GeForce 2 series

Lore & Background

The GeForce 2 architecture (NV15) is similar to the previous GeForce 256 line but with various improvements. Built on a 180 nm manufacturing process (compared to 220 nm for the GeForce 256), the silicon became more dense, allowing for more transistors and higher clock speeds. The most significant change for 3D acceleration was the addition of a second texture mapping unit to each of the four pixel pipelines, doubling the texture fillrate per clock compared to the previous generation—the reasoning behind the GeForce 2 GTS's naming suffix: GigaTexel Shader (GTS). The GeForce 2 also formally introduced the NSR (Nvidia Shading Rasterizer), a primitive type of programmable pixel pipeline somewhat similar to later pixel shaders; this functionality was also present in the GeForce 256 but was unpublicized. Another hardware enhancement was an upgraded video processing pipeline called HDVP (high definition video processor), which supported motion video playback at HDTV-resolutions (MP@HL).

In 3D benchmarks and gaming applications, the GeForce 2 GTS outperformed its predecessor by up to 40%. In OpenGL games (such as Quake III), the card outperformed the ATI Radeon DDR and 3dfx Voodoo 5 5500 cards in both 16 bpp and 32 bpp display modes. However, in Direct3D games running 32 bpp, the Radeon DDR was sometimes able to take the lead. The GeForce 2 (NV15) architecture was quite memory bandwidth constrained; the GPU wasted memory bandwidth and pixel fillrate due to unoptimized z-buffer usage, drawing of hidden surfaces, and a relatively inefficient RAM controller. The main competition for the GeForce 2 GTS, the Radeon DDR (R100), had hardware functions (called HyperZ) that addressed these issues. Because of the inefficient nature of the GeForce 2 GPUs, they could not approach their theoretical performance potential, and the Radeon, even with its significantly less powerful 3D architecture, offered strong competition. The later NV17 revision of the NV11 design used in the GeForce4 MX was more efficient.

The first models to arrive after the original GeForce 2 GTS were the GeForce 2 Ultra and GeForce 2 MX, launched on September 7, 2000. On September 29, 2000, Nvidia started shipping graphics cards which had 16 and 32 MB of video memory size. Architecturally identical to the GTS, the Ultra simply had higher core and memory clock rates. Meant to be a niche product, it was rumored that the GeForce 2 Ultra was intended to prevent 3dfx taking the lead with their Voodoo 5 6000, which ended up never released as 3dfx went bankrupt. The Ultra model actually outperformed the first GeForce 3 products in some cases, due to initial GeForce 3 cards having significantly lower fillrate. However, the Ultra lost its lead when anti-aliasing was enabled, because of the GeForce 3's new memory bandwidth/fillrate efficiency mechanisms; plus the GeForce 3 had a superior next-generation feature set with programmable vertex and pixel shaders for DirectX 8.0 games. The GeForce 2 Pro, introduced shortly after the Ultra, was an alternative to the expensive top-line Ultra and was faster than the GTS. In October 2001, the GeForce 2 Ti was positioned as a cheaper and less advanced alternative to the GeForce 3. Faster than the GTS and Pro but slower than the Ultra, the GeForce 2 Ti performed competitively against the Radeon 7500 (RV200), although the 7500 had the advantage of dual-display support. This mid-range GeForce 2 release was replaced by the GeForce4 MX series as the budget/performance choice in January 2002.

Reader's Guide

The GeForce 2 series marked a significant step in GPU evolution, doubling texture fillrate per clock and introducing the NSR programmable pixel pipeline, which foreshadowed later pixel shaders. Its architecture, however, was memory bandwidth constrained, limiting its real-world performance relative to theoretical potential. The GeForce 2 GTS outperformed its predecessor by up to 40% and competed strongly against the ATI Radeon DDR and 3dfx Voodoo 5 5500 in OpenGL titles, though the Radeon DDR could take the lead in Direct3D 32-bit color. The GeForce 2 Ultra, a niche high-clock variant, outperformed early GeForce 3 cards in fillrate but lost ground when anti-aliasing was enabled due to the GeForce 3's efficiency improvements. The GeForce 2 MX series (NV11) successfully addressed the low-end market, offering dual-display support and performance approaching the GeForce 256 at lower cost, competing against ATI's Radeon SDR, Radeon VE, and 3dfx's Voodoo4 4500. The GeForce 2 Ti served as a mid-range alternative to the GeForce 3. Nvidia ceased driver support for the GeForce 2 GTS, Pro, Ti, and Ultra models in 2005, and for MX models in 2007. The series was succeeded by the GeForce 3 for the high end and later by the GeForce4 MX for both the non-MX and MX lines.

Did You Know?

• The GeForce 2 GTS's suffix stands for GigaTexel Shader, referencing its doubled texture fillrate per clock.
• The GeForce 2 Ultra was rumored to have been intended to prevent 3dfx taking the lead with the Voodoo 5 6000, which was never released.
• The GeForce 2 MX series (NV11) offered dual-display support, a feature absent from the GeForce 256 and GeForce 2 non-MX models.
• The GeForce 2 architecture's NSR (Nvidia Shading Rasterizer) was a primitive programmable pixel pipeline, also present in the GeForce 256 but unpublicized.