GeForce 3 series
First Direct3D 8.0 GPU with programmable shaders.
The GeForce 3 series, known by the codename NV20, marked Nvidia’s third generation of GeForce graphics processors. Launched in February 2001, it introduced programmable pixel and vertex shaders, multisample anti-aliasing, and more efficient rendering. It was the first graphics card to fully support Microsoft Direct3D 8.0, and Nvidia marketed it under the name nFinite FX Engine.
The series debuted at the 2001 Macworld Conference & Expo in Tokyo, held at Makuhari Messe, where it powered real-time demos of Pixar’s Junior Lamp and id Software’s Doom 3. Apple later secured launch rights for its new computers. The lineup included three consumer models: the GeForce 3, the GeForce 3 Ti200, and the GeForce 3 Ti500. A professional variant, the Quadro DCC, was tailored for computer-aided design. A derivative called the NV2A, used in the Microsoft Xbox, ran at the same clock speed as the original GeForce 3 but added a second vertex shader, giving it performance comparable to the GeForce 4 Ti.
Architecturally, the GeForce 3 arrived three months after Nvidia acquired 3dfx’s assets. Its programmable shaders allowed applications to run custom visual effects using Microsoft Shader Language 1.1. The fixed-function transform and lighting (T&L) hardware from the GeForce 2 was likely retained on the chip for Direct3D 7.0 applications, since the single vertex shader wasn’t fast enough to emulate it. For pixel and texel throughput, the GeForce 3 had four pixel pipelines, each sampling two textures per clock—the same configuration as the GeForce 2, excluding the slower MX line.
The memory subsystem, called Lightspeed Memory Architecture (LMA), reduced overdraw, compressed the z-buffer to conserve bandwidth, and managed DRAM interactions more efficiently. Other changes included support for environment-mapped bump mapping (EMBM), first introduced by Matrox in 1999, and improved anti-aliasing. Earlier GeForce chips only used super-sampled anti-aliasing (SSAA), which rendered a larger internal image and scaled it down. The GeForce 3 added multisample anti-aliasing (MSAA) and Quincunx anti-aliasing, both faster than SSAA but with lower quality.
Quick Facts
- Codename
- NV20
- Created
- February 27, 2001
- Midrange
- Ti 200
- Highend
- GeForce 3 (original), Ti 500
- Openglversion
- OpenGL 1.3
- Predecessor
- GeForce 2 (NV15)
- Successor
- GeForce 4 Ti (NV25)
- Support Status
- Unsupported
- Architecture
- Kelvin
Facts from the source article.
Lore & Background
The GeForce 3 was unveiled during the 2001 Macworld Conference & Expo/Tokyo 2001 in Makuhari Messe and powered realtime demos of Pixar's Junior Lamp and id Software's Doom 3. Apple would later announce launch rights for its new line of computers. The GeForce 3 family comprises three consumer models: the GeForce 3, the GeForce 3 Ti200, and the GeForce 3 Ti500. A separate professional version, with a feature-set tailored for computer aided design, was sold as the Quadro DCC. A derivative of the GeForce 3, known as the NV2A, is used in the Microsoft Xbox game console; it is clocked the same as the original GeForce 3 but features an additional vertex shader, providing performance equivalent to that of the GeForce 4 Ti.
The GeForce 3 was introduced three months after Nvidia acquired the assets of 3dfx. Its programmable shader architecture enabled applications to execute custom visual effects programs in Microsoft Shader language 1.1. It is believed that the fixed-function T&L hardware from GeForce 2 was still included on the chip for use with Direct3D 7.0 applications, as the single vertex shader was not fast enough to emulate it yet. The GeForce 3 has four pixel pipelines which each can sample two textures per clock, the same configuration as GeForce 2 excluding the slower GeForce 2 MX line. The memory subsystem, dubbed Lightspeed Memory Architecture (LMA), reduces overdraw, conserves memory bandwidth by compressing the z-buffer and better manages interaction with the DRAM. Other architectural changes include EMBM support and improvements to anti-aliasing functionality, adding multi-sampling anti-aliasing (MSAA) and Quincunx anti-aliasing methods. The texture sampling units were upgraded to support 8-tap anisotropic filtering, compared to the previous limit of 2-tap with GeForce 2.
Nvidia refreshed the lineup in October 2001 with the release of the GeForce 3 Ti200 and Ti500, coinciding with ATI's releases of the Radeon 7500 and Radeon 8500. The Ti500 has higher core and memory clocks (240 MHz core/250 MHz RAM) than the original GeForce 3 (200 MHz/230 MHz), and generally matches the Radeon 8500 in performance. The Ti200 is clocked lower (175 MHz/200 MHz) making it the lowest-priced GeForce 3 release, but it still surpasses the Radeon 7500 in speed and feature set although lacking dual-monitor implementation. The original GeForce 3 and Ti500 were only released in 64 MiB configurations, while the Ti200 was also released as 128 MiB versions.
Reader's Guide
The GeForce 3 series marked a pivotal shift in GPU design by introducing programmable pixel and vertex shaders, enabling developers to create custom visual effects beyond fixed-function pipelines. This made it the first Direct3D 8.0 compliant card and laid the groundwork for future shader-based graphics. Its Lightspeed Memory Architecture improved memory bandwidth efficiency through z-buffer compression and overdraw reduction, while the addition of MSAA and Quincunx anti-aliasing offered better performance than the super-sampling methods used by previous GeForce chips. However, the GeForce 3's theoretical pixel and texel throughput per clock matched the GeForce 2, and in Direct3D 7 T&L benchmarks the GeForce 2 Ultra could outperform the GeForce 3 and Ti200 due to lower clock speeds on the newer cards. The Ti500 generally matched the Radeon 8500 in performance, while the Ti200 occupied a lower price point. The GeForce 4 Ti, introduced in April 2002, was a revision of the GeForce 3 architecture with higher speeds and improved features, eventually replacing the Ti500. The Ti200 remained in production for a short while, occupying a niche between the GeForce 4 Ti4200 and GeForce 4 MX460, but was discontinued by summer 2002 due to naming confusion with the GeForce 4 MX and Ti lines. Nvidia ceased driver support for the GeForce 3 series; the final Windows 9x/Me driver was 81.98 (December 21, 2005), the final Windows 2000/XP driver was 93.71 (November 2, 2006), and the final Linux 32-bit driver was 96.43.23 (September 14, 2012).
Did You Know?
- The GeForce 3 was the first Microsoft Direct3D 8.0 compliant 3D-card.
- A derivative of the GeForce 3, the NV2A, is used in the Microsoft Xbox game console and features an additional vertex shader.
- The GeForce 3 Ti200 was also released in 128 MiB versions, while the original GeForce 3 and Ti500 were only available in 64 MiB configurations.
- The GeForce 3's texture sampling units support 8-tap anisotropic filtering, up from 2-tap on the GeForce 2.
Frequently Asked Questions
What is the GeForce 3 series?
The GeForce 3 series, developed under Nvidia's internal codename NV20, was the company's third-generation GeForce line of graphics chips, released to the public in February 2001. The consumer lineup comprised the GeForce 3, GeForce 3 Ti200, and GeForce 3 Ti500, while a Quadro DCC variant served professional workstation users.
What made the GeForce 3 series groundbreaking?
It was the first graphics card to deliver full Direct3D 8.0 support with programmable pixel and vertex shaders, a capability Nvidia branded the nFinite FX Engine. The chip also introduced multisample anti-aliasing and a more efficient rendering pipeline to the consumer market.
Where and how was the GeForce 3 series first shown?
Nvidia unveiled the chip at the 2001 Macworld Conference & Expo held at Makuhari Messe in Tokyo, where it powered real-time demos of Pixar's Junior Lamp and id Software's Doom 3. Apple reportedly secured launch rights to pair the card with its upcoming Mac hardware.
What fabrication process and API versions did the GeForce 3 series support?
The NV20 die was manufactured on TSMC's 150-nanometer process. It shipped with Direct3D 8.0 and OpenGL 1.3 support, making it the first GPU to natively execute the new programmable shader model introduced in that Direct3D revision.
Why is the GeForce 3 series considered a turning point in GPU history?
By moving graphics rendering from fixed-function pipelines to fully programmable hardware shaders, it established the architectural paradigm that every subsequent generation from both Nvidia and AMD has expanded upon. In short, it kicked off the modern shader era that still defines how 3D graphics are created today.
More in Nvidia and AMD Graphics Processors 1-24
Spotted an error? Know more?
Reader corrections go straight into our review queue. Suggest an edit · How this site is sourced
