We are a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for us to earn fees by linking to Amazon.com and affiliated sites.

[nextpage title=”Introduction”]

NVIDIA has recently released its fastest GPU to date, the GeForce GTX 580. Let’s see how it compares to what was until then the fastest NVIDIA GPU, the GeForce GTX 480, and its competitors from AMD.

The video card we are reviewing is the reference model from NVIDIA. When a video card is first launched, all “manufacturers” buy their video cards already assembled from NVIDIA and only add their sticker to it. One or other manufacturer may add an overclocking, but physically all cards are absolutely identical. Only after a while manufacturers start launching customized solutions, changing the cooler and, sometimes, redesigning the printed circuit board.

The new GeForce GTX 580 can be found between USD 520 and USD 580, which puts it as the most expensive video card available on the market today. The Radeon HD 5970, which is the most powerful video card using an AMD GPU, can be bought for USD 500. In this review we will be comparing the GeForce GTX 580 to the GeForce GTX 480 and to the Radeon HD 5970. We also decided to compare the GeForce GTX 580 to two Radeon HD 6870 video cards in CrossFireX mode. Since each one of them cost around USD 260, this setup competes directly with the GeForce GTX 580.

In the table below we compare the main specs of the video cards included in our review. As mentioned, we connected two Radeon HD 6870 in parallel, and the specs below are for only one video card. The Radeon HD 5970 has two GPUs, and the specs below are for only one of the GPUs (this video card has a total of 2 GB, 1 GB connected to each GPU).

Video Card Core Clock Shader Clock Memory Clock (Real) Memory Clock (Effective) Memory Interface Memory Transfer Rate Memory Shaders Price
GeForce GTX 480 700 1,401 MHz 924 MHz 3,696 MHz 384-bit 177.4 GB/s 1.5 GB GDDR5 480 USD 450 – 510
GeForce GTX 580 772 MHz 1,544 MHz 1,002 MHz 4,008 MHz 384-bit 192.4 GB/s 1.5 GB GDDR5 512 USD 520 –580
Radeon HD 6870 900 MHz 900 MHz 1.05 GHz 4.2 GHz 256-bit 134.4 GB/s 1 GB GDDR5 1,120 USD 260 – 270
Radeon HD 5970 725 MHz 725 MHz 1 GHz 4 GHz 256-bit 128 GB/s 1 GB GDDR5 1,600 USD 500

Prices were researched at Newegg.com on the day we published this review. All graphics chip listed above are DirectX 11 parts.

You can compare the specs of these video cards with other video cards by taking a look at our AMD ATI Chips Comparison Table and NVIDIA Chips Comparison Table tutorials. 

Now let’s take an in-depth look at the GeForce GTX 580 reference model.

[nextpage title=”The NVIDIA GeForce GTX 580″]

Below we have an overall look at the NVIDIA GeForce GTX 580 reference model.

NVIDIA GeForce GTX 580Figure 1: NVIDIA GeForce GTX 580

NVIDIA GeForce GTX 580Figure 2: NVIDIA GeForce GTX 580

This video card has two DVI-D and one HDMI connectors.

NVIDIA GeForce GTX 580Figure 3: Video connectors

[nextpage title=”The NVIDIA GeForce GTX 580 (Cont’d)”]

In Figure 4, you can see the video card with its cooler removed. Note how it requires one six- and one eight-pin auxiliary power connectors. In Figures 5 and 6, you can see the cooler by itself. It has a copper base using vapor chamber technology, which is the same technology behind heat-pipes.

NVIDIA GeForce GTX 580Figure 4: Video card with the cooler removed

NVIDIA GeForce GTX 580Figure 5: The GPU cooler

NVIDIA GeForce GTX 580Figure 6: The GPU cooler

The reviewed card uses 12 1 Gbit GDDR5 chips, making its 1.5 GB video memory (1 Gbit x 12 = 1.5 GB). Each chip is connected to the GPU using a 32-bit data lane, making the video card’s 384-bit memory interface (32 bits x 12 = 384).

The chips used are K4G10325FE-HC04 parts from Samsung, which support up to 1.25 GHz (4.5 GHz QDR) and since on this video card memory is accessed at 1 GHz (4 GHz QDR), there is a nice 12.5% margin for you to increase the memory clock rate while keeping the chips inside the maximum they support. Of course you can always try to overclock the memory chips above their specs.

NVIDIA GeForce GTX 580Figure 7: Memory chips

Before seeing the performance results, let’s recap the main features of this video card.

[nextpage title=”Main Specifications”]

The main specifications for the NVIDIA GeForce GTX 580 video card include:

  • Graphics chip: NVIDIA GeForce GTX 580 running at 772 MHz
  • Memory: 1.5 GB GDDR5 memory (384-bit interface) from Samsung (K4G10325FE-HC04), running at 1,002 MHz (4,008 MHz, QDR)
  • Bus type: PCI Express x16 2.0
  • Video Connectors: Two DVI-D and one HDMI
  • Video Capture (VIVO): No
  • Cables and adapters that come with this board: NA
  • Number of CDs/DVDs that come with this board: NA
  • Games included: NA
  • Programs included: NA
  • More information: https://www.nvidia.com
  • Average Price in the US*: USD 550.00

* Researched at Newegg.com on the day we published this
review.

[nextpage title=”How We Tested”]

During our benchmarking sessions, we used the configuration listed below. Between our benchmarking sessions the only variable was the video card being tested.

Hardware Configuration

Software Configuration

  • Windows 7 Ultimate 64-bit
  • Video resolution: 2560×1600 @ 60 Hz

Driver Versions

  • AMD/ATI video driver version: Catalyst 10.10
  • NVIDIA video driver version: 260.99
  • Intel Inf driver version: 9.1.2.1008

Software Used

Error Margin

We adopted a 3% error margin. Thus, differences below 3% cannot be considered relevant. In other words, products with a performance difference below 3% should be considered as having similar performance.

[nextpage title=”3DMark Vantage Professional”]

3DMark Vantage measures Shader 4.0 (i.e., DirectX 10) performance and supports PhysX, a programming interface developed by Ageia (now part of NVIDIA) to transfer physics calculations from the system CPU to the video card GPU in order to increase performance. Mechanical physics is the basis for calculations about the interaction of objects. For example, if you shoot, what exactly will happen to the object when the bullet hits it? Will it break? Will it move? Will the bullet bounce back? Note that since we are considering only the GPU score provided by this program, physics calculations are not taken into account.

We ran this program at three 16:10 widescreen resolutions, 1680×1050, 1920×1200, and 2560×1600. First we used the “Performance” profile, and then we used the “Extreme” profile (basically enabling anti-aliasing at 4x, anisotropic filtering at 16x, and putting all detail settings at their maximum or “extreme” values). The results being compared are the “GPU Scores” achieved by each video card.

NVIDIA GeForce GTX 580

3DMark Vantage – Performance 1680×1050 Difference
Radeon HD 6870 x2 – CrossFireX 21920 13%
Radeon HD 5970 20880 8%
GeForce GTX 580 19371  
GeForce GTX 480 14821 -23%

NVIDIA GeForce GTX 580

3DMark Vantage – Performance 1920×1200 Difference
Radeon HD 6870 x2 – CrossFireX 18424 19%
Radeon HD 5970 17298 12%
GeForce GTX 580 15469  
GeForce GTX 480 11532 -25%

NVIDIA GeForce GTX 580

3DMark Vantage – Performance 2560×1600 Difference
Radeon HD 6870 x2 – CrossFireX 11338 26%
Radeon HD 5970 10527 17%
GeForce GTX 580 8985  
GeForce GTX 480 6625 -26%

NVIDIA GeForce GTX 580

3DMark Vantage – Extreme 1680×1050 Difference
Radeon HD 6870 x2 – CrossFireX 16968 7%
Radeon HD 5970 16330 3%
GeForce GTX 580 15882  
GeForce GTX 480 12160 -23%

NVIDIA GeForce GTX 580

3DMark Vantage – Extreme 1920×1200 Difference
Radeon HD 6870 x2 – CrossFireX 14162 12%
Radeon HD 5970 13497 7%
GeForce GTX 580 12638  
GeForce GTX 480 9580 -24%

NVIDIA GeForce GTX 580

3DMark Vantage – Extreme 2560×1600 Difference
Radeon HD 6870 x2 – CrossFireX 8529 15%
Radeon HD 5970 8239 11%
GeForce GTX 580 7409  
GeForce GTX 480 5616 -24%

[nextpage title=”Call of Duty 4″]

Call of Duty 4 is a DirectX 9 game implementing high-dynamic range (HDR) and its own physics engine, which is used to calculate how objects interact. For example, if you shoot, exactly what will happen to the object when the bullet hits it? Will it break? Will it move? Will the bullet bounce back? It gives a more realistic experience to the user.

To get accurate results, we had to disable the 80 FPS limit in the game. To do this, input the command, “/seta com_maxfps 1000” (minus the quotes) into the console (` key). It can be set to any number greater than 200.

We ran this program at three 16:10 widescreen resolutions, 1680×1050, 1920×1200, and 2560×1600, maxing out all image quality controls (i.e., everything was set to the maximum values in the Graphics and Texture menus). We used the internal game benchmarking feature, running a demo provided by NVIDIA called “wetwork.” We are putting this demo here for downloading if you want to run your own benchmarks. We ran the demo five times, and the results below are the average number of frames per second (FPS) achieved by each video card.

NVIDIA GeForce GTX 580

Call of Duty 4 – Maximum 1680×1050 Difference
Radeon HD 6870 x2 – CrossFireX 176.4 2%
GeForce GTX 580 172.3  
Radeon HD 5970 168.2 -2%
GeForce GTX 480 164.2 -5%

NVIDIA GeForce GTX 580

Call of Duty 4 – Maximum 1920×1200 Difference
Radeon HD 6870 x2 – CrossFireX 170.1 7%
Radeon HD 5970 164.4 4%
GeForce GTX 580 158.6  
GeForce GTX 480 146.2 -8%

NVIDIA GeForce GTX 580

Call of Duty 4 – Maximum 2560×1600 Difference
Radeon HD 6870 x2 – CrossFireX 139.4 23%
Radeon HD 5970 135.2 19%
GeForce GTX 580 113.7  
GeForce GTX 480 100.3 -12%

[nextpage title=”Crysis Warhead”]

Crysis Warhead is a DirectX 10 game based on the same engine as the original Crysis, but optimized (it runs under DirectX 9.0c when installed on Windows XP).

We used the HardwareOC Crysis Warhead Benchmark Tool to collect the data for this test.We ran this program at three 16:10 widescreen resolutions, 1680×1050, 1920×1200, and 2560×1600, all at very high image quality (but with no anti-aliasing and no anisotropic filtering) and using the Airfield demo. The results below are the number of frames per second achieved by each video card.

NVIDIA GeForce GTX 580

Crysis Warhead – Very High 1680×1050 Difference
Radeon HD 6870 x2 – CrossFireX 51 13%
Radeon HD 5970 48 7%
GeForce GTX 580 45  
GeForce GTX 480 43 -4%

NVIDIA GeForce GTX 580

Crysis Warhead – Very High 1920×1200 Difference
Radeon HD 6870 x2 – CrossFireX 48 23%
Radeon HD 5970 44 13%
GeForce GTX 580 39  
GeForce GTX 480 37 -5%

NVIDIA GeForce GTX 580

Crysis Warhead – Very High 2560×1600 Difference
Radeon HD 6870 x2 – CrossFireX 34 31%
Radeon HD 5970 30 15%
GeForce GTX 580 26  
GeForce GTX 480 24 -8%

[nextpage title=”Far Cry 2″]

Far Cry 2 is based on an entirely new game engine called Dunia, which is DirectX 10 when played under Windows Vista with a DirectX 10 compatible video card.

We used the benchmarking utility that comes with this game, setting image quality to Ultra High (x8 anti-aliasing) and running the “Ranch Long” demo three times. The results below are expressed in frames per second and are an arithmetic average of the three results collected.

NVIDIA GeForce GTX 580

FarCry 2 – Ultra 1680×1050 Difference
Radeon HD 6870 x2 – CrossFireX 129.0 11%
GeForce GTX 580 116.7  
Radeon HD 5970 109.2 -6%
GeForce GTX 480 103.3 -12%

NVIDIA GeForce GTX 580

FarCry 2 – Ultra 1920×1200 Difference
Radeon HD 6870 x2 – CrossFireX 118.2 17%
GeForce GTX 580 101.1  
Radeon HD 5970 96.2 -5%
GeForce GTX 480 88.8 -12%

NVIDIA GeForce GTX 580

FarCry 2 – Ultra 2560×1600 Difference
Radeon HD 6870 x2 – CrossFireX 80.5 17%
GeForce GTX 580 69.0  
Radeon HD 5970 64.9 -6%
GeForce GTX 480 59.5 -14%

[nextpage title=”Aliens vs. Predator”]

Aliens vs. Predator is a DirectX 11 game that makes full use of tessellation and advanced shadow rendering. We used the Aliens vs. Predator Benchmark Tool developed by Rebellion. This program reads its configuration from a textfile (our configuration files can be found here). We ran this program at 1680×1050, 1920×1200, and 2560×1600 resolutions, with max texture settings, 32x anisotropic filtering and 8x anti-aliasing.

NVIDIA GeForce GTX 580

Aliens vs. Predator 1680×1050 Difference
Radeon HD 6870 x2 – CrossFireX 62.8 21%
Radeon HD 5970 61.3 18%
GeForce GTX 580 52.0  
GeForce GTX 480 44.7 -14%

NVIDIA GeForce GTX 580

Aliens vs. Predator 1920×1200 Difference
Radeon HD 6870 x2 – CrossFireX 51.4 21%
Radeon HD 5970 50.4 18%
GeForce GTX 580 42.6  
GeForce GTX 480 37.3 -12%

NVIDIA GeForce GTX 580

Aliens vs. Predator 2560×1600 Difference
Radeon HD 6870 x2 – CrossFireX 31.6 17%
Radeon HD 5970 30.8 14%
GeForce GTX 580 27.1  
GeForce GTX 480 23.2 -14%

[nextpage title=”Lost Planet 2″]

Lost Planet 2 is a game that uses a lot of DirectX 11 features, like tessellation (to round out the edges of polygonal models), displacement maps (added to the tessellated mesh to add fine grain details), DirectCompute soft body simulation (to introduce more realism in the “boss” monsters), and DirectCompute wave simulation (to introduce more realism in the physics calculations in water surfaces; when you move or when gunshots and explosions hit the water, it moves accordingly). We reviewed the video cards using Lost Planet 2 internal benchmarking features, choosing the “Benchmark A” (we know that “Benchmark B” is the one recommended for reviewing video cards, however, at least with us, results were inconsistent). We set graphics at “high,” anti-aliasing at “MSAA8x” and DX11 at “full.” The results below are the number of frames per second generated by each video card.

NVIDIA GeForce GTX 580

Lost Planet 2 1680×1050 Difference
GeForce GTX 580 50.90  
Radeon HD 6870 x2 – CrossFireX 49.50 -3%
Radeon HD 5970 46.70 -8%
GeForce GTX 480 42.40 -17%

NVIDIA GeForce GTX 580

Lost Planet 2 1920×1200 Difference
GeForce GTX 580 44.70  
Radeon HD 6870 x2 – CrossFireX 41.20 -8%
Radeon HD 5970 40.20 -10%
GeForce GTX 480 37.30 -17%

NVIDIA GeForce GTX 580

Lost Planet 2 2560×1600 Difference
GeForce GTX 580 31.70  
Radeon HD 6870 x2 – CrossFireX 31.50 -1%
Radeon HD 5970 30.10 -5%
GeForce GTX 480 26.50 -16%

[nextpage title=”Conclusions”]

The new GeForce GTX 580 is indeed the fastest NVIDIA GPU ever released. It was between 31% and 36% faster on 3DMark Vantage and between 5% and 20% faster on games than its predecessor, the GeForce GTX 480.

However, it may not the fastest video card around. The Radeon HD 5970 was up to 19% faster than the GeForce GTX 580 in most games and simulations we ran. The only two games where the GeForce GTX 580 was faster than the Radeon HD 5970 were Far Cry 2 (between 5% and 7%) and Lost Planet 2 (between 5% and 11%). Since the Radeon HD 5970 is cheaper than the new GeForce GTX 580, we believe
its competitor from AMD brings a better bang for the buck.

Another alternative if you have around USD 500 to spend on a video card is to buy two Radeon HD 6870 cards and connect them in CrossFireX. In our tests this configuration proved to be up to 31% faster (and a little bit cheaper) than a single GeForce GTX 580. The only exception was on Lost Planet 2, where the new NVIDIA video card was up to 8% faster. The advantage of this configuration is that you don’t need to buy the two video cards at the same time, so if money is short, you can buy one today and the second card when that extra money shows up.