GeForce 500 Series

The Geforce 500 series is a series of desktop graphics chip company Nvidia and successor of the GeForce 400 series. All graphics processors of this series support Shader Model 5.0 (SM 5.0), DirectX 11 and OpenCL, CUDA and PhysX with it.

• 6.1 Measurement of power consumption of a whole system

Description

The first graphics card in the GeForce 500 series, Nvidia introduced before 9 November 2010. It is the GeForce GTX 580, which used the GF110 graphics processor. This is still based on the Fermi architecture of the GeForce 400 series, but in a slightly different version, the designated Nvidia CEO Jen -Hsun Huang as a " mid-life kicker". Nevertheless, it is technically the GF110 "only" a remake of the GF100 in a revised stepping. So full FP16 filtering has been added and improved the Z- Cull - efficiency. To reduce leakage currents and thus reduce the power consumption of partial fast switching transistors were replaced by slower models. In her presentation, the Geforce GTX 580 had a 20 % to about 15% higher in performance than the GeForce GTX 480 and solved this the fastest single-GPU card on the market. Since the later published competitor from AMD, the Radeon HD 6970, only about the performance of the Geforce GTX 480/570 reached, the GTX 580 will be the fastest single-GPU card in a monopoly position in the market. After the GTX 480 has been criticized in the press, among others, due to their high volume, built on the Nvidia GTX 580, a new dual-slot cooling system that relies on a proprietary Vapor Chamber technology of copper. Thus, the Geforce GTX 580 had a significantly lower noise. The second major criticism of the Geforce GTX 480, the high power consumption, Nvidia achieved, however, only marginal improvements. The GeForce GTX 580 is the first graphics card from Nvidia in the high-end sector since the Geforce GTX 285, where the GPU is used in the maximum configuration. The Geforce 400 series this was not possible due to problems with the 40nm manufacturing process at TSMC and too high a heat. On 7 December 2010, the Geforce GTX 570, in which a shader cluster of the GF110 graphics processor has been disabled followed. They thus reached almost exactly the performance of the Geforce GTX 480, but had higher values ​​in the range Power consumption and noise on, however, the graphics memory of 1536 MB to 1280 MB had been reduced.

A special feature of the series, the presented March 24, 2011 Geforce GTX 590 dar. It is Nvidia's first official dual-GPU graphics card since the Geforce GTX 295, after no such derivative at the Geforce 400 series on the market had been taken. It is based on two GF110 GPUs in full expansion, which are operated compared to the Geforce GTX 580 with significantly reduced clock rates. However, Nvidia officially as TDP of 365 watts, which is outside of the PCI -SIG specifications. This has already been a few weeks earlier broken by the Radeon HD 6990, with which the GTX 590 competed for the performance crown, both cards new negative records achieved in the area of ​​power consumption.

On 25 January 2011, Nvidia introduced the GeForce GTX 560 Ti as successor to the successful Geforce GTX 460. As a basis now served the GF114 graphics processor in which it is a refresh of the GF104. As with the GF110 thereby partially fast-switching transistors were replaced by slower models in order to avoid leakage currents and thus reduce the power consumption. In contrast to the GF104 GF114 on the GeForce GTX 560 is the Ti used in full configuration, whereas a shader cluster was turned off on the GTX 460. Together with higher clock rates, a 30 % increase in 3D performance reached the GTX 560 in about as the GTX 460 thus this is 6870 and 6950th used in the market between the AMD Radeon HD competitors With the GeForce GTX 560 Ti Nvidia placed for the first time since the Geforce 4 series of 2002, the abbreviation Ti ( Titanium) again. Another model based on the GF114 in the form of the GeForce GTX 560 (without the symbol Ti ) presented Nvidia on May 17, 2011. Then in this one shader cluster of GPU was disabled, so this is ultimately a higher clocked version of the GeForce GTX 460 (including the improved steppings of GF114 ). The GTX 560 reached in about the performance of the Radeon HD 6870th Nvidia announced at the map before no official reference design, but left this to the board partners. For both GTX 560 models presented Nvidia nor special versions for the OEM market, but technically much different from the retail version, because they are based on teildeaktivierten GF110 GPUs.

On 15 March 2011, Nvidia Geforce GTX 550 Ti introduced the prior based on the GF116 GPU. The map represents the successor of the GeForce GTS 450, Nvidia said by amending the name scheme and gave the abbreviation GTS. Instead, Nvidia now uses here the GTX abbreviation, which was criticized in the press, because it means that membership was suggested for performance and high-end sector, which was not available. A special feature of the GTX 550 Ti, the memory configuration: even though a 192 -bit memory interface is used, the Vram size is 1024 MB. NVIDIA accomplishes this by connecting two 256 MB on two memory controllers and even 512 MB ​​to the third. Regardless of approximately reaches the Geforce GTX 550 Ti performance of the 18 months previously presented Radeon HD 5770 (later renamed Radeon HD 6770 ), the GTX 550 it requires more power. For the OEM market brought out Nvidia Geforce GT nor the 545, in which a shader cluster the GF116 GPU has been disabled.

On April 12, 2011, Nvidia introduced the GeForce GT 520 before that uses the GF119 graphics processor, the video processor VP5 first is used. A clock reduced variant followed the end of September under the name GeForce 510 early on May 11, 2011, the GeForce GT 530 was introduced for the OEM market, where it is practically seen a new version of the GeForce GT 430 is based on the GF118 graphics processor.

GPUs

Naming

The Geforce 500 series, the naming scheme is used, which was first introduced with the Geforce 200 - series desktop. All graphics chips are identified by a letter abbreviation for the classification of the power sector as well as a three-digit number, which generally starts with a 5 ( for Geforce 500). The last two digits are used for further differentiation within each service sector.

Abbreviation

The abbreviation have largely lost their meaning in this series. From mainstream to high- end everything will once sold under the high-end performance and standing symbol GTX. In the low-end segment, there is the GT- shortcuts.

Model data

Notes:

• The specified clock rates are the established recommended by Nvidia or. However, is the final determination of the clock rates in the hands of the respective graphics card manufacturer. Therefore, it is quite possible that there are graphics cards models or will be having different clock speeds.
• With the stated date of the appointment of the public presentation is given, not the date of availability of the models.
• ROP stands for Raster Operation Processor.

Performance

For each model, the following theoretical power data:

Notes:

• The above performance data for the computing power of the stream processors, the pixel fill rate, the Texelfüllrate and memory bandwidth are the theoretical maximum values. The overall performance of a graphics card depends, among other things, on how well the available resources can be exploited or utilized. In addition, there are other not listed here, factors that affect the performance.
• The specified processing power on the stream processors is not directly comparable with information on theoretical performance values ​​of other architectures.

Power consumption data

The measured values ​​listed in the table refer to the pure power of graphics cards that comply with the Nvidia reference design. In order to measure these values ​​, it requires a special measuring apparatus; depending on the employed measurement technique and given measurement conditions, including the shared program, with which the 3D load is generated, the values ​​between different equipment may vary. Therefore, here measured value ranges are specified, each representing the lowest and highest measured values ​​from different sources.

Far more common than the measurement of the consumption of the graphics card is to determine the power consumption of a whole system. To this end, a reference system is assembled, in which the various graphics cards to be installed; then finds the measurement using an energy cost meter or similar apparatus rather than directly to the outlet. However, the significance of the measurements is limited: it is not clear which consumption comes from the graphics card and what is attributable to the rest of the PC system. The difference in consumption between idle and load 3D operation of this measuring method is not only dependent on the program with which the load was produced; the utilization and efficiency of the rest of the PC system, including the power supply, motherboard and processor affect the measured difference also. Because different the tested systems are usually of one's own home PC system, the values ​​given there can not be mapped to its own system. Only data from otherwise identical systems are good (conditional) for comparison with each other. Because of this dependence overall system measurement values ​​are not listed in the local table. But since they can provide a better picture of the practical power of a concrete system with a certain graphics card, pages are listed under the links that are undertaking such measurements.