GeForce 200 Series

The GeForce 200 Series is a series of desktop graphics chip company Nvidia and successor of the GeForce 9 series. All graphics processors of this series support Shader Model 4.0 (SM 4.0 ) to DirectX 10, OpenGL 3.3, CUDA and PhysX with it.

• 5.1 Measurement of power consumption of a whole system

Description

On 16 June 2008 Nvidia introduced the GeForce GTX 280 and 260, on which the GT200 chip is installed. This was more than 1.4 billion transistors to the hitherto complex and with a die area of 576 mm ² and is the largest GPU, which had been installed on a graphics card. The GT200 is based on the unified shader architecture of the G80 graphics processor, but is equipped with various improvements. Firstly, it is optimized for CUDA applications, a memory buffer between the stream processors for example, was integrated and increases the register size. In addition, the GT200 supports with the help of specially inserted for this purpose processing units and the double-precision arithmetic, while the predecessor rule only single precision. As the size of the chip and the number of stream processors for each cluster has been increased from 16 to 24. Thus, the ratio of shaders to TMUs of 2:1 increased the G80 and G92 on 3-1. Off the further optimization of the chip, such as the improvements to the thread scheduler a power saving function has been introduced, so that one comes despite higher computing power and higher load consumption in 2D mode with the consumption of the predecessor. A disadvantage is the production proved in 65 nm, since AMD had already produced in 55nm process, the Radeon HD 4000 series and thus could be more cost efficient.

The GeForce GTX 280 has about the performance of the dual-chip graphics card Geforce 9800 GX2. Following the success of previous series, the GTX 280 could not meet the sometimes very high expectations, even though they 4870 X2 was the fastest graphics card on the market until the introduction of the Radeon HD. On the GeForce GTX 260, two clusters of the GT200 GPU are disabled ( ie still 192 active stream processors ), and the memory interface and memory configuration reduced. Since approximately the same fast Radeon HD 4870 from AMD was offered much cheaper on the market, revised Nvidia GTX 260 On 16 September 2008 we introduced the GeForce GTX 260 with 216 Stream Processors. For this only one shader cluster is still disabled, thereby increasing the performance somewhat. As a result, the revised GTX 260 sold significantly more successful in the market.

On 18 December 2008, Nvidia announced the dual-GPU graphics card Geforce GTX 295 for 8 January 2009, officially, again produced the most powerful graphics card on the market with the Nvidia. The GTX 295 initially consisted of two individual boards, which were composed in the so -called " sandwich " design. To reduce production costs, Nvidia changed in May 2009 on a simpler single board layout, on which the two graphics cores are placed. The revised GeForce GTX 295 was introduced by Nvidia's board partners at Computex in June 2009. Also on 8 January, the GeForce GTX 285 was officially introduced to replace the GeForce GTX 280. Although she was already available at the launch, the official launch of the GeForce GTX 285 was postponed to January 15. Compared to its predecessor, the GTX 285 had improved by about 10 % on performance, at the same time the power consumption could be lowered so that now two 6 -pin connector instead of a 6-pin and one 8- pins are required (see text). Although the GTX 285, just like the GTX 295, a so-called " Spulenfiepen " has under certain circumstances, they sold relatively successful in the market. This is generally attributed to the fact that the GTX 285 could be offered much cheaper than its predecessor and by the lack of competing products as the fastest single- GPU card occupied a monopoly position. For observers was unexpected that Nvidia had removed the hybrid power mode when the Geforce GTX 295 and GTX 285. Both cards are based on the GT200b chip ( unofficially known as the GT206 ), where it is a 55nm derivative of the GT200 chip. Already in December 2008, Nvidia had the GTX 260 comes with the new GT200b chip.

On 3 March 2009, Nvidia announced at Cebit on the Geforce GTS 250 for March 10. Thus, the Geforce 200 series was officially extended to the performance sector. However, it is at the GTS 250 is a new version of the GeForce 9800 GTX , which is still based on the G92 chip. Since it has already been used in the Geforce 8 series, Nvidia came to naming the subject of criticism. Unlike previous editions is at the GTS 250 but not a pure remake, since Nvidia introduced by various changes to the board layout, doubled the video memory to 1024 MB and a power saving mode einbaute. In a likewise anticipated new version of the GeForce 9800 GT under the name GeForce GTS 240 Nvidia avoided any immediate. 24 July 2009 Nvidia presented them with slightly higher clock rates but then for the OEM market.

When AMD launched on April 2, the Radeon HD 4890 brought to the market, Nvidia still responded the same day with the presentation of Geforce GTX 275 based on the GT200b chip. However, this was not yet universally available on the market as opposed to the competition card, which is why we speak of a so-called "Paper Launch". Both cards offer about the performance of the Geforce GTX 280 already no longer produced and placed exactly between the GTX 260 (216 SPs) and GTX 285 enabled on the GTX 275 are, just like on the GTX 285, all shader cluster. However, the GT200b chip is operated at a higher core voltage, resulting in spite of reduced clock rate to a slightly higher power consumption ( see text).

The first cards based on the manufactured in 40 nm GT21x GPUs Nvidia introduced before 15 June 2009. However, these were to notebook graphics cards of the GeForce 200M series. The first desktop card followed on 8 July, where it was the GeForce G210 and GT 220 for the OEM market. On these graphics processors GT216 and GT218 were used. After the Series Notebook Nvidia had with these two cards in the desktop market for the first time a DirectX 10.1. Since the beginning of 2009 block OEM graphics cards under the name GeForce GT 230, it is a remake of the older GeForce 9600 GT. The maps correspond to any reference design and are not officially out of Nvidia. On 12 October 2009 Nvidia Geforce G210 and led the GT 220 also on the retail market, and expanded so that the Geforce 200 series on the mainstream and low-budget sector. However, while the Geforce G210 was renamed to GeForce 210 and GT 220 comes with minimally higher clock rates. On 17 November 2009 Nvidia Geforce GT 240 placed the in the mainstream sector, which replaced the successful GeForce 9600 GT, whose performance they had also. The GT 240 is based on the GT215 graphics processor, which was installed on the mobile graphics card Geforce GTS 250M and GTS 260M since the summer of 2009. At the completion of the GT212 graphics processor, which was already listed in the beta driver 185.20, waived Nvidia.

GPUs

Naming

The Geforce 200 series Nvidia introduced a new naming scheme. All graphics chips are identified by a letter abbreviation for the classification of the power sector as well as a three-digit number that generally begins with a 2 ( for Geforce 200). The last two digits are used for further differentiation within each service sector.

Abbreviation:

• G or no prefix - low budget
• GT - Mainstream
• GTS - Performance
• GTX - high-end

Given the general slump in market prices and currency fluctuations, the original classifications of Nvidia do not apply generally.

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.
• The clock frequency of the memory is also often reported as twice. The reason for this is the double data rate (DDR ).

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 refers to the use of both MUL operations, which is not reached in graphics shader calculations, as further calculations must be performed. In these calculations, therefore the performance of the computing power is lower on the stream processors.

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 put together, 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. Since distinguish the tested systems 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.