Kujtim

Postuar nga: riparim  :  Kategori: Kujtim
Memory is as fundamental to computer architecture as any other element. Theability of a systems memory to transact the right quantity of data in the right spanof time has a substantial impact on how that system ful?lls its design goals. Digitalengineers struggle with innovative ways to improve memory density and bandwidthin a way that is tailored to a speci?c applications performance and cost constraints.
Knowledge of prevailing memory technologies strengths and weaknesses is a keyrequirement for designing digital systems. When memory architecture is chosenthat complements the rest of the sys- tem, a successful design moves much closerto fruition. Conversely, inappropriate memory architecture can doom a good ideato the engineering doldrums of impracticality brought on by arti?cial complexity.This chapter provides an introduction to various solid-state memory technologiesand explains how they work from an internal structural perspective as well as aninterface timing perspective.
A memorys internal structure is important to an engineer, because it explains whythat memory might be more suited for one application over another. Interface timingis where the rubber meets the road, because it de?nes how other elements in thesystem can access memory components contents. The wrong interface on amemory chip can make it dif?cult for external logic such as a microprocessorto access that memory and still have time left over to perform the necessaryprocessing on that data. Basic memory organization and terminology are introduced?rst. This is followed by a discussion of the prevailing read-only memorytechnologies: EPROM, ?ash, and EEPROM. Asynchronous SRAM and DRAMtechnologies, the foundations for practically all random-access memories, arepresented next. These asynchronous RAMs are no longer on the forefront ofmemory technology but still ?nd use in many systems. Understanding their operationnot only enables their application, it also contributes to an understanding of themost recent synchronous RAM technologies. (High-per-formance synchronousmemories are discussed later in the book.) The chapter concludes with adiscussion of two types of specialty memories: multiport RAMs and FIFOs.Multiport RAMs and FIFOs are found in many applications where memoryserves less as a storage element and more as a communications channelbetween distinct logic blocks.
afër : E-libër Complete_Digital_Design

Advanced Microprocessor Concepts

Postuar nga: riparim  :  Kategori: Microprocessors edukativ dhe mikrokoordinator
Computer architecture is central to the design of digital systems, because mostdigital systems are, at their core, computers surrounded by varying mixes ofinterfaces to the outside world. It is dif?cult to know at the outset of a project howadvanced architectural concepts may ?gure into a design, because advanceddoes not necessarily mean expensive or complex. Many technologies that wereoriginally developed for high-end supercomputers and mainframes eventuallyfound their way into consumer electronics and other less-expensive digital systems.This is why a digital engineer bene- ?ts from a broad understanding of advancedmicroprocessor and computing concepts a wider palette of potential solutionsenables a more creative and effective design process.
This chapter introduces a wide range of technologies that are alluded to in manytechnical speci?- cations but are often not understood suf?ciently to take fulladvantage of their potential. What is a 200-MHz superscalar RISC processorwith a four-way set associative cache? Some people hear the term RISC andconjure up thoughts of high-performance computing. Such imagery is notincorrect, but RISC technology can also be purchased for less than one dollar.Caching is another big computer term that is more common than many peoplethink.
An important theme to keep in mind is that microprocessors and the systemsthat they plug into are inextricably interrelated, and more so than simply byvirtue of their common physical surround- ings. The architecture of onedirectly in?uences the capabilities of the other. For this reason, the two needto be considered simultaneously during the design process. Among manyother factors, this makes computer design an iterative process. One maybegin with an assumption of the type of mi- croprocessor required andthen use this information to in?uence the broader system architecture.
When system-level constraints and capabilities begin to come into focus,they feed back to the microprocessor requirements, possibly altering themsomewhat. This cycle can continue for several iterations until a design isrealized in which the microprocessor and its supporting peripherals arewell matched for the application.
afër : E-book Complete_Digital_Design