, and wave simulation is performed using DirectCompute. These cutting edge features make for an excellent benchmark for top-of-the-line consumer GPUs.
The Lost Planet 2 benchmark offers two different tests, which serve different purposes. This article uses tests conducted on benchmark B, which is designed to be a deterministic and effective benchmark tool featuring DirectX 11 elements.
- Lost Planet 2 Benchmark 1.0
- Settings: Benchmark B, 4x AA, Blur Off, High Shadow Detail, High Texture, High Render, High DirectX 11 Features
Lost Planet 2 Benchmark Test Results
| Graphics Card | Radeon HD6970 | GeForce GTX670 | Radeon HD7970 | GeForce GTX680 | GeForce GTX780 | GeForce GTX590 | Radeon HD6990 | GeForce GTX690 |
| GPU Cores | 1536 | 1344 | 2048 | 1536 | 2304 | 1024 | 3072 Total | 3072 |
| Core Clock (MHz) | 880 | 915 | 925 | 1006 | 863 | 608 | 830/880 | 915 |
| Shader Clock (MHz) | N/A | 980 Boost | N/A | Boost 1058 | Boost 902 | 1215 | N/A | Boost 1020 |
| Memory Clock (MHz) | 1375 | 1502 | 1375 | 1502 | 1502 | 854 | 1250 | 1502 |
| Memory Amount | 2048MB GDDR5 | 2048MB GDDR5 | 3072MB GDDR5 | 2048MB GDDR5 | 3072MB GDDR5 | 3072 GDDR5 | 4096MB GDDR5 | 4096MB GDDR5 |
| Memory Interface | 256-bit | 256-bit | 384-bit | 256-bit | 384-bit | 384-bit | 256-bit | 256-bit |
Metro 2033 is an action-oriented video game with a combination of survival horror, and first-person shooter elements. The game is based on the novel Metro 2033 by Russian author Dmitry Glukhovsky. It was developed by 4A Games in Ukraine and released in March 2010 for Microsoft Windows. Metro 2033 uses the 4A game engine, developed by 4A Games. The 4A Engine supports DirectX-9, 10, and 11, along with NVIDIA PhysX and GeForce 3D Vision.
The 4A engine is multi-threaded in such that only PhysX had a dedicated thread, and uses a task-model without any pre-conditioning or pre/post-synchronizing, allowing tasks to be done in parallel. The 4A game engine can utilize a deferred shading pipeline, and uses tessellation for greater performance, and also has HDR (complete with blue shift), real-time reflections, color correction, film grain and noise, and the engine also supports multi-core rendering.
Metro 2033 featured superior volumetric fog, double PhysX precision, object blur, sub-surface scattering for skin shaders, parallax mapping on all surfaces and greater geometric detail with a less aggressive LODs. Using PhysX, the engine uses many features such as destructible environments, and cloth and water simulations, and particles that can be fully affected by environmental factors.
NVIDIA has been diligently working to promote Metro 2033, and for good reason: it’s one of the most demanding PC video games we’ve ever tested. When their flagship GeForce GTX 480 struggles to produce 27 FPS with DirectX-11 anti-aliasing turned two to its lowest setting, you know that only the strongest graphics processors will generate playable frame rates. All of our tests enable Advanced Depth of Field and Tessellation effects, but disable advanced PhysX options.
- Metro 2033 Benchmark
- Settings: Very-High Quality, 4x AA, 16x AF, Tessellation, PhysX Disabled
Metro 2033 Benchmark Test Results
| Graphics Card | Radeon HD6970 | GeForce GTX670 | Radeon HD7970 | GeForce GTX680 | GeForce GTX780 | GeForce GTX590 | Radeon HD6990 | GeForce GTX690 |
| GPU Cores | 1536 | 1344 | 2048 | 1536 | 2304 | 1024 | 3072 Total | 3072 |
| Core Clock (MHz) | 880 | 915 | 925 | 1006 | 863 | 608 | 830/880 | 915 |
| Shader Clock (MHz) | N/A | 980 Boost | N/A | Boost 1058 | Boost 902 | 1215 | N/A | Boost 1020 |
| Memory Clock (MHz) | 1375 | 1502 | 1375 | 1502 | 1502 | 854 | 1250 | 1502 |
| Memory Amount | 2048MB GDDR5 | 2048MB GDDR5 | 3072MB GDDR5 | 2048MB GDDR5 | 3072MB GDDR5 | 3072 GDDR5 | 4096MB GDDR5 | 4096MB GDDR5 |
| Memory Interface | 256-bit | 256-bit | 384-bit | 256-bit | 384-bit | 384-bit | 256-bit | 256-bit |
The Unigine Heaven benchmark is a free publicly available tool that grants the power to unleash the graphics capabilities in DirectX-11 for Windows 7 or updated Vista Operating Systems. It reveals the enchanting magic of floating islands with a tiny village hidden in the cloudy skies. With the interactive mode, emerging experience of exploring the intricate world is within reach. Through its advanced renderer, Unigine is one of the first to set precedence in showcasing the art assets with tessellation, bringing compelling visual finesse, utilizing the technology to the full extend and exhibiting the possibilities of enriching 3D gaming.
The distinguishing feature in the Unigine Heaven benchmark is a hardware tessellation that is a scalable technology aimed for automatic subdivision of polygons into smaller and finer pieces, so that developers can gain a more detailed look of their games almost free of charge in terms of performance. Thanks to this procedure, the elaboration of the rendered image finally approaches the boundary of veridical visual perception: the virtual reality transcends conjured by your hand.
Since only DX11-compliant video cards will properly test on the Heaven benchmark, only those products that meet the requirements have been included.
- Unigine Heaven Benchmark 3.0
- Settings: DirectX 11, High Quality, Extreme Tessellation, 16x AF, 4x AA
Heaven Benchmark Test Results
| Graphics Card | Radeon HD6970 | GeForce GTX670 | Radeon HD7970 | GeForce GTX680 | GeForce GTX780 | GeForce GTX590 | Radeon HD6990 | GeForce GTX690 |
| GPU Cores | 1536 | 1344 | 2048 | 1536 | 2304 | 1024 | 3072 Total | 3072 |
| Core Clock (MHz) | 880 | 915 | 925 | 1006 | 863 | 608 | 830/880 | 915 |
| Shader Clock (MHz) | N/A | 980 Boost | N/A | Boost 1058 | Boost 902 | 1215 | N/A | Boost 1020 |
| Memory Clock (MHz) | 1375 | 1502 | 1375 | 1502 | 1502 | 854 | 1250 | 1502 |
| Memory Amount | 2048MB GDDR5 | 2048MB GDDR5 | 3072MB GDDR5 | 2048MB GDDR5 | 3072MB GDDR5 | 3072 GDDR5 | 4096MB GDDR5 | 4096MB GDDR5 |
| Memory Interface | 256-bit | 256-bit | 384-bit | 256-bit | 384-bit | 384-bit | 256-bit | 256-bit |
In this section, PCI-Express graphics cards are isolated for idle and loaded electrical power consumption. In our power consumption tests, Benchmark Reviews utilizes an 80-PLUS GOLD certified OCZ Z-Series Gold 850W PSU, model OCZZ850. This power supply unit has been tested to provide over 90% typical efficiency by Chroma System Solutions. To measure isolated video card power consumption, Benchmark Reviews uses the Kill-A-Watt EZ (model P4460) power meter made by P3 International. In this particular test, all power consumption results were verified with a second power meter for accuracy.
The power consumption statistics discussed in this section are absolute maximum values, and may not represent real-world power consumption created by video games or graphics applications.
A baseline measurement is taken without any video card installed on our test computer system, which is allowed to boot into Windows 7 and rest idle at the login screen before power consumption is recorded. Once the baseline reading has been taken, the graphics card is installed and the system is again booted into Windows and left idle at the login screen before taking the idle reading. Our final loaded power consumption reading is taken with the video card running a stress test using graphics test #4 on 3DMark11.
This section discusses power consumption for the NVIDIA GeForce GTX 780 video card, which operated at reference clock speeds. Our power consumption results are not representative of the entire GTX 780-series product family, which may feature a modified design or factory overclocking by some partners. GeForce GTX 780 requires an 8-pin and 6-pin PCI-E power connections for normal operation, and will not activate the display unless proper power has been supplied. NVIDIA recommends a 600W power supply unit for stable operation with one GeForce GTX 780 video card.
In our test results the GeForce GTX 780 consumed a mere 10W at the lowest idle reading, and 275W under full load with fan operating at 100%. NVIDIA’s average TDP is specified as 250W. This positions the GTX 780 among the least power-hungry top-end video cards we’ve tested under load, but much more impressive that it’s achieved by a flagship GTX-series product. If you’re familiar with electronics, it will come as no surprise that less power consumption equals less heat output as evidenced by our thermal results below…
This section reports our temperature results subjecting the video card to maximum load conditions. During each test a 20°C ambient room temperature is maintained from start to finish, as measured by digital temperature sensors located outside the computer system. GPU-Z is used to measure the temperature at idle as reported by the GPU, and also under load.
Using a modified version of FurMark’s “Torture Test” to generate maximum thermal load, peak GPU temperature is recorded in high-power 3D mode. FurMark does two things extremely well: drives the thermal output of any graphics processor much higher than any video games realistically could, and it does so with consistency every time. Furmark works great for testing the stability of a GPU as the temperature rises to the highest possible output.
The temperatures illustrated below are absolute maximum values, and do not represent real-world temperatures created by video games or graphics applications:
| Video Card | Ambient | Idle Temp | Loaded Temp | Max Noise | ||||
| ATI Radeon HD 5850 | 20°C | 39°C | 73°C | 7/10 | ||||
| NVIDIA GeForce GTX 460 | 20°C | 26°C | 65°C | 4/10 | ||||
| AMD Radeon HD 6850 | 20°C | 42°C | 77°C | 7/10 | ||||
| AMD Radeon HD 6870 | 20°C | 39°C | 74°C | 6/10 | ||||
| ATI Radeon HD 5870 | 20°C | 33°C | 78°C | 7/10 | ||||
| NVIDIA GeForce GTX 560 Ti | 20°C | 27°C | 78°C | 5/10 | ||||
| NVIDIA GeForce GTX 570 | 20°C | 32°C | 82°C | 7/10 | ||||
| ATI Radeon HD 6970 | 20°C | 35°C | 81°C | 6/10 | ||||
| NVIDIA GeForce GTX 580 | 20°C | 32°C | 70°C | 6/10 | ||||
| NVIDIA GeForce GTX 590 | 20°C | 33°C | 77°C | 6/10 | ||||
| AMD Radeon HD 6990 | 20°C | 40°C | 84°C | 8/10 | ||||
| NVIDIA GeForce GTX 650 Ti BOOST | 20°C | 26°C | 73°C | 4/10 | ||||
| NVIDIA GeForce GTX 650 Ti | 20°C | 26°C | 62°C | 3/10 | ||||
| NVIDIA GeForce GTX 670 | 20°C | 26°C | 71°C | 3/10 | ||||
| NVIDIA GeForce GTX 680 | 20°C | 26°C | 75°C | 3/10 | ||||
| NVIDIA GeForce GTX 690 | 20°C | 30°C | 81°C | 4/10 | ||||
| NVIDIA GeForce GTX 780 | 20°C | 28°C | 80°C | 3/10 |
As we’ve mentioned on the pages leading up to this section, NVIDIA’s Kepler architecture yields a much more efficient operating GPU compared to previous designs. This becomes evident by the low idle temperature, and translates into modest full-load temperatures. While NVIDIA’s reference design works exceptionally well at cooling the GK110 GPU on GeForce GTX 780, consumers should expect add-in card partners to advertise unnecessarily excessive over-cooled versions for an extra premium. 80°C after ten minutes at 100% load is nothing at all, and is nowhere close to this card’s 95°C thermal threshold.
IMPORTANT: Although the rating and final score mentioned in this conclusion are made to be as objective as possible, please be advised that every author perceives these factors differently at various points in time. While we each do our best to ensure that all aspects of the product are considered, there are often times unforeseen market conditions and manufacturer changes which occur after publication that could render our rating obsolete. Please do not base any purchase solely on our conclusion as it represents our product rating specifically for the product tested, which may differ from future versions of the same product. Benchmark Reviews begins our conclusion with a short summary for each of the areas that we rate.
My ratings begin with performance, where GeForce GTX 780 lacks direct competition from another graphics card. The closest available competing solution comes in the form of AMD’s Radeon HD 7970, which as you might have seen from the benchmark results, hardly compares. In fact, the only real competition that can stand up to GTX 780 is the GeForce GTX TITAN (not tested), and the dual-GPU GTX 690. There were rare occasions when the dual-GPU AMD Radeon HD 6990, such as in Metro 2033 and Aliens vs Predator, but otherwise AMD has nothing to compare against GTX 780 (as well as GTX TITAN, and GTX 690).
In the DirectX 10 game Crysis Warhead the GeForce GTX 780 graphics card easily surpassed AMD’s Radeon HD 7970 without much effort, but was nearly matched by the GTX 680 and eventually beaten by the dual-GPU GTX 590 and GTX 690. DirectX 11 test results continued to keep the GeForce GTX 780 consistently ahead of its competition in almost all tests: ultra-demanding DX11 games such as Batman: Arkham Asylum made good use of Kepler’s optimized architecture, helping to deliver 118-FPS and trailing performance for GTX 690 (127-FPS). Battlefield 3 gave the GeForce GTX 780 an astonishing 46-FPS lead over the Radeon HD 7970, all while using Ultra quality settings. Lost Planet 2 played well on all graphics cards when set to high quality with 4x AA, allowing GTX 780 to maintain an impressive 93.7 frame rate. In Aliens vs Predator the GeForce GTX 780 surpasses the AMD Radeon HD 7970 by nearly 40 FPS while outperforming GTX 590 by 20 FPS, but trailed slightly behind dual-GPU Radeon HD 6990 performance levels. Metro 2033 is another demanding game that requires high-end graphics to enjoy high quality visual settings, and although this benchmark favors Radeon products the GTX 780 maintained a lead over other cards at 1920×1080 while matching frame rates with Radeon HD 6990.
Synthetic benchmark tools offer an unbiased read on graphics products, allowing video card manufacturers to display their performance without special game optimizations or driver influence. Futuremark’s 3DMark11 benchmark suite strained our high-end graphics cards with only mid-level settings displayed at 720p, yet GeForce GTX 780 produced higher FPS results than every graphics card AMD produces. Unigine Heaven 3.0 benchmark tests used maximum settings that tend to crush most products, yet GTX 780 still produced a dominating performance that was second only to the GTX 690 (and presumably GTX TITAN).
Overclocking is an area I will cover in more detail with a follow-up article, since time constraints and testing setbacks kept me from having enough data to present it here. While the sample I received could be overclocked to 1200 MHz (Boost), it required maximum cooling and would occasionally crash the driver. Backing it down two steps produced 1176 MHz (Boost), and was completely stable in all tests, but still required upper-end fan speed. More details will be posted in the following days.
Appearance is a much more subjective matter, especially since this particular rating doesn’t have any quantitative benchmark scores to fall back on. NVIDIA’s GeForce GTX series has traditionally used a recognizable design over the past two years, but beginning with GTX TITAN and seen here again with the GeForce GTX 780, NVIDIA’s use of matte silver trim certainly helps the series stand out. Because GeForce GTX 780 operates so efficiently, and allows nearly all of the heated air to exhaust outside of the computer case, the reference design does an excellent job for function. While fashionably good looks might mean a lot to some consumers, keep in mind that this product still outperforms all the competition while generating much less heat and producing very little noise.
Construction is the one area NVIDIA graphics cards continually shine, and thanks in part to extremely quiet operation paired with more efficient cores that consume less energy and emit less heat, it seems clear that GeForce GTX 780 continues to carry on this tradition. Requiring an 8- and 6-pin PCI-E power connections reduce power supply requirements to 600W, which is practically mainstream. Additionally, consumers have a top-end single-GPU solution capable of driving three monitors in 3D Vision Surround with the inclusion of two DL-DVI ports with supplementary HDMI and DisplayPort output.
As of launch day (23 May 2013), the NVIDIA GeForce GTX 780 video card sells with a starting price of $649.99 (Amazon | Newegg). Please keep in mind that hardware manufacturers and retailers are constantly adjusting prices, so expect it to change a few times between now and one month later. There’s still plenty of value beyond basic frame rate performance, and the added NVIDIA Kepler features run it off the charts. Only NVIDIA Kepler video cards can offer automated GPU Boost technology, 3D Vision, Adaptive VSync, PhysX technology, FXAA, and now TXAA.
My conclusion: GeForce GTX 780 is essentially GTX TITAN Jr. NVIDIA’s GeForce GTX TITAN was already a huge problem for the AMD Radeon series, since there’s nothing to complete with it until much later in the year. Now GeForce GTX 780 arrives, and creates an additional layer of trouble for them when their technology finally catches up. Of course, just because GTX 780 gets a free pass doesn’t mean it will be an instant winner. Gamers must have a reason to spend $650 on a video card, especially with so many other platform options coming to market soon. But for those who can pay the asking price, their reward is quite sweet indeed. GeForce GTX 780 delivers performance beyond expectations, and challenges game developers to build even more realism into their titles.
+ Outperforms AMD Radeon HD 7970 and dual-GPU Radeon HD 6990
+ Outstanding performance with DX11 video games
+ Supports NVIDIA GPU Boost 2.0 technology, Adaptive VSync, TXAA, 3D Vision and PhysX
+ Triple-display and 3D Vision Surround support
+ Cooling fan operates at very quiet acoustic levels
+ Features DisplayPort connectivity for future monitor technology
+ Very low power consumption at idle and heat output under load
+ Upgradable into dual- and triple SLI card sets
– Very expensive enthusiast product!
COMMENT QUESTION: Do you prefer NVIDIA GeForce or AMD Radeon graphics cards?
