GeForce 2 Series
From Wikipedia, the free encyclopedia
| Nvidia GeForce 2 | |
|---|---|
 |
|
| Codename(s) | NV11, NV15, NV16 |
| Created | 2000 |
| Entry-level GPU | MX |
| Mid-Range GPU | GTS, Pro, Ti |
| High-end GPU | Ultra |
| Direct3D and Shader version | Direct3D 7.0 |
The GeForce2 (codenamed NV15) was the second generation of GeForce graphics cards by Nvidia Corporation. It was the successor to the GeForce 256.
Contents |
[edit] GeForce2 architecture
The GeForce2 architecture is largely similar to the previous GeForce 256 line, with a few notable improvements. Most significant is the addition of a second TMU (texture map unit) to each of the 4 pixel pipelines. This, coupled with a 67% increase in GPU clock rate (200 MHz vs 120 MHz), pushed the GTS's texel fillrate to a previously unheard of 1.6 billion texels per second, 3.3 times higher than that of its predecessor. This performance level became a naming suffix for the first card release, the GeForce2 GTS (giga-texel shader). Other hardware enhancements included an upgraded video processing pipeline, called HDVP (high definition video processor). HDVP supported motion video playback at HDTV-resolutions (MP@HL), although playback of high-resolution video still required much effort from the system CPU. The GeForce2 also introduced the Nvidia Shading Rasterizer (NSR), which was actually a primitive form of what is known as pixel shaders today, though they were not programmable and only found use in tech demos.
In 3D benchmarks and gaming applications the GTS outperformed its predecessor (GeForce 256) by up to 40%.[1] In OpenGL games (such as Quake III), the GTS outperformed the ATI Radeon and 3DFX Voodoo 5 cards in both 16bpp and 32bpp (true-color) display modes. But in Direct3D games, the Radeon was sometimes able to take the lead in 32-bit color modes.[2]
As studies of the architecture used for GeForce 256 and GeForce2 progressed, it was determined that the architecture was quite memory bandwidth constrained.[3] The chips wasted memory bandwidth and pixel fillrate on unoptimized z-buffer usage, drawing of hidden surfaces, and relatively inefficient RAM controllers. The main competition for these two chips, the ATI Radeon DDR, had effective optimizations (HyperZ) that combated these issues.[4] Because of memory bandwidth constraints on the GeForce chips, they could not approach their theoretical performance potential, and the Radeon, with its significantly less-endowed pipeline count, offered strong competition simply due to greater efficiency. The later NV17 revision of the NV10 design, used for the GeForce4 MX, was far more efficient in memory management; although the GeForce4 MX 460 was a 2x2 pipeline design, it could outperform the GeForce2 Ultra.
[edit] GeForce2 MX
The most successful GeForce2 part was the budget-model GeForce2 MX. This was due to its popularity with OEM system builders, like its predecessor the RIVA TNT2 M64. The combination of low cost and a complete 3D feature-set made it possible to equip a PC with complete 3D acceleration at a much lower price point than if a GeForce2 GTS was used. To reduce the costs involved with the architecture, Nvidia removed two 3D pixel pipelines and half of the GTS card's memory bandwidth by using cheaper SDR SDRAM instead of DDR SDRAM. Nvidia did however add true dual-display support to the MX. In comparison, the GTS and subsequent non-MX models could drive a separate TV-encoder, but this second-display was tied to the primary desktop.
The prime competitors to GeForce2 MX were ATI's Radeon VE (later Radeon 7000) and Radeon SDR. Radeon VE had the advantage of somewhat better dual-monitor display software, but it did not offer hardware T&L, an emerging 3D rendering feature of the day that was the major attraction of Direct3D 7. Radeon VE also had only a single rendering pipeline, meaning it had substantially less pixel fill rate than GeForce2 MX. The Radeon SDR, however, was the full original Radeon simply equipped with SDR SDRAM instead of DDR SDRAM. This card was released some time after GeForce2 MX, but was faster at 32-bit "truecolor" 3D rendering. Radeon SDR had slightly more powerful pixel pipelines (3 TMUs each) and more efficient overall operation due to HyperZ.[5] Radeon SDR lacked multi-monitor support, however.
Nvidia eventually created a wider range of GeForce2 MX pricing options with 3 additional configurations; the MX400, MX200, and MX100. The MX400, like the original MX, had a 128-bit SDR memory bus which could also be configured as 64-bit DDR. The MX400 outperformed the original MX because of an increased core clock rate. The MX200 was equipped with a cheaper 64-bit SDR memory bus, resulting in significantly less memory bandwidth than the original MX, a critical requirement for 3D rendering performance. The cheapest model, the MX100, was equipped with a narrow 32-bit SDR memory bus.[6]
The GeForce2 MX was later used by Nvidia as an integrated graphics processor within the nForce line of motherboard chipsets. It also saw an implementation as a mobile graphics chip for use in notebooks, called GeForce2 Go. This chip reduced peak power usage to 2.6 W.[7]
[edit] Later GeForce2 releases
Three additional cards based upon the GeForce2 GTS were later released - the first was the GeForce2 Ultra, launched in late 2000. Architecturally identical to the GTS, the Ultra was specified to have higher core and memory clocks. Nonetheless, the Ultra's production costs made them expensive and rare, even before the next generation GeForce 3 cards were released. The Ultra model actually outperformed the first GeForce 3 products in some cases, due to initial GeForce 3 cards having lower fill rate. However, the Ultra lost the lead when anti-aliasing was enabled, because of the GeForce 3's new memory bandwidth / fillrate efficiency mechanisms, plus the GeForce 3 had programmable vertex and pixel shaders for future games. Consequently, the Ultra had a short lifespan.
The GeForce2 Pro and the GeForce2 Ti (for "titanium") were created later to fill in additional pricing segments. Both parts fell between the GTS and Ultra with regards to performance. The GeForce2 Pro, introduced in 2000, was an alternative to the then top-line Ultra and was slightly faster than the GTS. In October 2001, the first time Nvidia used the "Titanium" badging, the GeForce2 Ti was positioned as cheaper and less advanced alternative to the high-end GeForce 3, as though the GeForce 3 was split into the Ti 500 and Ti 200 it still lacked a mass-market version such as the earlier GeForce 2 MX. The GeForce2 Ti performed competitively with the Radeon 7500 (however the 7500 had the advantage of dual-display support). These mid-range and near-budget GeForce 2 releases were replaced by the GeForce 4 MX series as the budget/performance choice in January 2002.
On Nvidia's website, the Ultra initially had its own separate page to set it apart from the GTS/Pro/Ti. After 2002, with the GeForce 2 considered a discontinued (legacy) product, all of the NV15 cores were grouped together as GTS/Pro/Ti/Ultra.
[edit] Successor
The successor to the GeForce2 (non-MX) line was the GeForce3. The non-MX GeForce2 line was reduced in price and saw several additions, in order to offer a mid-range alternative to the high-end-only initial GeForce3 product. Later, the entire GeForce2 line was replaced in its market position with the GeForce4 MX.
The GeForce4 MX was codenamed "NV17", meaning its technology was very similar to that of the GeForce2. However, GeForce4 MX gained a number of improvements from the GeForce4 Ti, such as a more efficient memory controller, bandwidth and fill rate-saving techniques, dual-monitor support, and a multi-sampling anti-aliasing unit.[8] These new additions allowed the GeForce 4 MX 440 and 460 to perform better and offer improved image quality over the entire GeForce2 line.
[edit] Models
[edit] Discontinued support
Nvidia has ceased driver support for GeForce2 GTS, GeForce2 Pro, GeForce2 Ti and GeForce2 Ultra.
Final drivers include:
- Windows 9x & Windows Me: 81.98 released on December 21, 2005
- Windows 2000 & 32-bit Windows XP: 93.71 released on November 2, 2006 [Download]
[edit] Competing chipsets
- 3dfx Voodoo 5
- ATI Radeon
- PowerVR Series 3 (Kyro)
[edit] References
- ^ Lal Shimpi, Anand. Nvidia GeForce 2 GTS, Anandtech, April 26, 2000.
- ^ Witheiler, Matthew. ATI Radeon 64MB DDR, Anandtech, July 17, 2000.
- ^ Lal Shimpi, Anand. Nvidia GeForce2 Ultra, Anandtech, August 14, 2000.
- ^ Lal Shimpi, Anand. ATI Radeon 256 Preview (HyperZ), Anandtech, April 25, 2000: p.5.
- ^ FastSite. , ATI RADEON 32MB SDR Review, X-bit Labs, December 27, 2000.
- ^ Worobyev, Andrey. Leadtek WinFast GeForce2 MX 64 MBytes, Leadtek WinFast GeForce2 MX64 and Leadtek WinFast GeForce2 MX MAX on Nvidia GeForce2 MX, MX200 and MX400, Digit-Life, accessed September 6, 2006.
- ^ Smith, Rick. Nvidia GeForce2 Go: High performance graphics to go, Reviews OnLine, December 13, 2000.
- ^ Freeman, Vince. VisionTek Xtasy GeForce4 MX 440 Review, Sharky Extreme, April 19, 2002: p.3.
[edit] See also
[edit] External links
|
|||||||||||||||||||||||||||||||
