GeForce FX Series - Business

Overview Nvidia s GeForce FX series is the fifth generation in the GeForce line With GeForce 3 Nvidia introduced programmable shader units into their 3D rendering capabilities in line with the release of Microsoft s DirectX 8 0 release and the GeForce 4 Ti was an optimized version of the GeForce 3 With real time 3D graphics technology continually advancing the release of DirectX 9 0 ushered in a further refinement of programmable pipeline technology with the arrival of Shader Model 2 0 The GeForce FX series is Nvidia s first generation Shader Model 2 hardware The Dawn demo was released by Nvidia to showcase pixel and vertex shaders effects of the GeForce FX Series The FX features DDR DDR2 GDDR 2 or GDDR 3 memory a 130 nm fabrication process and Shader Model 2 0 2 0A compliant vertex and pixel shaders The FX series is fully compliant and compatible with DirectX 9 0b The GeForce FX also included an improved VPE Video Processing Engine which was first deployed in the GeForce4 MX Its main upgrade was per pixel video deinterlacing a feature first offered in ATI s Radeon but seeing little use until the maturation of Microsoft s DirectX Video Acceleration and VMR video mixing renderer APIs Among other features was an improved anisotropic filtering algorithm which was not angle dependent unlike its competitor the Radeon 9700 9800 series and offered better quality but affected performance somewhat Though Nvidia reduced the filtering quality in the drivers for a while the company eventually got the quality up again and this feature remains one of the highest points of the GeForce FX family Hardware based on the NV30 project didn t launch until near the end of 2002 several months after ATI had released their competing DirectX 9 architecture The delay was partly caused by Nvidia s transition to a 130 nm manufacturing process which encountered unexpected difficulties Nvidia had ambitiously selected TSMC s then state of the art but unproven Low K dielectri c 130 nm 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 130 nm process node Marketing While it is the fifth major revision in the series of GeForce graphics cards it wasn t marketed as a GeForce 5 The FX effects in the name was decided on to illustrate the power of the latest design s major improvements and new features and to virtually distinguish the FX series as something greater than a revision of earlier designs The FX in the name also was used to market the fact that the GeForce FX was the first GPU to be a combined effort from the previously acquired 3dfx Interactive engineers and Nvidia s own engineers The advertising campaign for the GeForce FX featured the Dawn fairy demo which was the work of several veterans from the computer animation Final Fantasy The Spirits Within Nvidia touted it as The Dawn of Cinematic Computing while critics noted tha t this was the strongest case of using sex appeal in order to sell graphics cards yet The initial version of the GeForce FX the 5800 was one of the first cards to come equipped with a large dual slot cooling solution Called Flow FX the cooler was very large in comparison to ATI s small single slot cooler on the 9700 series Its blower fan was also very loud It was jokingly referred to as the Dustbuster The way it s meant to be played Nvidia debuted a new campaign to motivate developers to optimize their titles for Nvidia hardware at the Game Developers Conference GDC in 2002 In exchange for prominently displaying the Nvidia logo on the outside of the game packaging Nvidia offered free access to a state of the art test lab in Eastern Europe that tested against 500 different PC configurations for compatibility Developers also had extensive access to Nvidia engineers who helped produce code optimized for Nvidia products Overall performance GeForce FX5900 When the FX 5800 finally launched it was discovered after testing and research on the part of hardware analysts that the NV30 was not a match for Radeon 9700 s R300 GPU The most significant performance deficit occurs when the pixel shading hardware is rendering Shader Model 2 effects with FP32 precision Additionally the 5800 had roughly a 30 memory bandwidth deficit compared to Radeon 9700 Pro caused by the use of a comparatively narrow 128 bit memory bus Nvidia originally used GDDR 2 because of its support for much higher clock rates than the original DDR specification Even this memory couldn t clock fast enough to make up for the bandwidth of a 256 bit bus however NV30 s GPU architecture is a 4x2 design capable of rendering 8 Z pixels 8 stencil operations 8 textures and 8 shader operations per clock It is only capable of drawing 4 pixels per clock however which puts its pixel fillrate at half of R300 However in games with heavy use of stencil shadowing NV30 did benefit from its 8 pixels operation s per clock capabilities because the engine does a Z only pass This was not a typical rendering scenario however Pixel shader performance With regard to the Direct3D 9 0 shader model 2 a capabilities of the NV3x series and the related marketing claim of cinematic effects capabilities the actual performance was quite poor A combination of factors combined to hamper how well NV3x could perform these calculations Firstly the chips were designed for use with a mixed precision programming model A 64 bit precision FP16 mode would be used for situations where high precision math was unnecessary to maintain desired image quality In cases where accuracy was more important a 128 bit FP32 mode would be utilized However because ATI s R300 GPU didn t benefit from lower precision FP16 and the R300 performed significantly better on shaders overall and because it took more effort to optimize shader code for the lower precision the NV3x hardware was often unnaturally hampered by computing fu ll precision full time The NV3x chips also used a processor architecture that relied heavily on the effectiveness of the video card driver s shader compiler Proper instruction ordering and instruction composition of shader code could dramatically boost the chip s efficiency Compiler development is a long and difficult task and this was a major challenge that Nvidia tried to overcome during most of NV3x s lifetime Nvidia released several guidelines for creating GeForce FX optimized code and worked with Microsoft to create a special shader model called Shader Model 2 a Nvidia would also somewhat controversially rewrite game shader code and force the game to use their shader code instead of what the developer had written Valve Software s presentation In late 2003 the GeForce FX series became known for poor performance with DirectX 9 shader model 2 vertex pixel shaders because of a very vocal presentation by the popular game developer Valve Software Early indicators of potential ly poor pixel shader performance had come from synthetic benchmarks such as 3DMark 2003 Valve presented detailed performance statistics for their game Half Life 2 running on Nvidia NV30 based hardware Valve revealed a significant performance gap of approximately 80120 between the GeForce FX 5900 Ultra and the ATI Radeon 9800 Pro In shader 2 0 utilizing game levels Nvidia s top of the line FX 5900 Ultra performed about as fast as ATI s mainstream Radeon 9600 Pro which cost approximately one third as much as the Nvidia card Valve had initially planned on supporting partial floating point precision FP16 to optimize for NV3x but they realized that this was too time intensive and thus too costly ATI s cards did not benefit from FP16 mode so all of the work would be entirely for Nvidia s NV3x cards When Half Life 2 was released a year later Valve opted to make all GeForce FX hardware default to using the game s DirectX 8 shader code in order to extract adequate performance from th e Nvidia cards This naturally resulted in a reduction of visual quality Questionable tactics Nvidia historically has been known for their impressive OpenGL driver performance and quality and the FX series maintained this However with regard to image quality in both Direct3D and OpenGL they aggressively began various optimization techniques not seen before They started with filtering optimizations by changing how trilinear filtering operated on game textures reducing its accuracy and thus visual quality Anisotropic filtering also saw dramatic tweaks to limit its use on as many textures as possible to save memory bandwidth and fillrate Tweaks to these types of texture filtering can often be spotted in games from a shimmering phenomenon that occurs with floor textures as the player moves through the environment often signifying poor transitions between mip maps Changing the driver settings to High Quality can alleviate this occurrence at the cost of performance Nvidia also repl aced pixel shader code in software with GeForce FX optimized versions with lower accuracy These tweaks were especially noticed in benchmark software from Futuremark In 3DMark03 it was found that Nvidia had gone to extremes to limit the complexity of the scenes through driver shader changeouts and aggressive hacks that prevented parts of the scene from even rendering at all Side by side analysis of screenshots in games and 3DMark03 showed noticeable differences between what a Radeon 9800 9700 displayed and what the FX series was doing Nvidia also publicly attacked the usefulness of these programs and the techniques used within them in order to undermine their influence upon consumers It should however be noted that ATI also created a software profile for 3DMark03 Application specific optimizations are typical practice to fix bugs and enhance performance but when they affect visual quality significantly to enhance performance they become controversial With regards to 3DMark Fu turemark began updates to their software and screening driver releases for these optimizations Hardware refreshes and diversification See also Comparison of Nvidia graphics processing units GeForceFX 5500 SX Nvidia s only initial release the GeForce FX 5800 was intended as a high end part There were no GeForce FX products for the other segments of the market The GeForce 4 MX continued in its role as the budget video card and the older GeForce 4 Ti cards filled in the mid range In April 2003 Nvidia introduced the mid range GeForce FX 5600 and budget GeForce FX 5200 models to address the other market segments Each had an Ultra variant and a slower cheaper non Ultra variant With conventional single slot cooling and a mid range price tag the 5600 Ultra had respectable performance but failed to measure up to its direct competitor Radeon 9600 Pro The GeForce FX 5600 parts did not even advance performance over the GeForce 4 Ti chips they were designed to replace Likewise the entry level FX 5200 did not perform as well as the DirectX 7 0 generation GeForce 4 MX440 despite the FX 5200 possessing a notably superior feature set FX 5200 was also outperformed by the older Radeon 9000 In May 2003 Nvidia launched a new top end model the GeForce FX 5900 Ultra This chip based on a heavily revised NV35 GPU fixed many of the shortcomings of the 5800 which had been discontinued While the 5800 used fast but hot and expensive GDDR 2 and had a 128 bit memory bus the 5900 moved to slower and cheaper DDR SDRAM with a wider 256 bit memory bus The 5900 Ultra performed somewhat better than the Radeon 9800 Pro in games not heavily using shader model 2 and had a quieter cooling system than the 5800 In October 2003 Nvidia released a more potent mid range card using technology from NV35 the GeForce FX 5700 using a new NV36 core The FX 5700 was ahead of the Radeon 9600 Pro and XT in games with light use of shader model 2 In December 2003 Nvidia launched the 5900XT a graphics c ard intended for the mid range segment It was similar to the 5900 but clocked slower and using slower memory It managed to more soundly defeat Radeon 9600 XT but was still behind in a few shader heavy scenarios The final GeForce FX model released was the 5950 Ultra which was a 5900 Ultra with higher clock speeds The board was fairly competitive with the Radeon 9800XT again as long as pixel shaders were lightly used Windows Vista and GeForce FX PCI cards Windows Vista requires a DirectX 9 compliant 3D accelerator to display the full Windows Aero user interface During pre release testing of Vista and upon launch of the operating system the video card options for owners of computers without AGP or PCIe slots were limited almost exclusively to PCI cards based on the Nvidia NV34 core This included cards such as GeForce FX 5200 and 5500 PCI Since then both ATI and Nvidia have launched a number of DirectX 9 PCI cards utilizing newer architectures Discontinued support Nvidia has cea sed driver support for GeForce FX series Final Drivers Include Windows 9x Windows Me 81 98 released on December 21 2005 Download Product Support List Windows 95 98 Me 81 98 Windows 2000 32 bit Windows XP Media Center Edition 175 19 released on July 9 2008 Download Products supported list also on this page Note that the 175 19 driver is known to break Windows Remote Desktop RDP The last version before the problem is 174 74 It was apparently fixed in 177 83 although this version is not available for the GeForce 5 graphic cards Also worth of note is that 163 75 is the last known good driver that correctly handles the adjustment of the video overlay color properties for the GeForce FX Series Subsequent WHQL drivers do not handle the whole range of possible video overlay adjustments 169 21 or have no effect on those 175 xx See also Comparison of Nvidia graphics processing units GeForce 4 Series GeForce 6 Series References a b c d Wasson Scott April 7 2003 Nvidia s GeForce FX 5800 Ultra GPU Tech Report http techreport com articles x 4966 Retrieved 2008 06 14 http www maximumpc com article features graphics_extravaganza_ultimate_gpu_r