Computer Science 1.1.2

Computer Science 1.1.2

1. CISC vs RISC

   • CISC (Complex Instruction Set Computer)
     • Written in high level language and the compiler has little work to do.
     • Is a large and complex CPU with many transistors.
     • Less memory is needed.
     • Complex instructions can take multiple clock cycles to complete.
     • More complex hardware, richer instruction set results in less programming code.
   • RISC (Reduced Instruction Set Computer)
     • Smaller in size with fewer transistors.
     • Each small instruction carried out in one clock cycle, making pipelining simpler to improve performance.
     • More registers to store more smaller, simpler instructions.
     • Reduced instruction set results in faster processing of instructions.
     • Requires more lines of machine code due to fewer available instructions and more memory to store additional instructions created.

2. Multicore and Parallel Systems

   • Serial, Parallel and Distributed Processing.
     • Serial processing is the act of tending to and processing each item one at a time.
     • Parallel processing is the act of tending to all the items and processing them simultaneously.
     • Distributed processing is when a variety of computer systems using more than one computer or processor to run an application.
   • SIMD and MIMD are types of parallel architectures. The S stands for Single and the M for Multiple.
     • SIMD is Single Instruction Multiple Data. SIMD means that all parallel units share the same instruction, but they carry it out on different data elements.
     • MIMD is Multiple Instruction Multiple Data. MIMD means that parallel units have separate instructions, so each of them can do something different at any given time; one may be adding, another multiplying, yet another evaluating a branch condition, and so on.
   • Multiple cores results in more power that can be used to run multiple programs at the same time.
   • Double the cores doesn't mean double the speed however, as a fair amount of the extra speed is taken by the cores communicating with one another.