Introduction
We could again see it at CeBIT as well as WinHec, there’s a massive amount of commotion going on about upcoming 3D chips and cards. Lots of different chips and boards were shown or at least announced, of course months before the actual shipping date. The times in the 3D-chip arena are getting tougher, 1998 was far from enjoyable for most of the 3D-chip makers and many card makers got even into real trouble. Canopus and Miro left the 3D-card scene completely, 3Dfx swallowed STB and Diamond produced heavy losses, barely covered by the success of RIO. If you compare the 3D-chip with the CPU market, you can see that the competition as well as the ability to make money is a whole lot harder in the 3D arena than in the CPU section. Intel is still taking huge amounts of money for the majority of its CPUs, whilst even the suppliers of the fastest 3D chips are selling their 3D accelerators at less than a tenth of the price of a microprocessor with comparable complexity and die-size. This is indeed surprising if we consider that the mainstream 3D-card market is only a mere 3 years old.
A Short Look Back
The introduction of real 3D-accelerators started with the 3Dfx Voodoo chip, and that was the time when the first hard core 3D gamers started to evolve, producing high expectations as well as crazy hypes and some pathological fanaticism too. Voodoo (1) and 3Dfx remained at the top of the 3D graphics scene for more than a year, completely underestimated by the big players in the graphics scene at this time, S3 and Matrox. 3Dfx won the second round also, the Voodoo2 was a worthy successor of Voodoo (1). The idea of Voodoo2 was the same as for Voodoo (1), offer an add-on 3D-card to the normal 2D card, use a pass-through cable and offer a lot more power than Voodoo1. Voodoo2 was using two parallel texture units, a lot more graphics memory and the user had the chance to run two of those cards in parallel, called ‘SLI’-mode, offering at that time mind blowing 3D performance. This was certainly no cheap solution, but the hard core gamers jumped on this bandwagon right away, making Voodoo2 another huge success. It took six more months until the first decent 2D/3D-cards became available, NVIDIA shipped RIVA TNT and 3Dfx tried their slightly castrated version called ‘Voodoo Banshee’. People who believed in the marketing hype, saying that those two chips were a really new generation of 3D chips, were disappointed, since Voodoo2 SLI was still offering the best performance, Banshee and TNT had only the chance to come close in some areas.
Voodoo3, TNT2, Permedia3 and what not are the first 3D-chips that show a real further development of the technologies implemented into Voodoo2. What took no less than six chips in the days of Voodoo2 SLI is now condensed into a TNT2-chip, beefed up with a faster RAMDAC, good AGP-support, support of larger texture-sizes and several other goodies, running at a much higher clock speed than Voodoo2 as well. Really new concepts are still not to be found though and can also not be expected before the second half of 1999. We are still working with the second generation of 3D-chips, but even this generation has still got a lot to offer and you can be sure that it will be a hot summer in the 3D-arena this year.
We can expect the first announcements of third-generation 3D-chips within the next couple of months and there’s supposed to be a new quantum leap in 3D-performance and quality. Fill rates of 500-600 Mpixel/s, triangle rates of 20 million/s and more as well as the support of new quality enhancements will ask a lot more from game developers, CPU, memory, RAMDAC and even display technologies than we can imagine right now.
The Second Generation of 3D Chips
Let’s focus on those chips, that provide today’s top performance, TNT2, Voodoo3, Rage128, G400, PowerVR SG, Permedia3, etc. Voodoo3 was the first of those chips and the expectations were high when Voodoo3 was announced for the first time, since 3Dfx had the history of supplying two top performers in the past, the Voodoo in 1997 and the Voodoo2 in 1998. At Comdex 1998 the journalist and card-makers weren’t too impressed with the Voodoo3-features though. Even the following marketing campaign wasn’t able to convince more than a few fanatic 3Dfx followers, when 3Dfx threw in all of their arrogance and ignorance towards the criticism of 3D analysts and journalists about missing features of Voodoo3. What is sold as ‘Voodoo3’ today should rather carry the name ‘Banshee2’, since it’s a straightforward development of Banshee with performance measures that are close to Voodoo2. We certainly don’t want to forget improvements as digital flat panel support, higher resolutions and better RAMDAC and the price/performance ratio of Voodoo3 is also way better than Voodoo2 SLI. However, the absolute performance as well as the long list of missing features has disappointed a lot of hard core gamers.
3D Card Requirements for Power Gamers
We are trying to answer the question of what we should expect of an up-to-date 3D card today. Tom’s Hardware Guide expects no less than what is currently doable and thus we got to the following criteria:
OpenGl (ICD) and DirectX (6.x) Support
The support of those two is of the highest importance for optimal 3D-game support. The majority of 1st person 3D-action shooters is based on OpenGL, Quake2, Quake Arena, Unreal, Unreal Tournament, Halflife and many more are the typical examples. The majority of all other games is covered by DirectX, particularly flight simulators and racing games are mainly based on this 3D-interface from Microsoft. A 3D-card that doesn’t support those two 3D-platforms is pretty much out of the question for any gamer.
Fill Rates in excess of 300 Mpixel/s or Mtexel/s
The fill rates quoted by the chip vendors should be taken with a decent grain of salt. Firstly those data are ‘synthetic’, comparable to MIPS or MFLOPS of CPUs. The fill rate can be calculated from the 3D-chip clock, the number of independent pipelines of the chip, the graphics memory bandwidth and of course the hardwired features of the chip. The color depth, Z-buffer and particularly rendering quality varies significantly in between the vendors. A good example for this is TNT2, which has a lower theoretical fill rate than Voodoo3, but it scores higher frame rates in complex 3D scenes. Still the fill rate can give you some kind of idea of what kind of 3D-performance you can expect from a 3D-chip.
Up to 32 MB of Onboard Memory at Clock Speeds of Way over 100 MHz
The onboard memory of each 3D-card has a very high impact on the overall 3D-performance. 16 MB is enough to run 3D applications at up to 1024×768 in 32 bit color depth (this is not valid for PVRSG, which needs less memory for that). Realistic 3D scenes at 1280x1024x32 bit color require 32 MB and that’s what is state-of-the-art today. The memory clock still varies a lot between the different chips and so does the width of the memory interface, where currently 128 bit is state-of-the-art, moving towards ‘dual-256 bit’ = 2 interfaces with 128 bit or real 256 bit soon. The graphics memory bandwidth is an important limiting factor of the 3D-performance and you can say that a vendor who can safely handle highest memory clocks is well prepared for future developments.
32-Bit Rendering
More and more games are offering a true-color mode due to quality reasons, meaning that the displayed frames are using a 24 bit deep color depth (RGB, 16.7 million colors). This means that a huge amount of data needs to be computed for each frame, but the performance of the latest 3D-chips is starting to be capable of supplying this kind of computing power. A 3D-architecture that is limited to only 16 bit, as in case of the Voodoo3 requires a reduction of color information and is thus decreasing the quality and reality level. 32-bit color rendering with 32-bit Z-buffering will stay the optimal implementation for quite some time to come.
Fast RAMDACs with at least 250 MHz or Digital Flat Panel Support
The RAMDAC is the link between the digital display information stored in the frame buffer and the analog CRT. The higher the bandwidth of the RAMDAC, the higher is the number of pixels that can be displayed on the CRT each second. This means that a faster RAMDAC is crucial for decent refresh rates, its quality is crucial for the quality of the displayed picture on the screen and only fast RAMDACs can supply really high resolutions of more than 2000×1500, which is most important for 2D applications. If the user prefers a flat panel screen, he should make sure that there is no digital-analog-converter (DAC) and then a analog-digital-converter (ADC) between the graphics memory (or frame buffer) and the flat panel, because it is not only a waste of silicon, but it also decreases the display quality by a serious amount. A flat panel requires digital data and should thus be supplied with nothing else than that. That requires a digital output of the graphics card, where DFP is one of the standards. For optimal 2D-quality you should therefore either look for a fast RAMDAC for a CRT or a digital output for a flat screen.
State-Of-The-Art AGP-Support
AGP vs. PCI is a question that doesn’t need to be asked anymore today. AGP has succeeded in the upper performance area quite a while ago already. When AGP 4x will be released later on this year, we may finally see the visible advantage that many of us are still missing. A today’s 3D-card should support AGP 2x to be at least able to handle the data bandwidth that’s required for ‘several million polygons/s’. Games with large textures are coming up, FlightSim 99 is only one example, so that the 3D-chip should also be able to do AGP-texturing, which is one of the things that Voodoo3 is not able to do.
Multi-Texturing or Multi-Pixel-Rendering
The equipment of 3D-chips with two parallel rendering pipelines has latest by now become a standard in the 3D-performance arena. Last year this was implemented into the Voodoo2 chip set for the first time. In the past a pixel had to be rendered in two or more passes to reach higher realism, as e.g. for the lighting effects in Quake, Quake2, Unreal, Halflife or Shogo. The rendering of the texture and the lighting map can be done in parallel and thus at double the speed if the 3D-chip has got two parallel rendering pipelines. If a game is less complex and requires only one rendering pass, each of those pipelines can render a different pixel, thus doubling the fill rate (this is something that Voodoo2 could not do). All new or upcoming 3D-chips have at least two rendering pipelines. The future 3D-chips will soon come with four or more pipelines whilst at the same time 3D-games will require more than only two rendering passes for each pixel.
Support of Different Size Textures up to 2048×2048 or more
We are moving quickly towards a more and more realistic 3D-gaming experience, so that the textures need to be a lot more detailed than they used to. The Voodoo3 only supports textures up to 256×256, whilst the rest of the new 3D-chips can handle 2048×2048. This offers a higher level of detail in 3D-scenes. Other chips have problems with non-square textures, which also reduces realism. Today you should expect the support of 2048×2048 textures, it will be more pretty soon.
Hardware Bump Mapping
Bump mapping is one of those ‘hip’ 3D-features to talk about. A lot of blah-blah was going on about it in the last twelve months and many people were trying to make a big deal about it on the Web although no game did really support it. Today bump mapping is implemented into DirectX and game developers are starting to play with this feature. It enables you to see a realistically shaped surface with a relief on it, rather than the boring good old flat 3D-surfaces we know so well from Quake2 or many other games. A good example is waves on a water surface. Environment mapping can increase the realism even further by adding realistic reflections to those surfaces. Most 3D-chips are currently realizing bump mapping by adding another alpha-blending rendering pass to the rendering process, which gives an ‘OK’ kind of impression in many cases, but it’s still not really realistic. Matrox’ G400 and supposedly 3Dlabs’ Permedia3 are the only two chips that do real hardware bump mapping with environment maps right now, which is looking way better than the pseudo-bump mapping of its competitors. As soon as game developers make heavy usage of this nice feature, the other 3D-chip makers will have to come up with their hardware bump mapping solution as well.
Anisotropic Filtering
This feature is another catchword in the chase after customers and readers. I try to explain it as simply as possible. Bilinear and trilinear filtering, as used today, are ways of interpolating a pixel as a part of a texture so that it blends in into its environment reasonably. Those two filtering techniques have one big disadvantage, they filter evenly in each direction. This means that the filtering technique is the same at the edge of a wall as in the middle of a wall or the filtering is also the same regardless if you look at a surface under different angles. Unfortunately this isn’t very realistic, at the edge of a shape the filtering has to be different and the viewing angle should also have an impact on the filtering. Anisotropic filtering doesn’t mean anything than that the filtering is done ‘unevenly’. An algorithm has to find which part of a texture needs which kind of filtering. Thus anisotropic filtering is not a clearly defined procedure as bi- or trilinear filtering is. There are many different ways of implementing anisotropic filtering into a 3D-chip. We will have to see which one’s implementation looks best and most realistic. So far there isn’t any hardware implementation of anisotropic filtering in any of the new or announced 3D-chips.
Epilogue
So far about the requirements of a well performing 3D-chip or 3D-card. Of course there are a lot of other effects that 3D-chips can do today as well, like fog, transparency or different kind of shadings, but those ‘common’ features don’t really need to be mentioned again. However, there are still cases where features are implemented at a low quality level, when 3D-chip makers rate frame rates over image quality.
Realism is what we really want, the users and game developers have to tell the 3D-chip makers what they expect. The hardware developers have made another leap forward in terms of realism with the latest generation of 3D-chips and 3D-games should follow soon to take advantage of it. A look at the CPU-roadmaps shows that we can expect a lot more performance in very short time.