Tile Based Rendering and Accelerated 3D

ChickenHead writes "AnandTech has put together a review of the Hercules 3D Prophet 4500 based on the new Kyro II chip from STMicro. What's unique about this particular chip is that it uses a Tile-based Rendering Architecture which results in a much greater rendering efficiency than conventional 3D rendering techniques. It is so efficient in fact, that the $149 Kyro II card clocked at 175MHz is able to outperform a GeForce2 Ultra with considerably more power and around 3X the cost of the Kyro II card. With games not able to take advantage of the recently announced GeForce3's feature set, the Kyro II may be a cheap solution to tide you over until the programmable GeForce3 GPU becomes a necessity." A very readable and interesting summary and an interesting technology and a potentially extremely cool video card.

Comments

Tile-based rendering, strenghs and weaknesses

[Olivier Galibert]

The simple idea behind tile-based rendering is to divide the screen into square patches (8x8 or 16x16 usually) and, for each patch, find which of the triangles intersect the patch, do a quick depth sort to detect complete occlusions, and draw.

There is a good article on it, as applied to the powervr (which is using the same kind of architecture) at http://www.ping.be/powervr/PVRSGRendMain.htm. As others already said, you can see the results on the Dreamcast, or on the arcade version, the Naomi.

The strenghts are obvious:

• Lower fillrate required because of the per-petch occulted triangles elimination
• The currently-rendered tile memory can be on-die, L1-grade, releasing the bandwitch for texture reading

The weaknesses are a little less obvious:

• Rendering start delayed because it requires having all the triangles available. Can be somewhat hidden by multi-buffering
• Alpha-blending slows things down hard, because it increases the required fillrate very fast, and these cards are designed with a lower fillrate in mind
• There is no Z-buffer anymore (at least at peak speed, it's not copied back to the main memory), and we know that the 3D programmers love to do tricks with the Z-buffer

As a result, these cards are nice, but mostly represent another set of tradeoffs, not necessarily a revolution.

OG.