NVIDIA GeForce GTX 580 Video Card Review

The reinvented Fermi GF110 GPU delivers more graphical power per watt than any other DirectX-11 video card.

Everyone who waited for NVIDIA to launch their Fermi graphics architecture felt like they had held back once it was finally released. The GF100 graphics processor that was packaged into the GTX 480 used less than its full potential, and it didn't create the wide performance margin everyone expected between competitors. Seven months later, NVIDIA has returned with their updated Fermi GF110 GPU, delivering all 512 CUDA cores in the GeForce GTX 580. Featuring a tweaked graphics processor that runs much cooler and uses less power than the GTX 480, the NVIDIA GeForce GTX 580 is tested by Benchmark Reviews against the Radeon 5970 and CrossFire 6870 video cards, along with two overclocked GeForce GTX 460's in SLI, using the latest DirectX-11 video games.

Something happened to the Fermi architecture between the time it premiered as GF100 and when it began to really turn heads as GF104: the ratio of shaders and texture units was perfected. The original GF100 GPU placed too much emphasis on tessellation, and not enough on overall graphical performance. As a result of finding the right balance, the GF104 graphics processor on the GeForce GTX 460 became an overnight sensation for gamers. Now evolved into the GF110 GPU, all 512 cores understand their purpose and propel the GeForce GTX 580 to a level only rivaled by the competition's best and most-expensive dual-GPU Radeon HD 5970 graphics card. Trimmed down to a modest 244 watts of power consumption under load, the GTX 580 outperforms its predecessor in both power efficiency graphical performance.

Armed with the maximum number of CUDA cores and PolyMorph engines NVIDIA can deliver with the Fermi architecture, the GeForce GTX 580 represents their trophy effort to seize the performance market. While being similar to the GeForce GTX 480, the GeForce GTX 580 design updates the Fermi formula, improves upon the power appetite, reduces heat output, and increases graphical frame rate performance. The GF110 fixed function clock speed is tuned to 772 MHz, while the cores all operate at 1544 MHz. 1536MB of GDDR5 video frame buffer use a familiar 384-bit memory bus, clocked to 1002MHz for a 4008MHz data rate.

The NVIDIA GeForce GTX 580 competes on two levels: price point and GPU segment. At the $500 price point, it competes directly against ATI's dual-GPU Radeon HD 5970 and a pair of AMD Radeon HD 6870 video cards combined into CrossFireX. In regard to single-GPU competition, the closest video cards would be ATI's Radeon HD 5870 or NVIDIA's own GeForce GTX 480.

Using the most demanding PC video game titles and benchmark software available at the time of launch, Benchmark Reviews tests graphical frame rate performance of the GeForce GTX 580. Older DirectX-10 favorites such as Crysis Warhead and PCMark Vantage are included, as well as newer DirectX-11 titles such as: Aliens vs Predator, Battlefield: Bad Company 2, BattleForge, Lost Planet 2, Mafia II, Metro 2033, Tom Clancy's HAWX2, and the Unigine Heaven 2.1 benchmark. Built to deliver the best possible graphical experience to a performance-orientated gaming market, NVIDIA's GeForce GTX 580 video card delivers top-end frame rates with unmatched efficiency.

UPDATE 11-NOV-2010: This article has been updated to provide results for two $229 EVGA GeForce GTX 460 FTW video cards in SLI.

Manufacturer: NVIDIA Corporation
Product Name: GeForce GTX 580
Suggested Tested: $499.99 MSRP

Full Disclosure: The product sample used in this article has been provided by NVIDIA.

GeForce GTX 580 Closer Look

Compared to the bulging heat-pipes on the GeForce GTX 480, NVIDIA's GeForce GTX 580 actually looks like it belongs to the GTX 470 family. Both the GTX 480 and the new GeForce GTX 580 have profiles that measure 10.5" long and occupy two card slots, but the GTX 580 drops the 1/2-inch protruding nerf bars and wears a svelte 3.875" waistline. Not surprisingly, it also weighs considerably less, too.

Although the power demands have been reduced, the NVIDIA GeForce GTX 580 still requires an eight-pin and six-pin PCI-E power connection. Similar to the GTX 480 shroud design, the GeForce GTX 580 shares an identical vent near the header panel.

NVIDIA has designed the shroud with a deeper chamfer depression for the blower motor fan, allowing more air to reach the intake whenever two or more video cards are combined in close-proximity SLI configurations.

Popular in the world of CPU coolers, NVIDIA has used a hollow vapor chamber to provide a robust thermal management system on the GeForce GTX 580. This will bring into question the need for add-in card partners to design their own cooling solution, and challenge them to produce better results.

Pictured below is the heatsink component, with the vapor chamber residing inside the copper portion. The polished copper contact surface mates together with the GF110 GPU, as the blower motor fan drives air past the aluminum fins and outside the computer case.

NVIDIA offers a mini-HDMI 1.4a digital A/V output on the GeForce GTX 580, which add-in partners may further extend with a full-size adapter. Dual dual-link DVI digital outputs are retained on the GTX 580, which still means that at least two GeForce video cards will be needed for a NVIDIA 3D-Vision Surround functionality.

In the next section, we'll peel off the plastic shroud and take a detailed look at NVIDIA GeForce GTX 580...

GeForce GTX 580 Detailed

In many ways the new GF110 graphics processor is no different than the original GF100. NVIDIA claims that the Fermi block diagram is identical between the two, and only the ratio of tessellation, shader, and texture units has been refined. This means that the GF110 shares the same 530 mm² die profile, shared memory, dedicated L1 cache, and 768KB L2 cache as the GF100. The thermal threshold is reduced to 97°C, and the transistor count moves down from 3.2-billion to 3-billion. Benchmark Reviews offers our NVIDIA Fermi Graphics Architecture guide for a more comprehensive look into the Fermi GPU.

NVIDIA's GF110 GPU inside the GeForce GTX 580 maintains the same six 64-bit GDDR5 memory controllers (384-bit total) to facilitate high bandwidth access to the frame buffer. This also means that the same printed circuit board design could have been used for the GTX 580, and it was, but with several new twists. The first obvious change is the lack of blower fan openings in the PCB. The other changes are much more subtle, but make a big impact on functionality.

Circled below are the electronic components responsible for power management on NVIDIA's GeForce GTX 580 video card. Benchmark Reviews uses GPU stress tools such as FurMark to measure maximum power usage, although admittedly no video game exists that would ever create comparable power demands. NVIDIA now dedicates hardware circuitry to the task of monitoring power consumption as well as temperature, adjusting performance to protect the graphics card from damage.

With so much circuit board real-estate still undeveloped, add-in card partners may choose to re-design the GeForce GTX 580 PCB so long as NVIDIA offers engineering information. Other changes could potentially include the use of higher-density DRAM modules, replacing the Samsung 128MB 1250MHz K4G10325FE-HC04 GDDR5 IC's with 256MB IC parts such as: Samsung 1250MHz K4G20325FC-HC04 GDDR5, or 1500MHz K4G20325FC-HC03.

NVIDIA designed the GTX 580 for 244 watts Thermal Design Power (TDP), however the 6+8-pin power connections are good for up to 400W on demand. Keep this in mind when shopping for a power supply unit, because NVIDIA recommends a 600W PSU for the GTX 580; although I personally feel that a 800W PSU would be a safer suggestion in terms of upgrade longevity.

NVIDIA has designed triple-SLI capability into their upper-level 'GTX' family Fermi video cards: GTX 465, 470, 480, and now the GeForce GTX 580. Even though SLI and triple-SLI are possible, careful consideration for heat must be given to overclocked computers systems, since multiple GPU's inside the computer case will further extend the CPU's heat range.

NVIDIA Fermi Features

In today's complex graphics, tessellation offers the means to store massive amounts of coarse geometry, with expand-on-demand functionality. In the NVIDIA GF100-series GPU, tessellation also enables more complex animations. In terms of model scalability, dynamic Level of Detail (LOD) allows for quality and performance trade-offs whenever it can deliver better picture quality over performance without penalty. Comprised of three layers (original geometry, tessellation geometry, and displacement map), the final product is far more detailed in shade and data-expansion than if it were constructed with bump-map technology. In plain terms, tessellation gives the peaks and valleys with shadow detail in-between, while previous-generation technology (bump-mapping) would give the illusion of detail.

Using GPU-based tessellation, a game developer can send a compact geometric representation of an object or character and the tessellation unit can produce the correct geometric complexity for the specific scene. Consider the "Imp" character illustrated above. On the far left we see the initial quad mesh used to model the general outline of the figure; this representation is quite compact even when compared to typical game assets. The two middle images of the character are created by finely tessellating the description at the left. The result is a very smooth appearance, free of any of the faceting that resulted from limited geometry. Unfortunately this character, while smooth, is no more detailed than the coarse mesh. The final image on the right was created by applying a displacement map to the smoothly tessellated third character to the left.

Benchmark Reviews also more detail in our full-length NVIDIA GF100 GPU Fermi Graphics Architecture guide.

Tessellation in DirectX-11

Control hull shaders run DX11 pre-expansion routines, and operates explicitly in parallel across all points. Domain shaders run post-expansion operations on maps (u/v or x/y/z/w) and is also implicitly parallel. Fixed function tessellation is configured by Level of Detail (LOD) based on output from the control hull shader, and can also produce triangles and lines if requested. Tessellation is something that is new to NVIDIA GPUs, and was not part of GT200 because of geometry bandwidth bottlenecks from sequential rendering/execution semantics.

In regard to the GF110 graphics processor, NVIDIA has added a new PolyMorph and Raster engines to handle world-space processing (PolyMorph) and screen-space processing (Raster). There are sixteen PolyMorph engines and four Raster engines on the GF110, which depend on an improved L2 cache to keep buffered geometric data produced by the pipeline on-die.

GF100 Compute for Gaming

As developers continue to search for novel ways to improve their graphics engines, the GPU will need to excel at a diverse and growing set of graphics algorithms. Since these algorithms are executed via general compute APIs, a robust compute architecture is fundamental to a GPU's graphical capabilities. In essence, one can think of compute as the new programmable shader. GF110's compute architecture is designed to address a wider range of algorithms and to facilitate more pervasive use of the GPU for solving parallel problems. Many algorithms, such as ray tracing, physics, and AI, cannot exploit shared memory-program memory locality is only revealed at runtime. GF110's cache architecture was designed with these problems in mind. With up to 48 KB of L1 cache per Streaming Multiprocessor (SM) and a global L2 cache, threads that access the same memory locations at runtime automatically run faster, irrespective of the choice of algorithm.

NVIDIA Codename NEXUS brings CPU and GPU code development together in Microsoft Visual Studio 2008 for a shared process timeline. NEXUS also introduces the first hardware-based shader debugger. NVIDIA's GF100-series is the first GPU to ever offer full C++ support, the programming language of choice among game developers. To ease the transition to GPU programming, NVIDIA developed Nexus, a Microsoft Visual Studio programming environment for the GPU. Together with new hardware features that provide better debugging support, developers will be able enjoy CPU-class application development on the GPU. The end results is C++ and Visual Studio integration that brings HPC users into the same platform of development. NVIDIA offers several paths to deliver compute functionality on the GF110 GPU, such as CUDA C++ for video games.

Image processing, simulation, and hybrid rendering are three primary functions of GPU compute for gaming. Using NVIDIA's GF100-series GPU, interactive ray tracing becomes possible for the first time on a standard PC. Ray tracing performance on the NVIDIA GF100 is roughly 4x faster than it was on the GT200 GPU, according to NVIDIA tests. AI/path finding is a compute intensive process well suited for GPUs. The NVIDIA GF110 can handle AI obstacles approximately 3x better than on the GT200. Benefits from this improvement are faster collision avoidance and shortest path searches for higher-performance path finding.

GF110 Specifications

• 512 CUDA Cores
• 16 Geometry Units
• 4 Raster Units
• 64 Texture Units
• 48 ROP Units
• 384-bit GDDR5
• DirectX-11 API Support

GeForce 400-Series Products

VGA Testing Methodology

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.

According to the Steam Hardware Survey published for the month ending September 2010, the most popular gaming resolution is 1280x1024 (17-19" standard LCD monitors). However, because this 1.31MP resolution is considered 'low' by most standards, our benchmark performance tests concentrate on higher-demand resolutions: 1.76MP 1680x1050 (22-24" widescreen LCD) and 2.30MP 1920x1200 (24-28" widescreen LCD monitors). These resolutions are more likely to be used by high-end graphics solutions, such as those tested in this article.

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.

Cost to Performance Ratio

For this article Benchmark Reviews has included cost per FPS for graphics performance results. An average of the five least expensive product prices are calculated, which do not consider tax, freight, promotional offers, or rebates into the cost. All prices reflect product series components, and do not represent any specific manufacturer, model, or brand. The median retail prices for each product were obtained from NewEgg.com and current as of 08-November-2010:

• $242 Radeon HD 6870 1GB
• $255 GeForce GTX 470 1GB
• $324 Radeon HD 5870 1GB
• $437 GeForce GTX 480 1536MB
• $500 Radeon HD 5970 2GB
• $500 GeForce GTX 580 1536MB

Intel X58-Express Test System

• Motherboard: ASUS P6X58D-E (Intel X58/ICH10R/Marvell SE9128)
• Processor: Intel Core i7-920 Nehalem 2.66 GHz (BX80601920)
• CPU Cooler: Prolimatech Megahalems
• System Memory: Kingston HyperX DDR3 KHX2000C8D3T1K3 (3x2GB @ 1333 CL6-6-6-18)
• Primary Drive: OCZ Vertex-2 Extended Solid State Drive
• Power Supply Unit: OCZ Z-Series Gold 850W OCZZ850
• Monitor: 26-Inch Widescreen LCD (up to 1920x1200@60Hz)

DirectX-10 Benchmark Applications

• 3DMark Vantage v1.02
  • Extreme Settings: (Extreme Quality, 8x Multisample Anti-Aliasing, 16x Anisotropic Filtering, 1:2 Scale)
• Crysis Warhead v1.1 with HOC Benchmark
  • Moderate Settings: (Very High Quality, 4x AA, 16x AF, Airfield Demo)

DirectX-11 Benchmark Applications

• Aliens vs Predator Benchmark 1.0
  • Extreme Settings: (Very High Quality, 4x AA, 16x AF, SSAO, Tessellation, Advanced Shadows)
• BattleField: Bad Company 2
  • Extreme Settings: (Highest Quality, HBAO, 8x AA, 16x AF, 180s Fraps Single-Player Intro Scene)
• BattleForge v1.2
  • Extreme Settings: (Very High Quality, 8x Anti-Aliasing, Auto Multi-Thread)
• Lost Planet 2 Benchmark 1.0
  • Moderate Settings: (2x AA, Low Shadow Detail, High Texture, High Render, High DirectX 11 Features)
• Mafia II
  • Extreme Settings: (Antialiasing, 16x AF, High Shadow Quality, High Detail, High Geometry, Ambient Occlusion)
• Metro 2033
  • Moderate Settings: (Very-High Quality, AAA, 16x AF, Advanced DoF, Tessellation, 180s Fraps Chase Scene)
• Tom Clancy's HAWX 2 Benchmark 1.0.4
  • Extreme Settings: (Maximum Quality, 8x AA, 16x AF, DX11 Terrain Tessellation)
• Unigine Heaven Benchmark 2.1
  • Moderate Settings: (High Quality, Normal Tessellation, 16x AF, 4x AA)

Video Card Test Products

UPDATE 11-NOV-2010: This article has been updated to provide results for two $229 EVGA GeForce GTX 460 FTW video cards in SLI.

EVGA GeForce GTX 460 FTW 01G-P3-1377-TR (850 MHz GPU/1700 MHz Shader/1000 MHz vRAM - Forceware 262.99 Beta)
• AMD Radeon HD 6870 (900 MHz GPU/1050 MHz vRAM - AMD Catalyst Driver 10.10d)
ZOTAC GeForce GTX 470 ZT-40201-10P (608 MHz GPU/1215 MHz Shader/837 MHz vRAM - Forceware 262.99 Beta)
ATI Radeon HD 5870 (850 MHz GPU/1200MHz vRAM - AMD Catalyst Driver 10.10d)
ASUS ENGTX480/2DI/1536MD5 GeForce GTX 480 (701 MHz GPU/1401 MHz Shader/924 MHz vRAM - Forceware 262.99 Beta)
AMD Radeon HD 5970 Reference Design (725 MHz GPU x2/1000MHz vRAM - AMD Catalyst Driver 10.10d)
NVIDIA GeForce GTX 580 (772 MHz GPU/1544 MHz Shader/1002 MHz vRAM - Forceware 262.99 Beta)

DX10: 3DMark Vantage

3DMark Vantage is a PC benchmark suite designed to test the DirectX10 graphics card performance. FutureMark 3DMark Vantage is the latest addition the 3DMark benchmark series built by FutureMark corporation. Although 3DMark Vantage requires NVIDIA PhysX to be installed for program operation, only the CPU/Physics test relies on this technology.

3DMark Vantage offers benchmark tests focusing on GPU, CPU, and Physics performance. Benchmark Reviews uses the two GPU-specific tests for grading video card performance: Jane Nash and New Calico. These tests isolate graphical performance, and remove processor dependence from the benchmark results.

• 3DMark Vantage v1.02
  • Extreme Settings: (Extreme Quality, 8x Multisample Anti-Aliasing, 16x Anisotropic Filtering, 1:2 Scale)

3DMark Vantage GPU Test: Jane Nash

Of the two GPU tests 3DMark Vantage offers, the Jane Nash performance benchmark is slightly less demanding. In a short video scene the special agent escapes a secret lair by water, nearly losing her shirt in the process. Benchmark Reviews tests this DirectX-10 scene at 1680x1050 and 1920x1200 resolutions, and uses Extreme quality settings with 8x anti-aliasing and 16x anisotropic filtering. The 1:2 scale is utilized, and is the highest this test allows. By maximizing the processing levels of this test, the scene creates the highest level of graphical demand possible and sorts the strong from the weak.

Jane Nash Extreme Quality Settings

Cost Analysis: Jane Nash (1920x1200)

• $242 Radeon HD 6870 1GB costs $10.17 per FPS
• $255 GeForce GTX 470 1GB costs $10.99 per FPS
• $324 Radeon HD 5870 1GB costs $11.25 per FPS
• $437 GeForce GTX 480 1536MB costs $14.97 per FPS
• $500 Radeon HD 5970 2GB costs $11.63 per FPS
• $500 GeForce GTX 580 1536MB costs $13.12 per FPS
• $484 Radeon HD 6870 CrossFireX costs $10.85 per FPS

3DMark Vantage GPU Test: New Calico

New Calico is the second GPU test in the 3DMark Vantage test suite. Of the two GPU tests, New Calico is the most demanding. In a short video scene featuring a galactic battleground, there is a massive display of busy objects across the screen. Benchmark Reviews tests this DirectX-10 scene at 1680x1050 and 1920x1200 resolutions, and uses Extreme quality settings with 8x anti-aliasing and 16x anisotropic filtering. The 1:2 scale is utilized, and is the highest this test allows. Using the highest graphics processing level available allows our test products to separate themselves and stand out (if possible).

New Calico Extreme Quality Settings

Cost Analysis: New Calico (1920x1200)

• $242 Radeon HD 6870 1GB costs $13.37 per FPS
• $255 GeForce GTX 470 1GB costs $12.94 per FPS
• $324 Radeon HD 5870 1GB costs $14.86 per FPS
• $437 GeForce GTX 480 1536MB costs $17.27 per FPS
• $500 Radeon HD 5970 2GB costs $14.66 per FPS
• $500 GeForce GTX 580 1536MB costs $14.79 per FPS
• $484 Radeon HD 6870 CrossFireX costs $13.79 per FPS

Test Summary: The NVIDIA GeForce GTX 580 competes on two levels: price point and GPU segment. At the $500 price point, it competes directly against ATI's dual-GPU Radeon HD 5970 and a pair of AMD Radeon HD 6870 video cards combined into CrossFireX. In regard to single-GPU competition, the closest video cards would be ATI's Radeon HD 5870 or NVIDIA's own GeForce GTX 480.

3dMark Vantage usually sets the pace for coming events, and through the analysis of these two tests spread over two different resolutions we gain a clear insight into who ranks where. In the Jane Nash tests, the dual-GPU Radeon HD 5970 and CrossFireX Radeon HD 6870's outscore the GeForce GTX 580, but then in the New Calico tests the GTX 580 comes back to outperform or match these same video cards. Comparing the GeForce GTX 580 to the older GTX 480 creates a tremendous performance margin of 31/34%, even more so with the GTX 580 and ATI Radeon HD 5870 (+32/55%). Our cost analysis indicates a trend among the premium top-end graphics products: better frame rate, and less value.

DX10: Crysis Warhead

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
  • Moderate Settings: (Very High Quality, 4x AA, 16x AF, Airfield Demo)

Crysis Warhead Moderate Quality Settings

Cost Analysis: Crysis Warhead (1920x1200)

• $242 Radeon HD 6870 1GB costs $9.68 per FPS
• $255 GeForce GTX 470 1GB costs $9.44 per FPS
• $324 Radeon HD 5870 1GB costs $12.00 per FPS
• $437 GeForce GTX 480 1536MB costs $12.85 per FPS
• $500 Radeon HD 5970 2GB costs $11.90 per FPS
• $500 GeForce GTX 580 1536MB costs $12.20 per FPS
• $484 Radeon HD 6870 CrossFireX costs $9.68 per FPS

Test Summary: The CryENGINE2 graphics engine used in Crysis Warhead doesn't allow gamers to use the maximum quality settings, but it allows the NVIDIA GeForce GTX 580 to match performance with the dual-GPUs inside an ATI Radeon HD 5970. Trailing 6-FPS behind at 1680x1050 and 9-FPS at 1920x1200, the GTX 580 is no match for CrossFireX AMD Radeon HD 6870's. Comparing the Fermi GF100 in the GeForce GTX 480 against the optimized GF110 GPU inside the GeForce GTX 580 amounts to a huge performance difference of 21%, and up to 52% increase over the Radeon HD 5870. In terms of price to performance value, the AMD Radeon HD 6870 appears to seize on this opportunity at both ends of the spectrum, although it takes two cards to compete.

DX11: Aliens vs Predator

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
  • Extreme Settings: (Very High Quality, 4x AA, 16x AF, SSAO, Tessellation, Advanced Shadows)

Aliens vs Predator Extreme Quality Settings

Cost Analysis: Aliens vs Predator (1920x1200)

• $242 Radeon HD 6870 1GB costs $8.96 per FPS
• $255 GeForce GTX 470 1GB costs $8.73 per FPS
• $324 Radeon HD 5870 1GB costs $10.80 per FPS
• $437 GeForce GTX 480 1536MB costs $11.78 per FPS
• $500 Radeon HD 5970 2GB costs $9.84 per FPS
• $500 GeForce GTX 580 1536MB costs $11.01 per FPS
• $484 Radeon HD 6870 CrossFireX costs $9.06 per FPS

Test Summary: Aliens vs Predator may use the well-known Asura game engine, but DirectX-11 extensions push the graphical demand on this game to levels eclipsed by very few others. With an unbiased appetite for raw DirectX-11 graphics performance, Aliens vs Predator accepts AMD and NVIDIA products as equal contenders. When maximum quality settings and high-strain SSAO are called into action, the NVIDIA GeForce GTX 580 surpasses the GeForce GTX 480 by 22%, but doesn't quite match itself up to the dual-GPU ATI Radeon HD 5970 or CrossFireX AMD Radeon HD 6870's like it has done in other tests.

DX11: Battlefield Bad Company 2

The Battlefield franchise has been known to demand a lot from PC graphics hardware. DICE (Digital Illusions CE) has incorporated their Frostbite-1.5 game engine with Destruction-2.0 feature set with Battlefield: Bad Company 2. Battlefield: Bad Company 2 features destructible environments using Frostbit Destruction-2.0, and adds gravitational bullet drop effects for projectiles shot from weapons at a long distance. The Frostbite-1.5 game engine used on Battlefield: Bad Company 2 consists of DirectX-10 primary graphics, with improved performance and softened dynamic shadows added for DirectX-11 users.

At the time Battlefield: Bad Company 2 was published, DICE was also working on the Frostbite-2.0 game engine. This upcoming engine will include native support for DirectX-10.1 and DirectX-11, as well as parallelized processing support for 2-8 parallel threads. This will improve performance for users with an Intel Core-i7 processor. Unfortunately, the Extreme Edition Intel Core i7-980X six-core CPU with twelve threads will not see full utilization.

In our benchmark tests of Battlefield: Bad Company 2, the first three minutes of action in the single-player raft night scene are captured with FRAPS. Relative to the online multiplayer action, these frame rate results are nearly identical to daytime maps with the same video settings. The Frostbite-1.5 game engine in Battlefield: Bad Company 2 appears to equalize our test set of video cards, and despite AMD's sponsorship of the game it still plays well using any brand of graphics card.

• BattleField: Bad Company 2
  • Extreme Settings: (Highest Quality, HBAO, 8x AA, 16x AF, 180s Fraps Single-Player Intro Scene)

Battlefield Bad Company 2 Extreme Quality Settings

Cost Analysis: Battlefield: Bad Company 2 (1920x1200)

• $242 Radeon HD 6870 1GB costs $4.43 per FPS
• $255 GeForce GTX 470 1GB costs $4.12 per FPS
• $324 Radeon HD 5870 1GB costs $5.19 per FPS
• $437 GeForce GTX 480 1536MB costs $6.59 per FPS
• $500 Radeon HD 5970 2GB costs $5.56 per FPS
• $500 GeForce GTX 580 1536MB costs $5.43 per FPS
• $484 Radeon HD 6870 CrossFireX costs $4.52 per FPS

Test Summary: Our extreme-quality tests use maximum settings for Battlefield: Bad Company 2, still allowing the NVIDIA GeForce GTX 580 to outperform a dual-GPU ATI Radeon HD 5970 along with every other single-GPU video card on the market. Two AMD Radeon HD 6870's in CrossFire catch the GTX 580 on price and performance, but create more heat and consume much more power. Battlefield Bad Company 2 spells bad news for the older GeForce GTX 480, producing the highest cost per frame and being outperformed by 35% with the GTX 580.

DX11: BattleForge

BattleForge is free Massive Multiplayer Online Role Playing Game (MMORPG) developed by EA Phenomic with DirectX-11 graphics capability. Combining strategic cooperative battles, the community of MMO games, and trading card gameplay, BattleForge players are free to put their creatures, spells and buildings into combination's they see fit. These units are represented in the form of digital cards from which you build your own unique army. With minimal resources and a custom tech tree to manage, the gameplay is unbelievably accessible and action-packed.

Benchmark Reviews uses the built-in graphics benchmark to measure performance in BattleForge, using Very High quality settings (detail) and 8x anti-aliasing with auto multi-threading enabled. BattleForge is one of the first titles to take advantage of DirectX-11 in Windows 7, and offers a very robust color range throughout the busy battleground landscape. The charted results illustrate how performance measures-up between video cards when Screen Space Ambient Occlusion (SSAO) is enabled.

• BattleForge v1.2
  • Extreme Settings: (Very High Quality, 8x Anti-Aliasing, Auto Multi-Thread)

BattleForge Extreme Quality Settings

Cost Analysis: BattleForge (1920x1200)

• $242 Radeon HD 6870 1GB costs $7.06 per FPS
• $255 GeForce GTX 470 1GB costs $5.62 per FPS
• $324 Radeon HD 5870 1GB costs $6.79 per FPS
• $437 GeForce GTX 480 1536MB costs $7.50 per FPS
• $500 Radeon HD 5970 2GB costs $8.28 per FPS
• $500 GeForce GTX 580 1536MB costs $7.47 per FPS
• $484 Radeon HD 6870 CrossFireX costs $7.11 per FPS

Test Summary: With BattleForge graphics settings turned to their highest quality and SSAO enabled, the NVIDIA GeForce GTX 580 truly shines as it easily surpasses the dual-GPU Radeon HD 5970 and matches up to a pair of AMD Radeon HD 6870's in CrossFireX. The irony here is that BattleForge isn't even part of NVIDIA's The Way It's Meant To Be Played initiative; it's actually an AMD co-developed game. Nevertheless, all 512 CUDA cores dance past the others to offer one of the more respectable cost to performance ratios.

DX11: Lost Planet 2

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
  • Moderate Settings: (2x AA, Low Shadow Detail, High Texture, High Render, High DirectX 11 Features)

Lost Planet 2 Moderate Quality Settings

Cost Analysis: Lost Planet 2 (1920x1200)

• $242 Radeon HD 6870 1GB costs $7.81 per FPS
• $255 GeForce GTX 470 1GB costs $6.71 per FPS
• $324 Radeon HD 5870 1GB costs $10.42 per FPS
• $437 GeForce GTX 480 1536MB costs $9.30 per FPS
• $500 Radeon HD 5970 2GB costs $10.59 per FPS
• $500 GeForce GTX 580 1536MB costs $9.09 per FPS
• $484 Radeon HD 6870 CrossFireX costs $8.46 per FPS

Test Summary: Lost Planet 2 is one of the few PC video games that is impossible to play with maximum quality settings. Even when moderate quality levels are configured, top-end video cards like AMD's Radeon HD 6870 and the Radeon HD 5870 barely produce playable frame rates. At 16801050 the NVIDIA GeForce GTX 580 outperforms every other graphics product available, including a pair of Radeon HD 6870's in CrossFire. Increasing the display resolution to 1920x1200 results in the GTX 580 falling about 2-FPS behind the CrossFireX set, but still 8-FPS ahead of the Radeon HD 5970's dual Cypress GPUs that somehow compete with the older GeForce GTX 480.

DX9+SSAO: Mafia II

Mafia II is a single-player third-person action shooter developed by 2K Czech for 2K Games, and is the sequel to Mafia: The City of Lost Heaven released in 2002. Players assume the life of World War II veteran Vito Scaletta, the son of small Sicilian family who immigrates to Empire Bay. Growing up in the slums of Empire Bay teaches Vito about crime, and he's forced to join the Army in lieu of jail time. After sustaining wounds in the war, Vito returns home and quickly finds trouble as he again partners with his childhood friend and accomplice Joe Barbaro. Vito and Joe combine their passion for fame and riches to take on the city, and work their way to the top in Mafia II.

Mafia II is a SSAO-enabled PC video game built on 2K Czech's proprietary Illusion game engine, which succeeds the LS3D game engine used in Mafia: The City of Lost Heaven. In our Mafia-II Video Game Performance article, Benchmark Reviews explored characters and gameplay while illustrating how well this game delivers APEX PhysX features on both AMD and NVIDIA products. Thanks to DirectX-11 APEX PhysX extensions that can be processed by the system's CPU, Mafia II offers gamers is equal access to high-detail physics regardless of video card manufacturer.

• Mafia II
  • Extreme Settings: (Antialiasing, 16x AF, High Shadow Quality, High Detail, High Geometry, Ambient Occlusion)

Mafia II Extreme Quality Settings

Cost Analysis: Mafia II (1920x1200)

• $242 Radeon HD 6870 1GB costs $5.10 per FPS
• $255 GeForce GTX 470 1GB costs $5.57 per FPS
• $324 Radeon HD 5870 1GB costs $6.08 per FPS
• $437 GeForce GTX 480 1536MB costs $7.56 per FPS
• $500 Radeon HD 5970 2GB costs $8.24 per FPS
• $500 GeForce GTX 580 1536MB costs $7.59 per FPS
• $484 Radeon HD 6870 CrossFireX costs $7.15 per FPS

Test Summary: Of all the video games presently available for DirectX-11 platforms, Mafia II is by far one of the most detailed and feature-rich. Playable at the highest quality settings when APEX PhysX is disabled (for the benefit of non-GeForce products), all of the video cards tested delivered good frame rate performance. As we've seen in the other tests, the NVIDIA GeForce GTX 580 outperforms the ATI Radeon HD 5970 but the same margin that it surpasses the GeForce GTX 480. Although only 1-2 FPS ahead, the pair of CrossFireX AMD Radeon HD 6870's still earns a performance edge at the expense of higher total power consumption. When APEX PhysX is enabled on Mafia II, all Radeon graphics products are forced to use the CPU and performance quickly plummets.

DX11: Metro 2033

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
  • Moderate Settings: (Very-High Quality, AAA, 16x AF, Advanced DoF, Tessellation, 180s Fraps Chase Scene)

Metro 2033 Moderate Quality Settings

Cost Analysis: Metro 2033 (1920x1200)

• $242 Radeon HD 6870 1GB costs $10.39 per FPS
• $255 GeForce GTX 470 1GB costs $11.18 per FPS
• $324 Radeon HD 5870 1GB costs $14.53 per FPS
• $437 GeForce GTX 480 1536MB costs $14.86 per FPS
• $500 Radeon HD 5970 2GB costs $13.09 per FPS
• $500 GeForce GTX 580 1536MB costs $14.71 per FPS
• $484 Radeon HD 6870 CrossFireX costs $10.48 per FPS

Test Summary: There's no way to ignore the graphical demands of Metro 2033, and only the most powerful GPUs will deliver a decent visual experience using moderate quality settings. Even when these settings are turned down, as they were in our tests, Metro 2033 is a power-hungry video game that crushes frame rate performance. Although Metro 2033 offers advanced PhysX options, these settings are available only to NVIDIA GeForce video cards and disabled for all of our tests.

Metro 2033 proves to be too much for most video cards even when anti-aliasing is turned to its lowest setting, and causes the GeForce GTX 480 to perform at a barely playable 29.4 FPS. The inability to enjoy PhysX effects doesn't look like a huge drawback considering how low the other settings must be turned down, but that a decision for gamers. The NVIDIA GeForce GTX 580 may be the most powerful single-GPU video card available, but it's outperformed by the two closest dual-GPU options within its price point when Metro 2033 is involved.

DX11: Tom Clancy's HAWX2

Tom Clancy's H.A.W.X.2 has been optimized for DX11 enabled GPUs and has a number of enhancements to not only improve performance with DX11 enabled GPUs, but also greatly improve the visual experience while taking to the skies. 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 in question. This allows for a very low memory footprint and relies on the GPU power alone to expand the low resolution data to highly realistic detail.

The Tom Clancy's HAWX2 benchmark uses normal game content in the same conditions a player will find in the game, and allows users to evaluate the enhanced visuals that DirectX-11 tessellation adds into the game. The Tom Clancy's HAWX2 benchmark is built from exactly the same source code that's included with the retail version of the game. HAWX2's tessellation scheme uses a metric based on the length in pixels of the triangle edges. This value is currently set to 6 pixels per triangle edge, which provides an average triangle size of 18 pixels.

The end result is perhaps the best tessellation implementation seen in a game yet, providing a dramatic improvement in image quality over the non-tessellated case, and running at playable frame rates across a wide range of graphics hardware.

• Tom Clancy's HAWX 2 Benchmark 1.0.4
  • Extreme Settings: (Maximum Quality, 8x AA, 16x AF, DX11 Terrain Tessellation)

Tom Clancy's HAWX2 Extreme Quality Settings

Cost Analysis: Tom Clancy's HAWX2 (1920x1200)

• $242 Radeon HD 6870 1GB costs $3.56 per FPS
• $255 GeForce GTX 470 1GB costs $2.63 per FPS
• $324 Radeon HD 5870 1GB costs $5.40 per FPS
• $437 GeForce GTX 480 1536MB costs $3.55 per FPS
• $500 Radeon HD 5970 2GB costs $5.75 per FPS
• $500 GeForce GTX 580 1536MB costs $3.68 per FPS
• $484 Radeon HD 6870 CrossFireX costs $4.48 per FPS

Test Summary: This is a controversial game, at least in the sense that AMD has asked us not to use it for testing (which is why it wasn't included in the AMD Radeon 6850 and 6870 reviews) but NVIDIA endorses it. Our thinking is that HAWX 2 is a full retail product that will be purchased and played by consumers, regardless of how well Radeon products handle its tessellation. Tom Clancy's HAWX2 works incredibly well with the tessellation-optimized Fermi architecture, finally making NVIDIA's effort more transparent. Despite this benefit to GF100-series products, the game is primarily comprised of clear blue skies that require very little processing power. As a result, even a single AMD Radeon HD 6870 produces 68 FPS at 1920x1200.

When HAWX2 is turned up to use the highest possible quality settings with terrain tessellation enabled, the NVIDIA GeForce GTX 580 video card easily surpasses every product tested against it. Oddly enough, the newer but less-powerful AMD Radeon HD 6870 performs better than the older and more expensive ATI Radeon HD 5870: 10-FPS at 1680x1050 and 8-FPS at 1920x1200. This proves that AMD gave tessellation a little more emphasis on the Barts GPU (Cypress refresh), but doesn't give it enough power for two Radeon HD 6870's in CrossFire to do more than match performance with the GeForce GTX 470. Another twist is demonstrated by over-emphasized tessellation power of GF100 in NVIDIA's GeForce GTX 480, which gives it the strength to compete with the new GTX 580.

DX11: Unigine Heaven 2.1

The Unigine Heaven 2.1 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.

Although Heaven-2.1 was recently released and used for our DirectX-11 tests, the benchmark results were extremely close to those obtained with Heaven-1.0 testing. 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 2.1
  • Extreme Settings: (High Quality, Normal Tessellation, 16x AF, 4x AA

Heaven 2.1 Moderate Quality Settings

Cost Analysis: Unigine Heaven (1920x1200)

• $242 Radeon HD 6870 1GB costs $9.13 per FPS
• $255 GeForce GTX 470 1GB costs $8.67 per FPS
• $324 Radeon HD 5870 1GB costs $12.51 per FPS
• $437 GeForce GTX 480 1536MB costs $11.94 per FPS
• $500 Radeon HD 5970 2GB costs $11.39 per FPS
• $500 GeForce GTX 580 1536MB costs $11.16 per FPS
• $484 Radeon HD 6870 CrossFireX costs $9.18 per FPS

Test Summary: Reviewers like to say "Nobody plays a benchmark", but it seems evident that we can expect to see great things come from a graphics tool this detailed. For now though, those details only come by way of DirectX-11 video cards. Our 'extreme' test results with the Unigine Heaven benchmark tool appear to deliver fair comparisons of DirectX-11 graphics cards when set to higher quality levels. Heaven 2.1 is a very demanding benchmark tool, which is why tessellation is set to normal levels and antialiasing is reduced to 4x.

In Unigine's Heaven benchmark, both the AMD Radeon HD 6870 and ATI Radeon HD 5870 video cards trail behind the GeForce GTX 470, making the 5870's value rating is the worst of the entire bunch while the opposite is true for the GTX 470. The dual-GPU ATI Radeon HD 5970 is positioned between the older GeForce GTX 480 and new GeForce GTX 580, and all three share the $11 cost per FPS range. Combining two Radeon HD 6870 video cards into CrossFire will get you the best frame rate performance, and surprisingly, it nearly matches the best overall value.

Fermi GF110 GPU Overclocking

AMD and NVIDIA already stretch their GPUs pretty thin in terms of overclocking head room, but there's a difference between thin and non-existent. In this section, Benchmark Reviews overclocks the NVIDIA GeForce GTX 580 video card using MSI's free Afterburner utility. The MSI Afterburner "Graphics Card Performance Booster" application offers several adjustable variables to reach the desired overclock, and allows for voltage changes (increase/decrease). The aim of this project is to push the Fermi GF110 GPU as far as it could go without any extra power applied. Beginning with the maximum stable GPU clock speed, I slowly increased the settings until I began to see screen tearing or the Forceware driver crashed. Once I reached the most stable speeds for both GPU and GDDR5, I put the video card back into action with high-demand video games for additional benchmark tests. Here are the results:

GeForce GTX 580 Overclocking Results

Overclocking Summary: After re-testing the overclocked GeForce GTX 580 on eight different benchmarks, the increased performance amounted to 4.0-7.3% improvement in video frame rates. This may not seem like much of an overclock, and it's not, but considering that the GeForce GTX 580 already rests at the very top of NVIDIA's food chain it's not that surprising. The recent ASUS ENGTX480 Overclocking project used a refined GF100 GPU that yielded 12-17% improvements, while the AMD Radeon HD 6870 was limited to 6.5-9.3%. This reinforces the notion that higher-end processors have the least amount of headroom, but every extra frame translates into an advantage over your enemy.

GeForce GTX 580 Temperatures

Benchmark tests are always nice, so long as you care about comparing one product to another. But when you're an overclocker, gamer, or merely a PC hardware enthusiast who likes to tweak things on occasion, there's no substitute for good information. Benchmark Reviews has a very popular guide written on Overclocking Video Cards, which gives detailed instruction on how to tweak a graphics cards for better performance. Of course, not every video card has overclocking head room. Some products run so hot that they can't suffer any higher temperatures than they already do. This is why we measure the operating temperature of the video card products we test.

To begin my testing, I use GPU-Z to measure the temperature at idle as reported by the GPU. Next I use FurMark's "Torture Test" to generate maximum thermal load and record GPU temperatures at high-power 3D mode. The ambient room temperature remained at a stable 20°C throughout testing, while the inner-case temperature hovered around 37°C.

FurMark does two things extremely well: drive 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 discussed below are absolute maximum values, and not representative of real-world performance:

As a result of NVIDIA's new hardware power monitoring circuitry, temperatures are kept to their lowest level in many years. At first I suspected GPU load or power throttling, but there's no evidence of this on the GPU-Z histogram when we re-tested (at 26°C ambient room temp). Regardless, the nearly-ambient 32°C idle temperature and modestly warm 70°C loaded temp are something NVIDIA should be proud of... and the competition should take notice of.

VGA Power Consumption

UPDATE 11-NOV-2010: Benchmark Reviews has re-tested the GeForce GTX 580 video card for maximum power consumption. This section represents updated results.

For 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.

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 FurMark. Below is a chart with the isolated video card power consumption (system without video card minus measured total) displayed in Watts for each specified test product:

The NVIDIA GeForce GTX 580 surprised us with chilly idle and lukewarm loaded temperatures, and the surprises keep coming as we measure power consumption. The GeForce GTX 580 requires one eight-pin and one six-pin PCI-E power connection for proper operation. Resting at idle with no GPU load, the NVIDIA GeForce GTX 580 consumed 31W by our measure. Compensating for a small margin of error, this falls roughly in-line with idle power draw from the GeForce 8800 GT and slightly less than the GeForce GTX 280 or GTX 465. Most notably, it's considerably lower than the GF100 inside the GeForce GTX 480... by nearly 26%.

Once 3D-applications begin to demand power from the GPU, electrical power consumption climbs. Because the GeForce GTX 580 uses a new hardware power monitoring technology not included on previous GeForce models, we've had to work around the power-throttling effects enabled with FurMark or OCCT. To do so, we merely renamed Furmark.exe to Crysis.exe and changed some file names and locations. Measured at full throttle with FurMark's 3D 'torture' load, the GeForce GTX 580 topped out at 246W maximum power draw. NVIDIA's stated max TDP is 244W, which is falls within our measurements - even once efficiency rating and margin of error are factored in.

While the idle power draw is identical to older models like the GeForce 8800 GT, it's better than the GeForce GTX 280 and more recent GTX 465 models. At full power load the GeForce GTX 580 matches up to the ATI Radeon HD 5870, but still operates well below the levels of a Radeon HD 5970.

NVIDIA APEX PhysX Enhancements

Many of the latest video games are being developed with new graphical enhancement technologies in mind, such as APEX PhysX and 3D-Vision Surround. Each of these NVIDIA-developed technologies are designed to work their best on GeForce desktop graphics solutions, and only the most powerful GPUs can make the special effects stand out in full glory. While a single GeForce GTX 580 has enough power to enable all of the quality settings to their highest levels with APEX PhysX enabled, adding a second video cards for SLI opens up the possibilities for higher frame rate performance and excellent 3D-Vision performance.

Mafia II is the first PC video game title to include the new NVIDIA APEX PhysX framework, a powerful feature set that only GeForce video cards are built do deliver. While console versions will make use of PhysX, only the PC version supports NVIDIA's APEX PhysX physics modeling engine, which adds the following features: APEX Destruction, APEX Clothing, APEX Vegetation, and APEX Turbulence. PhysX helps make object movement more fluid and lifelike, such as cloth and debris. In this section, Benchmark Reviews details the differences made with- and without APEX PhysX enabled.

We begin with a scene from the Mafia II benchmark test, which has the player pinned down behind a brick column as the enemy shoots at him. Examine the image below, which was taken with a Radeon video card configured with all settings turned to their highest and APEX PhysX support disabled:

No PhysX = Cloth Blending and Missing Debris

Notice from the image above that when PhysX is disabled there is no broken stone debris on the ground. Cloth from foreground character's trench coat blends into his leg and remains in a static position relative to his body, as does the clothing on other (AI) characters. Now inspect the image below, which uses a GeForce graphics card with APEX PhysX enabled:

Realistic Cloth and Debris - High Quality Settings With PhysX

With APEX PhysX enabled, the cloth neatly sways with the contour of a characters body, and doesn't bleed into solid objects such as body parts. Additionally, APEX Clothing features improve realism by adding gravity and wind effects onto clothing, allowing for characters to look like they would in similar real-world environments.

Burning Destruction Smoke and Vapor Realism

Flames aren't exactly new to video games, but smoke plumes and heat vapor that mimic realistic movement have never looked as real as they do with APEX Turbulence. Fire and explosions added into a destructible environment is a potent combination for virtual-world mayhem, showcasing the new PhysX APEX Destruction feature.

Exploding Glass Shards and Bursting Flames

NVIDIA PhysX has changed video game explosions into something worthy of cinema-level special effects. Bursting windows explode into several unique shards of glass, and destroyed crates bust into splintered kindling. Smoke swirls and moves as if there's an actual air current, and flames move out towards open space all on their own. Surprisingly, there is very little impact on FPS performance with APEX PhysX enabled on GeForce video cards, and very little penalty for changing from medium (normal) to high settings.

NVIDIA 3D-Vision Effects

Readers familiar with Benchmark Reviews have undoubtedly heard of NVIDIA GeForce 3D Vision technology; if not from our review of the product, then for the Editor's Choice Award it's earned or the many times I've personally mentioned it in out articles. Put simply: it changes the game. 2010 has been a break-out year for 3D technology, and PC video games are leading the way. Mafia II is expands on the three-dimensional effects, and improves the 3D-Vision experience with out-of-screen effects. For readers unfamiliar with the technology, 3D-Vision is a feature only available to NVIDIA GeForce video cards.

Mafia 2 is absolutely phenomenal with 3D-Vision... and with its built-in multi-monitor profiles and bezel correction already factored this game is well suited for 3D-Vision Surround. Combining two GeForce GTX 580's into SLI allowed this game to play at 5760 x 1080 resolution across three monitors using upper-level settings with APEX PhysX enabled to deliver a thoroughly impressive experience. If you already own a 3D Vision kit and 120Hz monitor, Mafia II was built with 3D Vision in mind.

The first thing gamers should be aware of is the performance penalty for using 3D-Vision with a high-demand game like Mafia II. Using a GeForce GTX 480 video card as a point of reference, we experienced frame rate speeds up to 33 FPS with all settings configured to their highest and APEX PhysX set to high. However, when 3D Vision is enabled the video frame rate usually decrease by about 50%. This is no longer the hardfast rule, thanks to '3D Vision Ready' game titles that offer performance optimizations. Mafia II proved that the 3D Vision performance penalty can be as little as 30% with a single GeForce GTX 480 video card, or a mere 11% in SLI configuration. NVIDIA Forceware drivers will guide players to make custom-recommended adjustments specifically for each game they play, but PhysX and anti-aliasing will still reduce frame rate performance.

Of course, the out-of-screen effects are worth every dollar you spend on graphics hardware. In the image above, an explosion sends the car's wheel and door flying into the players face, followed by metal debris and sparks. When you're playing, this certainly helps to catch your attention... and when the objects become bullets passing by you, the added depth of field helps assist in player awareness.

Combined with APEX PhysX technology, NVIDIA's 3D-Vision brings destructible walls to life. As enemies shoot at the brick column, dirt and dust fly past the player forcing stones to tumble out towards you. Again, the added depth of field can help players pinpoint the origin of enemy threat, and improve response time without sustaining 'confusion damage'.

NVIDIA APEX Turbulence, a new PhysX feature, already adds an impressive level of realism to games (such as with Mafia II pictured in this section). Watching plumes of smoke and flames spill out towards your camera angle helps put you right into the thick of action.

NVIDIA 3D-Vision/3D-Vision Surround is the perfect addition to APEX PhysX technology, and capable video games will prove that these features reproduce lifelike scenery and destruction when they're used together. Glowing embers and fiery shards shooting past you seem very real when 3D-Vision pairs itself APEX PhysX technology, and there's finally a good reason to overpower the PCs graphics system.

Editor's Opinion: NVIDIA Fermi

My opinion of NVIDIA's Fermi architecture has changed over the past several months since it was first announced, due largely in part to refinements made to their graphics processor. Testing with NVIDIA's GF100 GPU held its own set of challenges, and many times the video cards based on this graphics processor seemed condemned by the inherited legacy of issues. From the flagship GeForce GTX 480 down to the GTX 465, Fermi impressed gamers with strong FPS performance... and that was about it. Thermal output and power consumption were unfashionably high, to which AMD constantly and consistently focused their marketing attacks. Then along comes GF104 on the GeForce GTX 460, a video card that completely changed the game.

NVIDIA's GeForce GTX 460 not only changed the collective opinion regarding their Fermi architecture, it also changed the GPU landscape. AMD held the upper hand by releasing a DirectX-11 video card first, but they've painted themselves into a corner with their Evergreen GPU. Unlike NVIDIA's Fermi architecture, which can shape-shift as desired, AMD's Cedar, Redwood, and Juniper GPUs are all simply slices of the same processor: Cypress. This is where intelligent consumers will spot the flaw: AMD came to the (video) card game and showed their entire hand from the first deal, while NVIDIA had a few spare aces up their sleeves. NVIDIA's GeForce GTX 480 is only 15/16 of the complete GF100 package, and we're just beginning to see what's possible with a 7/8-whole GF104 GPU with GTX 460. Now that AMD has unwrapped their Barts (Cypress refresh) GPU, NVIDIA returns to offer all 512 Fermi cores in the GF110 GPU.

Now that NVIDIA has finally cooked Fermi with the perfect blend of tessellation, shaders, and texture units, consumers are able to see what they've been missing. We poked around the inner workings for our NVIDIA GF100 GPU Fermi Graphics Architecture article, but the modular nature of this processor left a lot of uncertainty at the time. With AMD soon to launch their own counter-attack with the Caymen-equipped Radeon HD 6970, it's unclear just how long NVIDIA will keep it's position on the throne of discrete graphics. AMD proved that Barts can do more with less, just like NVIDIA has done with their reworked Fermi architecture, and so now it becomes a matter of finding the acceptable price point for the segment. Of course, this all depends on yield... something both vendors have struggled with as they continue to depend on TSMC for results.

NVIDIA GeForce Fermi Graphics Card Family

With Barts already on the shelf and GTX 580 arriving this week, AMD and NVIDIA are once again even-Steven in their competition for DirectX-11 supremacy. Now all that they need are some highly anticipated video games to showcase tessellation like never before and increase demand for their products as a result. Titles such as Tom Clancy's H.A.W.X.2 certainly showcase a beautifully realistic terrain, but low-end graphical processing requirements don't exactly help to sell the high-performance video cards. It's the games like Lost Planet 2 that will crush performance and push sales for top-end products, but the interest in this genre isn's nearly as strong as FPS titles such as Call of Duty: Black Ops or BattleField: Bad Company 2. Unfortunately for AMD and NVIDIA, most game developers are working to the hardware available inside console gaming systems, and not the more powerful desktop computers.

Even if you're only after raw gaming performance and have no real-world interest in CUDA, there's reason to appreciate the Fermi GF100-series GPU. New experience-enhancing products such as the NVIDIA GeForce 3D Vision double the demands on frame rate output and require more powerful graphics processing power as a direct result. This is where Fermi-based products deliver the performance necessary to enjoy the extended gaming experience. I'm a huge fan of the 3D experience, which is why 3D Vision earned our Editor's Choice Award and I've written a NVIDIA 3D-Vision Multimedia Resource Guide, and at the moment only Fermi-based GeForce video cards deliver the power necessary to drive up to three monitors for 3D-Vision Surround.

Some older game titles will also benefit from the Fermi architecture, beyond a simple increase in video frame rates. For example, Far Cry 2 (among others) will receive 32x CSAA functionality native to the game, but future NVIDIA Forceware driver updates could also further add new features into existing co-developed video games. NVIDIA's R260 Forceware release introduced new features enthusiasts have been wanting for quite some time, my favorite is the removal of previous driver files and extensions. Additionally, NVIDIA NEXUS technology brings CPU and GPU code development together in Microsoft Visual Studio 2008 for a shared process timeline. NEXUS also introduces the first hardware-based shader debugger. NVIDIA's GF100-series are the first GPUs to ever offer full C++ support, the programming language of choice among game developers.

Fermi is also the first GPU to support Error Correcting Code (ECC) based protection of data in memory. ECC was requested by GPU computing users to enhance data integrity in high performance computing environments. ECC is a highly desired feature in areas such as medical imaging and large-scale cluster computing. Naturally occurring radiation can cause a bit stored in memory to be altered, resulting in a soft error. ECC technology detects and corrects single-bit soft errors before they affect the system. Fermi's register files, shared memories, L1 caches, L2 cache, and DRAM memory are ECC protected, making it not only the most powerful GPU for HPC applications, but also the most reliable. In addition, Fermi supports industry standards for checking of data during transmission from chip to chip. All NVIDIA GPUs include support for the PCI Express standard for CRC check with retry at the data link layer. Fermi also supports the similar GDDR5 standard for CRC check with retry (aka "EDC") during transmission of data across the memory bus.

NVIDIA GeForce GTX 580 Conclusion

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. Benchmark Reviews begins our conclusion with a short summary for each of the areas that we rate.

UPDATE 11-NOV-2010: This article has been updated to provide results for two $229 EVGA GeForce GTX 460 FTW video cards in SLI.

Beginning with frame rate performance, the NVIDIA GeForce GTX 580 video card competes at a level comparable to the dual-GPU ATI Radeon HD 5970 and occasionally matched up well against a pair of AMD Radeon HD 6870's in CrossFireX configuration. All three of these options share the same $500 price point, and both offer similar DirectX 11 functionality. In comparison to the Fermi GF100-powered GeForce GTX 480, the GF110 proved that GeForce GTX 580 was far more than an added streaming multiprocessor and clock speed increase; it was the perfect blend of tessellation, shaders, and texture units we first witnessed with the GF104 inside GeForce GTX 460.

In our DirectX 10 tests, 3D Mark Vantage had the GeForce GTX 580 trailing slightly behind the Radeon HD 5970 and CrossFire 6870's in Jane Nash, but then it comes back and matches or exceeds them in New Calico. Crysis Warhead matches the GeForce GTX 580 to the Radeon HD 5970 equally, and both trail behind the Radeon 6870's in CrossFire. In our DirectX 11 tests, Aliens vs Predator puts the GeForce GTX 580 video card behind the Radeon 5970 and CrossFire 6870's, and then positions it between them for Battlefield: Bad Company 2. Then BattleForge, Lost Planet 2, and Mafia II all report the GeForce GTX 580 even with, or outperforming, the Radeon HD 5970 and CrossFire 6870's. Testing with Metro 2033 the GeForce GTX 580 takes a turn South, and both Radeon contenders surpass it. Tom Clancy's HAWX2 clearly works better with GeForce tessellation, putting the GTX 580 and all other NVIDIA products way ahead of AMD Radeon video cards. Finally, the Unigine Heaven benchmark confirms the trends we've seen in all the tests leading up to this, and position the GeForce GTX 580 slightly ahead of the dual-GPU ATI Radeon HD 5970 and trailing shortly behind a pair of AMD Radeon HD 6870's in CrossFireX.

Appearance is a more subjective matter since the rating doesn't have benchmark scores to fall back on. Partners traditionally offer their own unique twist on the design, with improved cooling solutions and colorful fan shroud designs. This might not happen with the GeForce GTX 580, because the video card operates so efficiently that improving an already effective cooling solution would be superfluous. The reference design allows nearly all of the heated air to externally exhaust outside of the computer case, which could be critically important to overclockers wanting the best possible environment for their computer hardware. This deep shroud chamfer also preserves the Fermi GF110 GPU in SLI sets. Overall, the GTX 580 might not look as tough as the GTX 480, but it doesn't need to overcompensate by exposing a few heat-pipes.

Defining value at the premium-priced high-end segment isn't easy, because hardware enthusiasts know that they're going to pay top dollar to own the top product. Even still, value is a fast moving target because the price on these products literally changes by the minute in this industry. NVIDIA suggests that the GeForce GTX 580 video card launch with a retail price of $499.99. It's expected that many of their add-in card partners will bundle a game or factory overclock the GPU to further increase the overall product value. Using the suggested pricing in conjunction with NewEgg's lowest average product pricing (as of 08 November 2010), the cost per frame performance analysis is illustrated in the charts below:

In summary, the GF110 GPU inside the GTX 580 clearly contrasts how far off the mark GF100 was when it launched with GTX 480, possibly lending credibility to the leap in series number (GeForce 400 vs 500). The NVIDIA GeForce GTX 580 redeems the Fermi architecture with performance results the enthusiast community can finally appreciate, along with reduced power consumption and thermal output everyone can be grateful for. These are all impressive enhancements to the series, and some will argue that it's what NVIDIA should have done with Fermi from the start.

Taking all aspects of the NVIDIA GeForce GTX 580 into consideration, there's really a lot more to like about the Fermi architecture now. The GF110 graphics processor finally has its priorities straight, and the dramatically efficient power consumption levels have reduced heat output to their lowest level in many years. The expensive price tag on the GTX 580 is something consumers of premium top-end graphics products might already be used to, but it's hard to like a $500 price point. I find myself reminded that this video card matches performance with a dual-GPU Radeon HD 5970 that was priced at $700 for the longest time, and the few remaining models have come down to Earth. And while the GTX 580 proves itself a contender against the 5970, there's still the small matter of two AMD Radeon HD 6870's combined into CrossFire to consider. This will ultimately be a decision for the consumer, who either wants the best overall performance a single card can offer along with several proprietary features benefits only available from NVIDIA, or they'll settle for two lesser products that produce comparable frame rates.

So what do you think of NVIDIA's GeForce GTX 580 video card? Leave comments below, or ask questions in our Forum.

Pros:

+ Fastest single-unit DX11 graphics accelerator available
+ Matches performance with dual-GPU Radeon HD 5970
+ Outstanding performance for ultra high-end games
+ Much lower power consumption vs GTX 480
+ Reduced heat output and cooling fan noise
+ Fan exhausts all heated air outside of case
+ Includes native HDMI audio/video output
+ Adds 32x CSAA post-processing detail
+ Supports triple-SLI functionality
+ Adds Error Correcting Code (ECC)

Cons:

- Very expensive premium-level product
- Outperformed by overclocked GTX 460's in SLI
- Outperformed by CrossFire Radeon HD 6870's

Ratings:

• Performance: 10.0
• Appearance: 9.25
• Construction: 9.75
• Functionality: 9.75
• Value: 6.25

Final Score: 9.0 out of 10.

Related Articles:

• MSI R6870 Radeon HD 6870 Video Card
• ASUS P8Z77-V Deluxe Motherboard Components
• Sunbeam SATA-IDE-USB Adapter
• Biostar TA890GXB-HD mATX AMD Motherboard
• ASUS ENGT240 1GB GDDR3 Video Card
• EVGA UV Plus+ UV-19 USB Display Hub
• ASUS ENGTX260 Matrix GeForce GTX 260 Video Card
• Thermaltake Toughpower W0133RU 1200W Modular PSU
• Apevia X-Qpack 2 CM500 Camouflage SFF Case
• Fractal Design Define XL Computer Case