Trends in computer architecture: case study: parallel processing in the sega genesis (the sega genesis architecture, sega genesis operation and sega genesis programming).

  Case Study: Parallel Processing in the Sega Genesis

Home video game systems are examples of (nearly) full-featured computer architectures. They have all of the basic features of modern computer architectures, and several advanced features. One notably lacking feature is permanent storage (like a hard disk) for saving information, although newer models even have that to a degree. One notably advanced feature, which we explore here, is the use of multiple processors in a MIMD configuration.

Three of the most prominent home video game platforms are manufactured by Sony, Nintendo, and Sega. For the purpose of this discussion, we will study the Sega Genesis, which exploits parallel processing for real-time performance.

THE SEGA GENESIS ARCHITECTURE

Figure 10-34 illustrates the external view of the Sega Genesis home video game

image

system. The Sega Genesis consists of a motherboard, which contains electronic components such as the processor, memory, and interconnects, and also a few hand-held controllers and an interface to a television set.

In terms of the conventional von Neumann model of a digital computer, the Sega Genesis has all of the basic parts: input (the controllers), output (the television set), arithmetic logic unit (inside of the processor), control unit (also inside the processor), and memory (which includes the internal memory and the plug-in game cartridges).

The system bus model captures the logical connectivity of the Sega architecture as well as some of the physical organization. Figure 10-35 illustrates the system

image

bus model view of the Sega Genesis. The Genesis contains two general-purpose microprocessors, the Motorola 68000 and the Zilog Z80. These processors are older, low cost processors that handle the general program execution. Video game systems must be able to generate a wide variety of sound effects, a process that is computationally intensive. In order to maintain game speed and quality during sound generation the Genesis off-loads sound effect computations to two special purpose chips, the Texas Instruments programmable sound generator (TI PSG) and the Yamaha sound synthesis chip. There are also I/O interfaces for the video system and the hand-held controls.

The 68000 processor runs the main program and controls the rest of the machine. The 68000 accomplishes this by transferring data and instructions to the other components via the system bus. One of the components that the 68000 processor controls is the architecturally similar, but smaller Z80 processor, which can be loaded with a program that executes while the 68000 returns to execute its own program, using an arbitration mechanism that allows both processors to share the bus (but only one at a time.)

The TI PSG has 3 square wave tones and 1 white noise tone. Each tone/noise can have its own frequency and volume.

The Yamaha synthesis chip is based on FM synthesis. There are 6 voices with 4 operators each. The chip is similar to those used in the Yamaha DX27 and DX100 synthesizers. By setting up registers within the chips, a rich variety of sounds can be created.

The plug-in game cartridges contain the programs, and there is additional runtime memory available in a separate unit (labeled “Main memory” in Figure 10-35.) Additional components are provided for video output, sound output, and hand-held controllers.

SEGA GENESIS OPERATION

When the Sega Genesis is initially powered on, a RESET signal is enabled, which allows all of the electrical voltage levels to stabilize and initializes a number of runtime variables. The RESET signal is then automatically disabled, and the 68000 begins reading and executing instructions from the game cartridge.

During operation, the instructions in the game cartridge instruct the 68000 to load a program into the Z80 processor, and to start the Z80 program execution while the 68000 returns to its own program. The Z80 program controls the sound chips, while the 68000 carries out graphical operations, probes the hand-held controllers for activity, and runs the overall game program.

SEGA GENESIS PROGRAMMING

[Note from Authors: This section is adapted from a contribution by David Ashley, dash@xdr.com.]

The Sega Genesis uses plug-in cartridges to store the game software. Blank cartridges can be purchased from third party vendors, which can then be programmed using an inexpensive PROM burner card that be plugged into the card cage of a desktop computer. Games can be written in high level languages and compiled into assembly language, or more commonly, programmed in assembly language directly (even today, assembly language is still heavily used for game programming). A suite of development tools translates the source code into object code that can then be burned directly into the cartridges (once per cartridge.) As an alternative to burning cartridges during development, the cartridge can be replaced with a reprogrammable development card.

The Genesis contains two general-purpose microprocessors, the Motorola 68000 and the Zilog Z80. The 68000 runs at 8 MHz and has 64 KB of memory

devoted to it. The ROM cartridge appears at memory location 0. The 68000 off-loads sound effect computations to the TI PSG and the Yamaha sound synthesis chip.

The Genesis graphics hardware consists of 2 scrollable planes. Each plane is made up of tiles. Each tile is an 8´8 pixel square with 4 bits per pixel. Each pixel can thus have 16 colors. Each tile can use 1 of 4 color tables, so on the screen there can be 64 colors at once, but only 16 different colors can be in any specific tile. Tiles require 32 bytes. There is 64 KB of graphics memory, which allows for 2048 unique tiles if memory is used for nothing else.

Each plane can be scrolled independently in various ways. Planes consist of tables of words, in which each word describes a tile. A word contains 11 bits for identifying the tile, 2 bits for “flip x” and “flip y,” 2 bits for the selection of the color table, and 1 bit for a depth selector. Sprites are also composed of tiles. A sprite can be up to 4 tiles wide by four tiles high. Since the size of each tile is 8´8, this means sprites can be anywhere from 8´8 pixels to 32´32 pixels in size. There can be 80 sprites on the screen at one time. On a single scan line there can be 10 32-pixel wide sprites or 20 16-pixel wide sprites. Each sprite can only have 16 colors taken from the 4 different color tables. Colors are allocated 3 bits for each gun, and so 512 colors are possible. (Color 0=transparent.)

There is a memory copier program that is resident in hardware that performs fast copies from the 68000 RAM into the graphics RAM. The Z80 also has 8KB of RAM. The Z80 can access the graphics chip or the sound chips, but usually these chips are controlled by the 68000.

The process of creating a game cartridge involves (1) writing the game program, (2) translating the program into object code (compiling, assembling, and linking the code into an executable object module; some parts of the program may be written in a high level language, and other parts, directly in assembly language), (3) testing the program on a reprogrammable development card (if a reprogrammable development card is available), and (4) burning the program into a blank game cartridge.

See Further Reading below for more information on programming the Sega Genesis.

Leave a comment

Your email address will not be published. Required fields are marked *