GeForce 256
First GPU with integrated transform and lighting hardware.
The GeForce 256 launched Nvidia’s GeForce line, announced on August 31, 1999, and hitting shelves on October 11, 1999. It built on the RIVA TNT2 by packing more fixed pixel pipelines, shifting geometry calculations from the host CPU to a dedicated hardware transform and lighting (T&L) engine, and adding hardware motion compensation for MPEG-2 video. This card marked a big step forward for 3D PC gaming and was the first accelerator fully compliant with Direct3D 7. Nvidia called it “the world’s first GPU,” defining a Graphics Processing Unit as a single-chip processor combining transform, lighting, triangle setup/clipping, and rendering engines, capable of handling at least 10 million polygons per second.
The “256” in its name came from the “256-bit QuadPipe Rendering Engine,” referring to the NV10 chip’s four 64-bit pixel pipelines. In single-textured games, it could output four pixels per cycle; with two textures, that dropped to two multitextured pixels per cycle, since each pipeline still had only one texture mapping unit, like the TNT2. The GeForce 256 also added support for cube environment mapping and dot-product (Dot3) bump mapping. Its built-in T&L hardware set it apart from older 3D accelerators that relied on the CPU for these tasks, cutting the complexity and cost of 3D graphics solutions. This made such hardware affordable for consumer graphics cards, rather than limiting it to expensive professional CAD systems. The NV10’s T&L engine also let Nvidia enter the CAD market for the first time with the Quadro line, which used the same silicon but had different drivers and certifications for CAD needs. TSMC manufactured the chip on its 220 nm CMOS process.
Only one GeForce 256 model was released, though it came in two memory configurations. The SDR version, using Samsung SDR SDRAM, came out in October 1999, followed by a DDR version with Hyundai (now SK Hynix) DDR SDRAM in mid-December 1999. Compared to earlier high-end cards like the 3dfx Voodoo3 3500 and Nvidia’s own RIVA TNT2 Ultra, the GeForce 256 could boost frame rates by 50% or more in games that used hardware T&L, especially with a low-budget CPU.
Quick Facts
- Codename
- NV10
- Date
- October 11, 1999 (SDR) / December 13, 1999 (DDR)
- Fab
- TSMC
- Process
- 220 nm (CMOS)
- Midrange
- GeForce 256 SDR
- Highend
- GeForce 256 DDR
- Openglversion
- OpenGL 1.2.1 (T&L)
- Predecessor
- RIVA TNT2
- Successor
- GeForce 2 series
- Support Status
- Unsupported
- Architecture
- Celsius
Facts from the source article.
Lore & Background
The '256' in its name stems from the '256-bit QuadPipe Rendering Engine,' describing the four 64-bit pixel pipelines of the NV10 chip. In single-textured games NV10 could output 4 pixels per cycle, while a two-textured scenario limited this to 2 multitextured pixels per cycle, as the chip still had only one TMU per pipeline. The GeForce 256 also added support for cube environment mapping and dot-product (Dot3) bump mapping. The integration of transform and lighting hardware into the GPU itself set it apart from older 3D accelerators that relied on the CPU for these calculations. This reduction of 3D graphics solution complexity brought the cost of such hardware to a new low and made it accessible to cheap consumer graphics cards instead of being limited to the previous expensive professionally oriented niche designed for computer-aided design (CAD). NV10's T&L engine also allowed Nvidia to enter the CAD market with dedicated cards for the first time, with a product called Quadro, which uses the same silicon chips but with different driver support and certifications.
Reader's Guide
The GeForce 256 was marketed as the first GPU, but its hardware T&L had little real-world value at launch due to lack of broad application support. Initially, it was only somewhat beneficial in certain situations in a few OpenGL-based 3D first-person shooters, most notably Quake III Arena. Benchmarks using low-budget CPUs like the Celeron 300A gave favorable results for the GeForce 256, but benchmarks with fast CPUs such as the Pentium II 300 gave better results with some older graphics cards like the 3dfx Voodoo 2. Competitors pointed out that a fast CPU could more than make up for the lack of a T&L unit. Software support for hardware T&L was not commonplace until several years after the GeForce 256's release. Early drivers were buggy and slow, while 3dfx cards enjoyed efficient, high-speed, mature Glide API and/or MiniGL support for the majority of games. Only after the GeForce 256 was replaced by the GeForce 2, and ATI's T&L-equipped Radeon was released, did hardware T&L become widely utilized in games. The GeForce 256 was also quite expensive for the time and didn't offer tangible advantages over competitors' products outside of 3D acceleration; its GUI and video playback acceleration were not significantly better than that offered by competition or even older Nvidia products. The later release and widespread adoption of GeForce 2 MX/4 MX cards with the same feature set meant unusually long support for the GeForce 256, until approximately 2006, in games such as Star Wars: Empire at War or Half-Life 2, the latter of which featured a Direct3D 7-compatible path.
Did You Know?
- The GeForce 256 was the first fully Direct3D 7-compliant 3D accelerator.
- The SDR version used SDR SDRAM from Samsung Electronics; the DDR version used DDR SDRAM from Hyundai Electronics (now SK Hynix).
- The Quadro line uses the same silicon chips as GeForce cards but with different driver support and certifications for CAD applications.
Frequently Asked Questions
What is the GeForce 256?
It is the graphics card that launched Nvidia's GeForce product line, fabricated by TSMC on a 220-nanometer CMOS process. It shipped in two memory flavors: SDR SDRAM in October 1999 and DDR SDRAM by mid-December 1999.
Why does Nvidia call the GeForce 256 the 'first GPU'?
Nvidia coined the term 'Graphics Processing Unit' for this card because it was the first chip to integrate transform, lighting, and pixel rendering into a single silicon package. That dedicated hardware T&L engine meant the host CPU no longer had to handle vertex math, a shift that defined the GPU concept going forward.
How did the GeForce 256 improve on the RIVA TNT2?
The 256 packed in additional fixed-function pixel pipelines and, most importantly, a dedicated hardware transform-and-lighting block that offloaded geometry work from the CPU. It also added hardware motion compensation for MPEG-2 video, something the TNT2 lacked.
When exactly was the GeForce 256 announced and released?
Nvidia unveiled the card on August 31, 1999, and it reached retail shelves on October 11 of that year. The DDR SDRAM revision followed roughly two months later in mid-December 1999.
Why is the GeForce 256 considered a turning point in PC gaming?
It was the first accelerator to be fully compliant with Direct3D 7, which unlocked a new wave of 3D titles that relied on hardware-assisted geometry. By establishing the single-chip GPU architecture, it set the design template that every subsequent graphics processor has followed.
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