GeForce FX

Categories: Wikipedia articles needing copy edit | Graphics cards | NVIDIA

The GeForce FX (codenamed NV30) is a graphics card in the GeForce line, from the manufacturer NVIDIA. The fastest model as of late 2005 (GeForce FX 5950 Ultra) appears comparable to competitor ATI Technologies's Radeon 9800 XT. It features DDR, DDR-II or GDDR-3 memory, a 130 nanometer fabrication process, and a wide swath of additional features, including the most robust vertex shader and pixel shader engines available. It is fully DirectX 9 compliant. Limited samples of the GeForce FX were sent to the press on November 18, 2002, and mass production was expected to begin in December 2002, with cards finally reaching the market by February, 2003.

The GeForce FX also included an improved VPE (Video Processing Engine), which was first deployed in the GeForce4 MX. The main upgrade was per-pixel video-deinterlacing. This was a feature first offered in ATI's Radeon, but it saw little use until the maturation of Microsoft's DirectX-VA and VMR APIs.

The GeForce FX series was as successful as its predecessor, the GeForce 4, though not as successful as the GeForce 2. However, hardware enthusiasts saw the FX series as a great disappointment. Due to market demand and the FX's deficiency as a worthy successor, NVIDIA extended the production life of the aging GeForce 4, keeping both the FX and 4 series in production for some time, at great expense.

To industry analysts, the GeForce FX's poor Shader 2.0 performance was evidence of poor underlying architectural decisions. A contract dispute over the pricing of the Xbox's NV2A led to Microsoft withholding the specifications for Shader Model 2.0 (in DirectX 9.0.) The FX's disorientation feature-set and pipeline architecture are directly attributed to NVidia's designers mis-guessing the direction of the Direct3D API.

History

The NV30 project had been delayed for three key reasons. One was because Nvidia decided to produce an optimized version of the GeForce 3 (NV 20) which resulted in the GeForce 4 Ti (NV 25), while ATI cancelled its competing optimized chip (R250) and opted instead to focus on the R300 (Radeon 9700). The other reason was Nvidia's commitment with Microsoft, to deliver the Xbox console's graphics processor (NV2A.) The Xbox venture diverted most of Nvidia's engineers over not only the NV2A's initial design-cycle but also during mid-life product revisions (needed to discourage hackers.) Finally, NVidia's transition to a 130 nm manufacturing process encountered unexpected difficulties. NVIDIA had ambitiously selected TSMC's then state-of-the-art (but unproven) low-K 0.13u process node. After sample silicon-wafers exhibited abnormally high defect-rates and poor circuit performance, NVIDIA was forced to re-tool the NV30 for a conventional (FSG) 0.13u process node. (NVidia's manufacturing difficulties with TSMC spurred the company to search for a second foundry. NVIDIA selected IBM to fabricate several future Geforce chips, citing IBM's process technology leadership. Yet curiously, NVIDIA avoided IBM's low-K process.)

Beaten to market by ATI's Radeon 9700, NVIDIA planned for the GeForce FX 5800 Ultra to regain the high-end 3D-performance crown. These plans, however, did not come to fruition. The initial version of the GeForce FX (the 5800) was so large that it required two slots to accommodate it, required a massive heat sink and cooling fan arrangement, produced a great deal of noise from its fan. Although it rated respectable in competitive performance testing during its debut, the FX 5800's results were a disappointment because many expected Nvidia to have the advantage of (the supposedly faster) 130 nm manufacturing process and a 6 month development lead over the Radeon 9700. The 5800 was plagued by shortages of expensive DDR-II memory which also failed to overcome its limited 128-bit memory bus (the Radeon 9700/9800 had a 256-bit memory bus) and the Radeon 9800 revision arrived timely to secure the performance lead. After a late and high-key introduction, NVIDIA quietly withdrew the 5800 from the market pending design revisions.

By early 2003, ATI had taken a considerable chunk of the high-end graphics market. In the meantime, NVIDIA introduced the mid-range 5600 and low-end 5200 models to address the mainstream market. With conventional single-slot cooling and a more affordable price-tag, the 5600 had respectable performance but failed to measure up to its direct competitor, Radeon 9600. As a matter of fact, the mid-range GeForce FX did not even advance performance over the chips they were designed to replace, the GeForce 4 Ti. In DirectX 8 applications, the 5600 lost by a considerable margin to the Ti 4200. Likewise, the entry-level FX 5200 performed worse than the GeForce 4 MX 440, despite the FX 5200 possessing a better 'checkbox' feature-set. Value-oriented gamers shunned the MX 440 and 5200 and opted for the Radeon 9000/9200 or paid more for the proven and very capable Ti 4200 which because of its age was now priced below the Radeon 9600/GeForce 5600.

With the launch of the GeForce FX 5900, NVIDIA fixed many of the problems of the 5800. While the 5800 used DDR-II and had a 128-bit memory bus, the 5900 reverted to the slower DDR but it more than made up for it with a 256-bit memory bus. The 5900 had a quieter cooling system than the 5800, but it still occupied two slots (the Radeon 9700 and 9800 were both single-slot cards.) By mid-2003, ATI's top product (Radeon 9800) was outselling NVidia's top product (FX 5900), perhaps the first time that ATI had been able to displace NVidia's position as performance king.

NVIDIA later attacked ATI's mid-range card, the Radeon 9600, with the GeForce FX 5700 and 5900XT. The 5700 was a new chip sharing the architectural improvements found in the NV35. The FX 5700's use of DDR II memory kept product prices expensive, leading NVIDIA to introduce the FX 5900XT. The 5900XT is identical to the 5900 but is clocked slower, and uses slower memory.

In late 2003, the GeForce FX series became known notorious for poor performance with DirectX 9 Vertex & Pixel shaders. Early indicators of potentially poor PS2.0 performance came from synthetic benchmarks (such as 3DMark 2003.) But outside of the developer community and tech-savvy computer gamers, few mainstream users were aware of such issues. Then, Valve Software dropped a bombshell on the gaming public. Using a pre-release build of the Half-Life 2 game engine, Valve published benchmarks revealing a complete generational gap (80-120% or more) between the GeForce FX 5900 Ultra and the ATI Radeon 9800. In Shader 2.0 enabled game-levels, NVIDIA's top-of-the-line FX 5900 Ultra performed about as fast as ATI's mainstream Radeon 9600, which cost a third as much as the NVIDIA card. (When Half-Life 2 was released a year later, Valve forced all Geforce FX hardware to use the game's DirectX 8 shader profile, in order to avoid the FX-series's poor Shader 2.0 performance.)

GeForce FX Models

There are also "GeForce PCX" versions of the 5200, 5700 and 5950. These are much the same as the "normal" versions, but they have a bridge linking their native AGP bus to a PCI Express x16 link. They also do not require external power supplies, as the PCI Express bus supplies the required power.

External links

• NVIDIA: Cinematic Computing for Every User
• Museum of Interesting Tech article Picture and specifications for the FX5800