IS310 4-7
sector
- a fraction of track holding 512 or 4096 bytes
Arithmetic Shift
A SHIFT instruction that performs division or multiplication
Dithering
A process that generates continuous color approximations by placing small dots of different colors in an interlocking pattern.
cache controller
A special-purpose processor or software that manages cache content; it guesses what data will be requested in the near future and loads this data from the storage device into the cache before it's actually requested.
instruction pointer
A special-purpose register that stores the address of the next instruction the control unit should fetch form memory
cache miss
An access to data that isn't stored in the cache.
Branch prediction
An approach to dealing with conditional branches in which the CPU guesses whether a branch condition will be true or false based on past experience
Branch
An instruction that causes the processor to depart from sequential instruction order; it's operand is loaded into the register that the control unit uses to fetch the next instruction. Also called JUMP Alters next instruction fetched/executed
What happens to register values when the CPU suspends processing one program and starts working on another?
Answer: -Values currently in the register are moved (PUSHED) to a stack for the program being suspended. -If the new program is being resumed then values in a stack are moved (POPED) back into the registers so the program can resume.
True or False: A parallel bus moves data faster than a serial bus?
Answer: False A serial buss moves data faster, but a parallel bus moves more data at one time.
load-store architecture
Avoid combining data movement with transformation
grayspace display
Displays black, white, and shades of gray
True or False: An inclusive OR (OR) instruction generates the value true if either (but not both) data input is true.
False
True or False: Character and text recognition is most accurate when text is printed in a single font and style, with all text oriented in the same direction on the page.
False
Parallel access (Disk Array)
Multiple locations on the same storage medium can be accessed at the same time
erasable PROM (EPROM)
ROM is cleared with a special ultraviolet light, and then users can write to the ROM
What are some of the characteristics that differentiate storage devices?
Speed Volatility Access method Portability Cost Capacity
Device electronics and mechanics
Speed or capacity increases must be coupled with improvements in components that position the read/write heads and the storage medium.
Basic RAM types are
Static RAM (SRAM) and Dynamic RAM (DRAM)
Hit Ratio
The ratio of cache hits to read accesses.
True or False: A cylinder is the same track on all platters of a disc drive?
True
Cache
a "fast" storage area used to improve the performance of read/write accesses to a slower storage device
Artificial
a "made-up" workload that is supposed to be representative of a class of real workloads
Logical SHIFT
a SHIFT instruction used to extract a single bit from a bit string
Switch
a device that can be open or closed to allow or block passage of electricity - implemented as a transistor
Block
a generic term describing the amount of data transferred in one read/write operation - term is most commonly used with magnetic tapes but can be used with any storage device
laser
a printer that operates by charging areas of a photoconductive drum; toner is attracted to charged areas of the drum and then to paper. -Use pixels as fundamental output unit -Have relatively large buffers Operates with an electrical charge and the attraction of ink to this charge Color laser output uses three separate print generators -Laser -Drum -Laser modulators
SDRAM:
a read ahead RAM that uses the same clock pulse as the system bus, read and write operations are broken into simple steps that can be completed in one bus clock cycle.
Solid State Drive (SSD)
a secondary storage device that packages flash memory (or other NVM devices) within a format that mimics a traditional magnetic disk drive: - that contains no moving parts.(EX: solid state hard drive, USB drive)
Buffer
a small storage area that holds data in transit from one device or location to another
point
a standard measurement unit of font size; equals 1/72 of an inch.
palette
a table of colors used to represent pixel color; the number of bits used to represent each pixel determines the table size.
Compression
a technique that reduces the number of bits used to encode a set of data items (e.g., a file or a stream of motion video images):
OCR (Optical Character Recognition)
a technology that combines optical-scanning technology with a special purpose processor or software to interpret bitmap content.
QR code
a two-dimensional bar code format that's widely used on posters and printed material to provide scannable information to a cell phone app.
The storage medium is typically metallic or some other ______ material (i.e., a material that will accept and hold a magnetic charge)
coercible
bus master
controls all bus transfers
MOVE
copies data bits to storage locations, any combination of registers and primary locations
STORE
data transfer from a register into primary storage
As stored in memory or a register, an instruction is a sequence of bits that must be ____________ to extract the processing function and data inputs (or the location of the data inputs
decoded
To improve performance: Data transfers to/from the CPU go "through" memory - commonly called
direct memory access (DMA)
Control unit
directs flow of data to/from memory, registers, and the arithmetic logic unit
Data is represented and processed within the CPU as
electrical signals
The _______ matches interrupt codes with memory addresses of programs that "handle" the interrupt
interrupt table
A(n) ____ is a microchip containing all the circuits and connections that implement a CPU.
microprocessor
OR
two 0 bits yields a 0, all other combinations are 1, or two falses are false, all other combinations are true
AND
two 1 bits yields a 1 but, all other combinations are 0, or two trues are true, all other combinations are false
Benchmarks can be roughly divided into 2 classes:
Artificial and Live-Load
spindle
One center mounting and attached motor - usually rotating multiple platters
RAM is ______ in typical use but its storage life can be extended hours or days with battery backup
non-volatile
Mechanical switches:
non-volatile, but slow and unreliable
Track
one concentric circle on one platter (the recording surface that passes under a R/W head as the platter rotates once
Replaced in the late 1980s by
single in-line memory modules (SIMMs) -DIPS are permanently mounted on a small card
Electronically-erasable PROM (EEPROM)
uses electric voltages delivered to the pins of the ROM chip to force erasure. -can be erased w/o removing them from computer -can store BIOS software
A word is:
-A fixed number of bits/bytes -The basic "unit" of data transformation in a CPU -The size of a data item that the CPU manipulates when executing a "normal" instruction
Portability is usually obtained at the expense of speed
For portable devices - slower "external" communication technologies and standards are used -For example, flash drive vs. installed RAM For removable media - loss of control over environmental conditions necessitates performance compromises -For example, sealed magnetic disc drive vs. CD or DVD
CMYK color
Four-dye scheme using a separate black dye (K)
Programmable ROM (PROM)
Manufactured blank and written once Each bit has a one and zero circuit - fry the one that you don't need! ---Programmed once for read-only access
What is an advantage of optical storage over magnetic storage?
Optical recording densities are at least 10 times higher than magnetic storage -Volatility (long term storage)
Most desktop and laptop computers and many midrange computers implement some version of the __________ bus standard
Peripheral Component Interface (PCI)
Human speech consists of a series of sounds called ____, roughly corresponding to the sounds of each letter of the alphabet
Phonemes
Magnetic disk storage uses rotating platters covered with coercible material Disk terminology: (5 things)
Platter, Spindle, Track, Cylinder & Sector
fetch cycle
The CPU cycle (also called the "instruction cycle") in which data inputs are prepared for transformation
Capacitors:
faster than batteries, but require frequent recharge unless they're "big"
Op code:
first group of bits represent instruction's unique binary number also a unique binary number representing the processing function and a template for extracting the operands
The first and still most widely-used NVRAM is called
flash RAM
NOT
flip every bit, or change true to false and vice versa
As data contents are created and deleted over time sectors of a single file tend to become scattered across random disk locations is called
fragmentation
If the instruction includes memory addresses of data inputs they're copied
from memory and loaded into registers as inputs for the ALU
Operands:
subsequent groups of bits that hold instruction's input values also one or more groups of bits after the op code that contain data to be processed or identify the location of that data (a register or memory address)
What is the primary purpose for a buffer?
temporary storage to assist with speed differences between devices
Speed mismatches between the CPU and primary storage cause
wait states
Sequential access time
time to read two adjacent sectors on the same track and recording surface
True or False: Image quality improves as pixel size increases.
False
True or False: In a peer-to-peer controlled bus the CPU manages which device can send data when?
False
RGB
Generates color by mixing red, green, and blue
operating system supervisor
If interrupt register is filled, the CPU branches to the
_____ are made of semiconductor material that has been treated with chemical impurities to enhance the semiconducting effects.
Transistors
Transistor-based switches:
Very fast but require continuous flow of electricity (i.e., volatile
Interrupt Register
When an interrupt is detected it is automatically stored in the
Dynamic RAM (DRAM)
a type of RAM that stores each bit by using a single transistor and capacitor
Live-Load
a workload based on "real" tasks such as playing an online game, encoding a DVD, or responding to web server requests
Batteries:
poorly suited to rapid storage/retrieval
Standard Performance Evaluation Corporation (SPEC)
provides a suite a benchmarks including: SPEC CPU: computational performance with integers and floating point numbers SPEC MPI: computational performance of problems distributed across a cluster SPECviewperf: workstation graphics performance SPECmail: email server performance
Stored magnetic charge must be above a minimum amount required to generate detectable current flow in the R/W head - sometimes called the
read threshold
power bus
routes electrical power (voltage and ground) to attached devices
HALT
self-explanatory An instruction that suspends the normal flow of instruction execution in the current program.
The CPU interacts with each device as though it were a storage device with ________ organized storage locations (e.g., a magnetic tape)
sequentially
primary storage devices generally emphasize
speed and "faster" access methods at the expense of other characteristics
Registers
storage locations within the CPU that hold ALU inputs, ALU outputs, and other data for fast access
The ______ is the communication channel that connects the CPU, primary storage, and peripheral devices such as secondary storage, network, and video controllers
system bus
Access time is
the elapsed time required to complete one read or write operation
Maximum data transfer rate
the fastest rate at which a disk can deliver data to other computer system components
PUSH
the process of copying register values to the top of a stack
Unconditional branch
always changes sequence
Conditional branch
changes only if the value true is stored in a register (value was stored as a result of a previous comparison instruction)
Gates are wired into ________ to perform more complex processing
circuits
SPEC MPI:
computational performance of problems distributed across a cluster
Crystalline
highly reflective (one bit)
Minimizing wait states dramatically
improves CPU and computer system performance
Scaling out
increasing available computer power by employing multiple computers in parallel for example -Clusters -Grids
SPECviewperf
workstation graphics performance
Which is better lossless or lossy compression?
Depends on what the goal is Lossless - preserve original quality, minimal CPU time Lossy - less storage space
True or False: An IDL can represent image components as embedded fonts, vectors, curves and shapes, and embedded bitmaps.
True
True or False: Moore's Law says that the rate of increase in transistor density on microchips increases steadily, roughly doubling every 18 to 24 months.
True
True or False: The control unit handles executing instructions to move data to memory, I/O devices, or secondary storage.
True
True or False: The instruction pointer (IP) can also be called the "program counter."
True
True or False: The system bus is logically or physically divided into subchannels?
True
LED Displays
Use less power and have a longer lifespan than LCD displays, making them the display choice for many laptop manufactures.
Portable Data Capture Devices
Used for warehouse inventory control and package routing, tracking and delivery
digital signal processing (DSP)
a microprocessor specialized for processing continuous streams of audio or graphical data; commonly embedded in audio and video hardware.
benchmark
a performance measure for a computer system or one of its components when performing a specific and realistic type of software task, for example: -Responding to an HTTP request -Processing a complex database transaction -Reading/writing a disk -Redrawing the screen in an animation -Combinations of the above
postscript
an adobe image description language designed mainly for printed documents, although it's also a programming language for generating video display outputs. -Used in printing and publishing and as graphic file interchange format and embedded printer technology -Lacks features needed to generate and manage documents as an integrated whole
Device controller
an interface device that connects the storage device (or its R/W mechanism) to the system bus
The ____ is a digital circuit that generates timing pulses, or signals, and transmits the pulses to other devices in the computer. a) clock rate b) system clock c) clock cycle d) wait state
b) system clock
Current packaging is
dual in-line memory modules (DIMMs) -SIMMs with (different) electrical contacts on both sides -More contacts required by larger word sizes and bus width
Early packages were ___________ chips installed on expansion cards or directly in motherboard
dual-inline package (DIP)
Defragmentation
is a disk reorganization process that takes scattered sectors of the same file and reorganizes them for maximal read/write efficiency
bus
is a shared electrical or optical channel that connects two or more devices
Like the CPU a bus has a clock rate: parallel bus
the rate is much lower than the CPU (e.g., 66 MHz)
Like the CPU a bus has a clock rate: serial bus
the rate is similar to the CPU (e.g., 2.5 GHz) though only a few bits are transmitted per cycle
optical scanner
A device that generates bitmap representations of printed images; detects light reflected from the page with an array of photosensors.
Image Description Language (IDL)
A language (usually device independent) that uses compact bit strings or ordinary ASCII or Unicode text to describe primitive image components, such as straight lines and simple shapes; reduces storage space requirements because a description of a simple image component is usually much smaller than a bitmap. -IDLs (Image Description Language) are commonly used to improve printer performance
from primary storage
The control unit reads an instruction from
a store operation
A register to memory address
Moore's Law
transistor count on a chip doubles every 18-24 months at no cost increase -Implies greater power and/or speed IF the additional transistors are used as effectively as the previous ones
ROM technologies (oldest to newest, but all are "old"):
1. Read-only memory (ROM) 2.Programmable ROM (PROM) 3.Erasable PROM (EPROM) 4.Electronically-erasable PROM (EEPROM)
___________________ describes the surface area of a storage medium used to store 1 bit Areal density is a number stated as bits per area unit Typical units are bits, bytes, or tracks per inch
Areal density (also called recording density or bit density) -The coercible material per bit decreases as the areal density increases; higher areal density makes stored data more susceptible to loss caused by decay and leakage if all other factors are equal
_______ is the loss of magnetic charge strength over time
Magnetic decay -All magnets lose charge over time -Rate of charge loss varies with coercible material and its mass -Natural charge decay over time; data must be written at a higher power than the read threshold to avoid data loss.
Two approaches to controlling bus access:
Master slave bus and Peer-to-peer bus
Bit encoding methods include:
Pits and lands, Dye-based & Phase-change
half-toning
Simulating shades of gray by dithering black and white dots. See also dithering.
font
a collection of characters of similar style and and appearance -Usually measured in points -one seventy-second of an inch refers to height of characters
instruction
a command to the CPU to perform a single processing function on specific data inputs
Cylinder
set of tracks on all recording surfaces the same distance from the edge
L3 cache
shared among multiple CPU cores on a single chip
Typical "normal data sizes"
"Business" applications - 32 or 64 bits "Scientific" applications - 64 or 128 bits Database and multimedia applications - highly variable, but more is generally better!
gigahertz (GHz)
A measurement of wave of system clock frequency; one billion cycles per second
PassMark
Test suite for microcomputers
Amorphous
- low reflectivity (zero bit)
Pointing Devices include:
-Mouse -Trackball -Joystick
Average access time
average of access times for many different storage device locations
SPECmail:
email server performance
interrupt code
Interrupt value is an unsigned integer called an
cache hit
An access to data already contained in the cache.
Writing to a cache:
-Data is sent and written immediately to the cache -Write completion is acknowledged before data is written to the storage device -Data is copied from the cache to the storage device "later"
Memory-Storage Hierarchy Facts
-A computer system includes multiple types of storage devices -Each device has a unique combination of characteristics -Each device is optimal (or at least reasonable) for certain purposes -The mix of devices and their capacities is a cost/performance trade-off
Volatile
- if it cannot reliably hold data for long periods of time
Cloud-based storage services come in many forms but they have common features and underlying principles:
-A service provider manages large amounts of storage hardware in remote locations shared by many users thus realizing significant economies of scale -Data is stored in multiple remote locations to protect against loss and ensure availability when and where needed -High-speed network connections among local computer systems and storage service providers enable rapid movement of data -Data stored on local storage devices is frequently or continuously synchronized with copies stored in remote locations -Software on both local and remote computer systems keeps track of all data copies and coordinates data movement among local and remote storage locations as needed -Users aren't aware of (and don't care about) the work that software does behind the scenes to ensure data protection and availability
Serial access (Tape)
-Access locations or organized serially (in a line) -Access to location N requires accessing (or skipping over) locations 1 through N+1 -Old technology - avoided whenever possible!
Buffer overflow - a condition where:
-All storage locations in the buffer have data and the receiving device has not yet processed the data -New data arrives and is either lost or overwrites other data in the buffer
Random access (Disk)
-Also called direct access -Any location on the storage medium can be accessed in (approximately) the same amount of time
Device controller implements:
-Bus protocol -Translation between bus and device protocols -Translation between logical and physical accesses and addresses
Immediate acknowledgement of a write operation has risks:
-Cache is implemented with RAM and is thus volatile -If power is lost or the system crashes after write acknowledgement but before the write to the storage device completes then the written data is "lost"
CPU Speed (4 characteristics)
-Clock Rates -Registers -Word Size -Cache
video display
-Connected through dedicated low-speed communication links -Only display text and primitive graphics
LCD
-Contains matrix of liquid crystals sandwiched between two polarizing filter panels -Active and passive matrix displays -Manufactured with thin film transistor (TFT) technology
Compression with secondary storage
-Data going to storage device is compressed prior to storage -Data read from the storage device is decompressed
Compression with data communication
-Data is compressed prior to transmission across a low-bandwidth channel -Data in decompressed as it leaves the channel
Reading from a cache:
-Data is read from the storage device into the cache in anticipation of future read requests -Data is requested from the storage device -If the data is already in the cache is immediately transmitted
Two common approaches to lossy compression:
-Decompression algorithm isn't a mirror of the compression algorithm (e.g., PDF) -There is no decompression algorithm (e.g., MP3) or the decompression algorithm is really just a decoding algorithm (e.g., video DVD)
Matrix-Oriented Image Composition facts
-Display surfaces vary wide in size and composition Divided into rows and columns similar to a large matrix -Each cell (pixel) represents one simple component of an image Resolution -Number of pixels displayed per linear measurement unit -Stated in dots per inch (dpi)
High-Performance Clustering Example
-Each node is a 32-CPU rack -Groups of 16 racks are directly connected -Each rack group is interconnected by a high-speed 8-way switch -Specialized rack groups manage all secondary storage access -Architecture is optimized for: -Parallel processing with significant need for inter-node communication -Flexible assignment of compute nodes to problems and problem pieces
Immediate write acknowledge can be:
-Enabled - maximizes performance improvement associated with write caching -Selectively enabled - difficult/complex to implement -Disabled - minimizes or eliminates performance improvement associated with write caching (effectively turns the write cache into a large buffer)
Can be reduced with bitmap compression using
-Graphics Interchange Format (GIF) -Joint Photographic Experts Group (JPEG) -Moving Pictures Experts Group (MPEG)
Cache performance principles:
-If the cache is faster than the underlying storage device then access to the cache (read or write) will be faster than access to the underlying storage device -For reading, can we guess what will be read next from the storage device and put it in the cache "ahead of time"? -For writing, can we (quickly) place the data in the cache and copy it to the storage device later?
Input pads INCLUDE (e.g., digitizer tablet)
-Infrared detector -Photosensor -Pressure-sensitive pad -Magnetic fields
Rapid increases in processor performance relative to data communication and storage performance has made compression increasingly attractive:
-MP3 and similar audio compression techniques -GIF and JPEG -Video DVDs -H.323 video-conferencing -Compressed tape formats -Automatic compression of "old" files on secondary storage
multicore microprocessors places:
-Multiple processing cores (roughly comparable to a CPU) on a single chip -Usually includes one or more large (multi-megabyte) L3 primary storage caches
phase change
-Phase-change -Used with "rewritable discs" (e.g., DVD-RW) Recording layer coated with a substance that can be in one of two reflective states
Multi-CPU architecture employs multiple microprocessors on a single motherboard sharing:
-Primary storage -Secondary storage -System bus -I/O devices
ADD
-Produce the arithmetic sum of two bit strings -Need multiple ADD instructions, one per data type/format
How does a cache differ from a buffer?
-Reading from a cache doesn't consume the data -Cache is used for bidirectional data transfer -Cache is used only for storage devices -A cache is usually much larger than a buffer -More "intelligence" is require to manage cache content
A buffer can improve the efficiency of the faster device during an I/O operation by:
-Reducing the number of interruptions -Reducing processing overhead for the interruptions
MP3 takes advantage of human limitations:
-Sensitivity that varies with audio frequency (pitch) -Inability to recognize faint tones of one frequency simultaneously with much louder tones in nearby frequencies -Inability to recognize soft sounds that occur shortly after louder sounds
Audio I/O Devices
-Sound: an analog signal that must be converted to digital form for computer processing or storage -Various mathematical transformations convert complex sounds to a single numeric representation -Sampling and playback rely on analog-to-digital converters (ADC) and digital-to-analog converters (DAC) Used in computer systems for: -General-purpose sound output (e.g., warnings) -General-purpose sound input (e.g., digital recording for voice email messages) -Voice command input -Speech recognition -Speech generation
Storage devices vary in the following important characteristics:
-Speed -Volatility (or lack thereof) -Access method -Portability (or lack thereof) -Cost and capacity
The source and destination of an I/O operation typically different in two important respects:
-Speed of data transfer -Data transfer unit size
Thus, to store a CPU's data we must either:
-Store electrical signals directly -Use the electrical signals to generate something else that can be stored
The stored charge is determined by:
-Strength of the "write" magnetic field -Mass of coercible material that holds a bit value -Magnetic properties of the coercible material -Loss of charge due to magnetic leakage, magnetic decay, and loss of coercible material
Storage device portability comes in two forms:
-The entire device (medium, R/W mechanism, and maybe the controller) is portable For example, flash drive, compact flash card, external USB hard drive, many cell phones when connected to the USB port of a laptop or desktop computer -Only the storage medium is removable and portable For example, CD and DVD
Scaling out is gradually (but not completely) supplanting scaling up:
-The gap between network vs. "within computer" data transfer rates has narrowed, though it's still several orders of magnitude -Software for managing multicomputer configurations has improved significantly - morphing into "cloud" computing -Organizational need for flexibility - need to be able to quickly redeploy computing resources
Data flows through a buffer:
-The sending device adds data to the buffer, gradually filling it -The receiving device (or buffer manager) consumes data in the buffer, gradually emptying it -The content of the buffer rises and falls depending on the timing and relative speed of addition and consumption
keyboard
-Translate keystrokes directly into electrical signals -Generate bit stream outputs (scan code) with a keyboard controller -Can connect to computer in various ways(e.g., PS/2, USB, wireless)
On-chip caches
-Used in combination with some form of read-ahead access -The "waiting space by the door" is composed of SRAM (the cache) -The "real" storage is DRAM -Sometimes called enhanced DRAM (EDRAM)
Dye Based
-Used with "write once" disks (e.g., CD-R) Manufactured dye layer has high reflectivity (all one bits) -Write operation uses higher-powered layer to "burn" a dark spot (zero bit) -Write times are slow since multiple "laser hits" are required
Magnetic Read/Write Operations -A magnetic R/W head operates two ways
-When writing, current flows left-to-right or right-to-left and the magnetic gap generates a magnetic field with the same polarity as the current flow -When reading, the stored magnetic charge induces an electric current in the direction of the magnetic polarity -In either case, direction of current flow represents a zero or one bit value
Exclusive OR (XOR)
0 and 1 are 1, all other combinations are 0, or true and false is true, all other combinations are false
Execution stages:
1)Fetch from memory 2)Increment and store instruction pointer (IP) 3)Decode instruction and store operands and instruction pointer 4)Access ALU inputs 5)Execute instruction within the ALU 6)Store ALU output
What three general elements are required for a storage device to function?
1. Storage Medium (saves the 1's and 0's) 2. Read/Write Mechanism 3. Device Controller
An input/output (I/O) port is:
A communication pathway between the CPU and a peripheral device -A set of memory addresses through which data is passed between the CPU and one peripheral device
Reduced Instruction Set Computing (RISC)
A computer and processor design approach that typically includes fixed-length instrucions, short instruction length, and a large number of general-purpose register; the main feature is the absence of some complex instructions from the instruction set -Avoid "unnecessary" complex instructions - keep instruction count to several dozen to a few hundred -Minimize number/complexity of instruction formats -Minimize maximum instruction length
Complex Instruction Set Computing (CISC)
A computer and processor design approach, using complex instructions that do more work per instruction; it reduces the extra memory required for program storage and execution in RISC CPUs
a load operation
A memory address to a register
MOVE copies data from
A memory address to a register (a load operation) A register to memory address (a store operation) A register to another register
Non-volatile memory:
A memory device that can hold content without continuous power flow
Pipelining
A method of organizing CPU circuitry so that multiple instructions can be in different stages of execution at the same time; a form of parallel processing
logical device
A read (device to CPU) or write (CPU to device) operation is called
stack
A reserved area of primary storage accessed on a last-in, first-out (LIFO) basis; this mechanism enables a program suspended by an interrupt to resume execution in exactly the same state as before an interruption.
Musical Instrument Digital Interface (MIDI)
A standard for storing and transporting control information between computers and electronic musical instruments and synthesizers.
bitmap
A stored set of numbers describing the content of all pixels in an image.
PDF417 format
A two-dimensional rectangular bar code format with vertical bars marking the left and right edges
Static RAM (SRAM)
A type of RAM that's implemented entirely with transistors; the basic storage unit is a flip flop circuit.
plasma display
A video display device that uses an active matrix display and generates light by applying an electrical charge to neon gas.
What is the difference between data access time and data transfer rate?
Access time = Elapsed time required to complete one read or write operation Data Transfer Rate = How much data is read or written in a single read/write operation?
Wait states access to (3 things)
Access to memory Access to system bus Access to storage and I/O devices
The system bus of a typical computer system is logically or physically divided into subchannels, each with a specific purpose:
Address Bus, Data Bus, Control Bus and Power Bus
Portable Document Format (PDF)
An Adobe image description language developed to generate and manage documents as an integrated whole rather than a collection of independent images and pages --Ability to distribute compressed documents with complete authorial control over exact format of the printed and displayed document, regardless of end user's specific computer, OS, or printer
Speculative execution
An approach to dealing with condition branches in which the CPU executes instruction after a branch prediction but before the final branch condition value is known with certainty
digital-to-analog converter (DAC)
An audio device that accepts a bitstream representing sound samples and generates a continuous analog signal that can be amplified and routed to a speaker.
Analog-to-digital converter (ADC)
An audio device that accepts a continuous electrical signal representing sound, samples it at regular intervals, and outputs a bitstream representing the samples. See also sampling.
wait state is
An idle clock cycle during which the CPU is waiting for a response from another device
dot-matrix printer
An impact printer that moves a print head containing a matrix of pins over the paper, and a pattern of pins matching the character or symbol to be printed is forced out of the print head.
magnetic tape
An older secondary storage medium that uses a strip of thin plastic coated with a magnetically sensitive recording medium
cache swap
An operation performed after a cache miss. The cache controller guesses which data is least likely to be needed in the near future, writes it to the storage device, and purges it from the cache. The requested data is then read from the storage device and placed in the cache.
bar code scanner
An optical input device that detects specific patterns of bars or boxes representing numeric data.
mark sensor
An optical input device that scans for light or dark marks at specific locations on a page.
True or False: Layer 1 cache is shared among multiple CPU cores on a single chip?
Answer: False (layer 3)
Multiprocessing
Any CPU architecture in which duplicate CPUs or processor stages can execute in parallel -carries the duplication to higher levels
Non-volatile RAM (NVRAM)
Any RAM device that can hold content without continuous power flow
peer-to-peer bus
Any device can temporarily become a bus master -Requires a protocol for "passing around" the bus master role and a prioritization scheme for competing requests to be bus master
multithreading
Application software that takes advantage of multiprocessing is more complex because it must be designed for parallel execution
Methods of directly storing electrical signals include:
Batteries, Capacitors, Mechanical switches & Transistor-based switches
pits and lands
CD's use these to store information
two reflective states
Crystalline & Amorphous
Instruction sets
Collection of instructions that a CPU can process
Lossy Compression
Compressing then decompressing does not reproduce original data (common with audio and still/motion video) -data compression techniques in which some amount of data is lost. This technique attempts to eliminate redundant information.
Lossless compression
Compression followed by decompression exactly reproduces original data -Generally used for data such as files containing programs or numeric data (e.g., ZIP files)
what are the Electrical Properties
Conductivity, Resistance, Heat & Speed and circuit length
CPU components include:
Control unit - directs flow of data to/from memory, registers, and the arithmetic logic unit Arithmetic logic unit (ALU) - executes computation and comparison instructions Registers - storage locations within the CPU that hold ALU inputs, ALU outputs, and other data for fast access
Optical Input Devices
Detect light reflected off a printed surface or object into a photosensor
bus slaves
Devices that must go through the bus master for access to the bus.
Digital Cameras
Digital still cameras, video cameras, and Webcams use a 2D photosensor array placed behind lenses to capture reflected and focused ambient light -Digital still camera -Captures one image at a time -Can configure to store images in a compressed format, such as JPEG
The central processing unit (CPU) is the computer system "brain":
Executes program instructions including computation, comparison, and branching Directs all computer system actions including processing, storage, input/output, and data movement
True or False: Phosphors emit colored light in liquid crystal displays.
False
True or False: Quantum processors are expected to replace conventional processors in most computer system
False
True or False: The larger the cache size the faster the computer runs.
False
True or False: Variable-length instructions simplify the instruction-fetching process in the control unit.
False
True or False: A monochrome display can display black, white, and many shades of gray in between, so it requires 8 bits per pixel.
False
CMY
Generates color using cyan (absence of red), magenta (absence of green), and yellow (absence of blue)
Program status word (PSW)
Goes by many different names - Set of bit flags containing error and other codes related to processing results, for example: -Result of comparison operations -Divide by zero -Overflow and underflow
An ______ is a device controller "on steroids"
I/O channel
The CPU would incur many ______ if it waited for peripheral devices to complete tasks
I/O wait states
I/O wait states
Idle processor cycles consumed while waiting for secondary storage or I/O devices to complete access requests.
The CPU constantly alternates between two stages (or cycles):
Instruction cycle: Also called the fetch cycle
______ is the cancellation of magnetic charge in adjacent areas of opposite polarity
Magnetic leakage -Causes relatively rapid loss of charge -Worst when bit storage areas can be adjacent in three dimensions (e.g., magnetic tape) -Cancellation of adjacent charges of opposite polarity and migration of charge to nearby areas; data must be written at a higher power than the read threshold to avoid data loss.
SHIFT
Move all bits left or right and fill in zeros Can be used to extract single bit values (logical shift) Can be used for binary multiplication and division (arithmetic shift)
_______ holds instructions and data for immediate/frequent CPU access
Primary storage
Pros of providing only a minimal instruction set
Processor is simple to build and construct Simple = cheaper CPUs with very fast clock rates
Cons of providing only a minimal instruction set
Programs that need complex processing/data are complex Complex = expensive, slow, and error-prone program development
Compression ratio
Ratio of uncompressed to compressed data size (often an average)
The number of refresh cycles per second is normally stated in hertz and called the ____.
Refresh Rate
Access methods fall into three broad classes:
Serial access (Tape) Random access (Disk) Parallel access (Disk Array)
TPC
Server-oriented performance for processing business or database transactions
Attributes of an Instruction Sets
Size of the instruction set Size of the individual instructions, op codes, and operands Supported data types Number and complexity of processing operations implemented as individual instructions
Cost and Capacity
Speed - cost increases as speed increases Volatility-Cost increases as volatility decreases (permanence is more expensive than volatility) Access method-Serial is cheapest, direct is more expensive, parallel is more expensive than non-parallel Portability-Portability increases cost, though most portable devices sacrifice other characteristics to minimize the cost increase Capacity-Within limits, cost increases proportionally to capacity
Media integrity
Stability of coercible material and its attachment to the substrate; physical stress and extremes of temperature and humidity must be avoided to prevent loss of coercible material.
peripheral devices
Storage and I/O devices in a computer, other than the CPU and primary storage.
Magnetoresistive RAM (MRAM)
Stores data using magnetic charges instead of electrical charges. Has greater storage capacity, consumes less power, and has faster access times than electronic RAM -Stores bit values with two magnetic elements One with fixed polarity Other with polarity that changes when a bit is written -Read and write speeds comparable with SRAM -Density comparable with DRAM -Writes aren't destructive―better longevity than flash RAM
execution cycle
The CPU cycle in which instructions are retrieved from registers, the specified data transformation is performed, and data outputs are stored in registers
in the instruction register
The control unit stores the instruction in the
Logical access:
The device, or its controller, translates linear sector address into corresponding physical sector location on a specific track and platter
read-only memory (ROM)
The earliest type of nonvolatile memory, with data content written permanently during manufacture; this primary storage device can be read, but no further data can be written.
clock rate
The frequency (expressed in Hz) at which the system clock generates timing pulses -the frequency of those ticks
flash RAM:
The most common type of nonvolatile memory; typically used to store firmware and in portable secondary storage systems, such as USB flash drives. -Cost and bit density is comparable to DRAM
refresh rate
The number of refresh cycles per second on a video display device; normally stated in hertz. See also refresh cycle.
machine state
The saved register values of interrupted processes or programs that represent their state before an interrupt.
linear address space
The set of sequentially numbered storage locations in a peripheral device; these locations must be converted into a disk's corresponding platter, sector, and track for the CPU to physically access the correct sector.
Access time is:
The sum of time required to: "Accept" the read or write command "Find" the appropriate location on the storage medium Transfer data to/from the location
rotational delay
The time a hard disk controller must wait for the right sector to rotate beneath read/write heads.
Head-to-head switching time
The time needed to switch a hard drive's read/write circuitry to the correct read/write head before accessing a sector.
In what scenario is writing to cache a problem?
When the power goes out before the cache controller has completed the write to the secondary storage device.
video controllers
a device connected to the system bus (or dedicated video bus) that accepts commands and data the CPU and generates analog or digital video signals, which are transmitted to the monitor.
Storage medium
a device or substance on which data is stored, for example: -Storage circuitry of a flash drive or RAM device -Metallic surface of a magnetic disk -Reflective surface of an optical disc
Read/Write (R/W) mechanism
a device used to access (read) and store (write) data values on a storage medium, for example -Access circuitry of a flash drive or RAM device -Laser and photo-detector in an optical disc drive
Random Access Memory (RAM)
a primary storage technology with the following characteristics: -Bits are stored using transistors and/or capacitors -Semiconductor chip -Read and write access time is approximately equal -Combination of random and parallel access
Plotters
a printer that generates line drawings on sheets or rolls of paper up to 64 inches wide. -Use inkjet technology -Can produce any large output, including posters and banners -Usually called largeformat printers
Inkjet
a printer that produces printed images by placing small drops of liquid ink onto paper; ink is forced out of the nozzle by mechanical movement of by heat. -Use pixels as fundamental output unit -Have relatively large buffers -Most common printing technology -Prints with liquid ink placed directly onto paper -Uses mechanical movement or heat to force ink out of nozzle -Paper is drawn past moving print head -Resolution is up to 1200 dpi
touchscreen
a technology that enables a flat panel display to function as both an input and out device. -Additional layers added to a flat panel display to detect touch -Touch sensors (capacitors) are laid out in a grid and connected with traces -Most common form is based on capacitance - the ability of a substance (e.g., a finger) to hold electrical charge -Touching the screen interrupts the electrical field generated by embedded capacitors in a detectable way
Phase-change memory (PRAM or PCRAM)
a type of nonvolatile memory under development that uses a GST company capable of switching between amorphous and crystalline states; has fast write times and high longevity.
A(n) ____ program performs specific tasks that can be counted or measured.
benchmark
In a(n) ____, the processor always departs from the normal execution sequence. a) HALT b) exception JUMP c) unconditional BRANCH d) conditional BRANCH
c) unconditional BRANCH
Data Bus
carries bits of a data item being transferred to/from memory or the CPU
Address bus
carries bits of a memory address (which identify the source or destination of a bus transfer
Control Bus
carries bits of commands, responses, status codes, and similar signals
SPEC CPU
computational performance with integers and floating point numbers
Compression algorithm
computational technique for reducing data size
Decompression algorithm
computational technique for reversing compression algorithm
Boolean logic
convert individual bits within a bit string (bitwise operations) or treat entire bit strings as true or false and manipulate/combine them (logic operations)
Instruction register
copy of most recently fetched instruction
Rock's Law
cost of a processor fabrication facility doubles every four years -Currently >10 billion dollars
LOAD
data transfer from main memory to a register
A ________ can connect multiple devices to a single bus slot
device controller
Peripheral devices are connected to a bus via a
device controller
monochrome display
displays one of two colors, requires only one bit per pixel
Resistance
even good conductors turn some electrical energy into heat -Circuit length is limited because energy loss accumulates -Heat must be dissipated to prevent higher resistance or physical damage to conductors
Arithmetic logic unit (ALU)
executes computation and comparison instructions
Primary storage is
fast, volatile, parallel access, non-portable, and relatively expensive
Nonvolatile
if it holds data without loss over long periods of time (typically, years or decades)
L2 cache
implemented outside of but dedicated to a single CPU
Scaling up
increasing available computer power by employing powerful computers for example -Multicore microprocessors -Multi-CPU architecture
L1 cache
integrated with each CPU's control unit
An _______ is a signal to the CPU that some event has occurred that requires its attention, for example: Storage device has completed a read command User pressed a key or clicked a mouse Packet arrived from the network UPS switched to backup power A processing error occurred (e.g., overflow)
interrupt
If there are data inputs embedded in the instruction they're loaded
into registers as inputs for the ALU
flip-flop circuit:
is an electrical switch that "remembers" its last position (open or closed) as long as power continuously flows though it
sustained data transfer rate
is computed based on an assumed "typical distribution" of data
average access time
is the sum of average access delay and the time required to read one sector.
Secondary storage holds
large quantities of data for long time periods -Thus, secondary storage devices tend to emphasize non-volatility and cost at the expense of other characteristics
ALU circuitry
manipulates all bits of a word in parallel while executing a single instruction
program counter
memory address for next instruction fetch
MFLOPS
millions of (fetched/executed) floating point operations per second
MIPS
millions of (fetched/executed) instructions per second - presumed to be integer instructions or a "typical" mix
Gate
multiple switches wired together to perform a processing function on one bit: A)NOT B)AND C)OR D)XOR E)NAND
platter
one of a stack of metal disks that store information in the hard drive -1 disk, usually recorded on both sides
The first group of bits represents the instruction's unique binary number, commonly called the ____.
op code
Digital still cameras, video cameras, and webcams use an array of ______________ placed behind lenses to capture reflected and focused ambient light.
photosensors
Secondary storage is
slow, non-volatile, various access methods, may be portable, less expensive
Sector
the amount of data transferred to/from an optical or magnetic disk in one read/write operation - usually 512 bytes
track-to-track seek time
the average time needed to move a read/write head between two adjacent tracks; typically measured in milliseconds.
POP
the process of removing register values from the top of a stack and loading them back into the correct registers
Average access delay
the time required to "move" between two sectors separated by an "average" number of recording surfaces, tracks, and sectors