Very Long Instruction Word (VLIW) architectures rely on compile-time detection of parallelism; this implies the compiler analyses the program and detects operations to be executed in parallel; such operations are packed into one “large” instruction.
After one instruction has been fetched all the corresponding operations are issued in parallel. No hardware is needed for run-time detection of parallelism.
Advantages of the Very Long Instruction Word (VLIW) architecture;
- Simple architecture
- Each instruction word contains several instructions that are not dependent on each other, therefore you don’t need a large window of execution.
- The whole program is available at compile time so you can look through the program to determine dependencies.
Disadvantages of the Very Long Instruction Word (VLIW) architecture;
- Large code size after compilation
- Dependencies are detected at compile time which is not as good as in superscalar.