A+ 1001: CPU Flashcards
CPU
Central Processing Unit
Main components of CPU
I/O unit:
- external data bus
- internal data bus
Control Unit
- Logic unit “decoder”
- instruction address register
- instruction register
- Instruction Table
Registers
ALU (arithmetic and Logic Unit)
Clock Multiplier
SRAM (Cache)
Intel 8088 code
Used on the first-ever CPU
Clock
Tells the CPU to do something
Cpu pipeline
Cpu core
The internal steps were taken by the CPU Core to perform calculations
CPU can have multiple cores each acting like a CPU in itself
Clock Speed
Rate at which cpu can process information
1 Hz 1 cycle per second
1 GHz = 1 Billion cycles per second
Regulated by the quartz oscillator that acts like a metronome
The rest of the motherboard runs at a max of 400Mhz (4 million cycles per second)
2 major manufacturers
Intel
AMD (Advanced Micro Devices)
Clock multiplying
Cpu takes the pulse coming from the quartz oscillator and multiplies it, using an internal multiplier, because the CPU runs at a clock speed multitudes faster than the mother board
microarchitecture
internal design of the cpu
identified by the code name of cpu
What sets the base speed of the motherboard?
It is set at the factory with the oscillating quartz crystal
Overclocking
Process of manually set clock speeds on CPU and motherboard, to push the system beyond its rated speed
Hyperthreading
one core (pipeline) handling two incoming pieces of code
What happens when you click on a program?
A copy of that program that lives in mass storage is copied into RAM, once it is in RAM individual lines from the program is fed into the CPU where they are executed
or
When you click on a program, a process is created
That process is assigned its own ram and credentials (ie serial number)
The system then assigns that process to a CPU core
If there are no cores available, it will virtually split the core into one of the core threads
If there are no Cores or threads available then the process waits in queue until it is called into action.
If a core or thread is available the process is executed.
SRAM
Superfast ram that is built into the CPU and acts like a Cache
This helps to reduce the lag that results from the differing speeds between CPU, RAM, and MASS STORAGE.
Pipeline stall
Is what happens when the CPU asks for the next line of code and it is not available
The pipeline is shut down and has to wait for the code to be retrieved from RAM
3 Caches
Level 1 cache:
- 64k Ram
- Runs at multiplied speed of CPU
Level 2 cache:
- 128 - 256 K Ram
- Feeds the level 1 cache
- Runs at half the multiplied clock speed
Level 3 cache:
- Megabytes of RAM
- runs at base motherboard speed, littel faster than the RAM itself to prevent stalling
Set association
Defines efficiency of the different kinds of caches
4-way
8-way
12-way
CPU Sockets
Package for CPU
The mount where a CPU connects to the motherboard
PGA(Pin Grid Array): for cpu with pins
LGA(Land Grid Array):for cpu without pins, the socket has pins
Family names
Micro Architecture Design:
1st Gen: Nehalem 2nd Gen: Sandy Bridge 3rd Gen: Ivy Bridge 4th Gen: Haswell 5th Gen: Broadwell 6th Gen: Skylake 7th Gen: Kaby Lake 8th Gen: Coffee Lake
A single Micro Architecture will have different models
i3, i5,i7,i9
New types of cpus require new types of sockets
Why is it important to know the micro-architecture (family name) of a CPU?
To ensure it fits the socket on the mother board
Intel cpu designation
Intel
I7 - 5820K
Model: i7;
Generation: 5
SKU: 820
K: (alpha suffix)
AMD
AMD Ryzen 7 2700X
Brand: Ryzen market Segment: 7 Generation: 2 Performance Level: 7 Model number: 00 Power suffix: X
Comon Cpu socket:
INTEL:
LGA1150:Core i3/i5/i7, Pentium, Celeron, Xeon
LGA1151 (mainstream) Core i3/i5/i7, Pentium, Celeron, Xeon
LGA2011: Core i7, Core i7 extreme edition, Xeon
LGA2066 (higher-end cpus): Core i5/i7/i9, Xeon
AMD:
FM2: A-series
AM3 FX, Opteron
AM4 (mainstream): Ryzen, A-Series
TR4 (High end), Ryzen Thread Ripper
Can you interchange between AMD and Intel?
No
When buying a mother board, what should you look at?
Socket type: Does it match the CPU
Speed: How fast of a CPU can this motherboard handle
Orientation notch
notches on the cpu chip that tells you its orientation
OEM CPU
CPUs you buy in bulk not in retail package
installing new cpu
- open socket
- check orientation notches
- check that it is flush
- close socket
- apply thermal paste
- Add heatsink and fan
- connect the fan to motherboard on CPU-fan connector
Liquid cooling system
a closed-loop system, the hot liquid is moved towards the radiator and fans, by a pump, where it is cooled, and the cool liquid moved over the CPU
Benefits of liquid cooling systems
low noise
more effective
When an instruction is sent to the CPU in a binary pattern, how does the CPU know what instruction the pattern means?
Code book
The CPU has an internal code book that identifies each instruction pattern. A register is a memory location inside a CPU. The external data bus is the set of wires that carry data and instructions between the CPU and RAM. In this context, translator is a made-up term.
What is the design foundation on which families of CPUs are built?
a. ) Microarchitecture
b. ) Machine Language
c. ) Binary
d. ) System crystal
MicroArchitecture
Microarchitecture is the underlying circuitry at the core of the CPU. Machine language is the binary format for instructions sent to the CPU. Binary describes the two states that electrical pulses to the CPU can represent. The system crystal provides clock pulses to the CPU.
How does a CPU increase the speed of the system clock?
a. ) Hyperthreading
b. ) OverClocking
c. ) Internal crystals
d. ) Clock multipliers
d.) Clock multipliers
There are clock multipliers inside a CPU that multiply the number of pulses sent by the system crystal. Overclocking uses multipliers and other techniques to run the internal speeds higher than the design specifications. It could be a right answer but is not the BEST answer. There are no internal crystals inside the CPU.
Which type of memory inside a CPU is the slowest?
a. ) Register
b. ) L1
c. ) L2
d. ) L3
d.) L3
L3 is the slowest memory inside a CPU. L2 is faster than L3 and L1 is faster than L2. System RAM is slower than all of these, but it is not inside the CPU.
Which is a common Intel socket?
a. ) 1151
b. ) AM4
c. ) TR4
d. ) AM3
a.)1151
1151 is a common Intel socket. Intel sockets usually are numbered whereas AMD sockets tend to have letters and/or letters and numbers.
When installing a CPU, protect it with what?
a. ) Antistatic wrist strap
b. ) OEM Fan
c. ) Thermal Paste
d. ) Orientation notch
a.) antistatic wrist strap
External databus
The external data bus connects the processor to adapters, the keyboard, the mouse, the hard drive, and other devices. An external data bus is also known as an external data path. You can see the external data lines by looking between the expansion slots on the motherboard
Fetch, Decode, Execute Cycle
Fetch
- The Instruction Address register increments by one
- The instruction is read from the ram into the instruction register
Decode
- The control unit reads the instruction from the instruction register and determine and compares it to the instruction table to determin what to do with the value attached to the opcode.
Execute
- The value is then moved to the appropriate register in accordance with the specified instruction or passed to the alu or written back to the RAM
Common problems with overclocking
- Overheating
- data signals fall behind the clock speed which produces gibberish
- Increased power consumption, which can be a problem for laptops
What is the purpose of the system clock
The system clock is a device used in computers which regulates the internal components of the computer by issuing a high-frequency signal. This signal ensures that all components are synchronized.
How to overclock a system
overclock CPUs by
telling the clock chip to multiply the pulse faster than the CPU’s designed
speed
- Increase the bus speed fo rthe system
- increase voltage going into the CPU (to provide stabillity)
Bits and Bytes
- Any individual 1 or 0 = a bit
- 4 bits = a nibble
- 8 bits = a byte
- 16 bits = a word
- 32 bits = a double word
- 64 bits = a paragraph or quad word
Difference between SRAM and DRAM
SRAM
Static random-access memory (static RAM or SRAM) is a type of random-access memory (RAM) that uses latching circuitry (flip-flop) to store each bit. SRAM is volatile memory; data is lost when power is removed.
DRAM
DRAM uses capacitors that lose charge over time due to leakage, even if the supply voltage is maintained. Since the charge on a capacitor decays when a voltage is removed, DRAM must be supplied with a voltage to retain memory (and is thus volatile). Capacitors can lose their charge a bit even when supplied with voltage if they have devices nearby (like transistors) that draw a little current even if they are in an “off” state; this is called capacitor leakage. Due to capacitor leakage, DRAM needs to be refreshed often.
CPU’s in mobile devices
The ever-growing selection of mobile devices, such as the Apple iPhone and iPad and most Android devices, use a CPU architecture
developed by ARM Holdings, called ARM. ARM-based processors use a simpler, more energy-efficient design, the reduced instruction set computing
(RISC) architecture. They can’T match the raw power of the Intel and AMD complex instruction set computing (CISC) chips, but the savings in cost and battery life make ARM-based processors ideal for mobile devices. (Note that
the clear distinction between RISC and CISC processors has blurred. Each design today borrows features of the other design to increase efficiency.)
ARM Holdings designs ARM CPUs, but doesn’t manufacture them. Many other companies—most notably, Qualcomm—license the design and manufacture their own versions.
Intel Product lines
Enthusiast: Core i7/i9
Mainstream: Core i7/i5/i3
Budget: Pentium, Celeron
Server: Xeon
Workstation: xeon
How are xeons different from core in the Intel line?
Error Correcting Code (ECC)
Xeon CPUs tend to have a lot more built-in, business-critical technology. For example, they support error-correcting code (ECC) memory, which prevents data corruption and system crashes. ECC RAM is also more expensive and slower, so few home users find the trade-off worth it, as home PCs are pretty reliable.
UPTIME
For businesses where uptime is mission-critical, even a few hours can cost far more than ECC memory is worth. Take financial trading, for example, where transactions happen faster than humans can understand. When computers go down, or data gets messed up, that’s a lot of lost money for these firms, which is why they’re willing to invest in specialized technologies.
RAM
Xeon processors also support far more RAM than Core chips do,
PCLe lanes
as well as heaps of PCIe lanes for connecting expansion cards.
CORES
XEON Typically offers more cores, like the 28-core, 56-thread Xeon W-3275M
SPEED
Typically xeon cpu’s are slower than core cpu’s
POWER
Where Xeon rules are power draw and heat generation—and not in a good way. Xeon chips are far more power-hungry and get a lot hotter. The 28-core, 56-thread Xeon W-3275M, for example, has a thermal design power (TDP) of 205 watts, and the W-3223 has a TDP of 160 watts. The i9-9900K, meanwhile, has a TDP of 95 watts.
cpu cores
Each core is a processing unit
The CPU split up the work into individual Cores
How to determine the speed of cpu?
MHz
Threads
Instructions per cycle (IPC)
Watts
Difference between 32 and 64 bit processer
64 bit processer can process 64 bits at a time
It determines the number of bit locations in RAM that the processor can access
Paralization
A microarchitecture design that runs the fetch, decode, execute cycle in parallel, instead of consecutively, speeding up processing
while the previous decode opporation is still running the cpu starts the fetch process of the next FDE cycle
This is possible beause each part of the FDE cycle uses a different part of the cpu.
Archetitures that speed up CPUs
Paralization
Out of order execution (identifying dependencies and reorganizing instructions)
Cache
SuperScalar
Multiple cores
AMD product lines
Enthusiast: Ryzen, Ryzen Threadripper
Mainstream: A-Series Pro, Ryzen
Budget: A-Series, FX
Portable/Mobile: Ryzen, A-Series
Server: Opteron, EPYC
Workstation: Ryzen PRO, Ryzen Threadripper
Throttling
Cpu’s running at lower spead when demand is low
Thermal throttling
Because most portable and mobile computing devices are very compact, they
can’t dissipate heat as quickly as a well-cooled desktop system. Mobile CPUs can scale up to handle demanding tasks, but they’ll start accumulating heat
quickly. As this heat nears levels that could damage the CPU, it will engage in thermal throttling to protect itself. A system trying to do demanding work
with only a fraction of its full power available may grind to a halt!
TDP
Thermal Design Power
Describes how much heat a cpu generates
The TDP can give you a rough idea of how much energy a CPU draws and what kind of cooling it will need. It can also help you select more efficient CPUs
How many instructions are required to move commands from the EDB through the cpu back to the EDB
- Fetch Get the data from the EDB.
- Decode Figure out what type of command needs to be executed.
- Execute Perform the calculation.
- Write Send the data back onto the EDB.
Wait states
Pipeline stalls
When cpu runs faster than RAM can supply it
Multicore processor
A dual-core CPU has two execution units—two sets of pipelines—but the two sets of pipelines share
caches and RAM. A single-core CPU has only one set of everything. Today, multicore CPUs—with four, six, or eight cores—are common.
Higher-end CPUs have up to 32 cores! With each generation of multicore CPU, both Intel and AMD have tinkered with the mixture of how to allocate the cache among the cores
How does multicore processing and multi-threading differ?
Hyperthreading requires OS and applications to be written in a way that can take advantage of the multi-threading capabillity.
multicore processing divides up work independently from the OS
IMC
Integrated memory controller
To optimize flow of information into and out of CPU.
Enables faster control over L3 cache shared amongst cores
IGPU
Integrated Graphics Processing Unit
GPU integrated into CPU
Enhances overall performance of PC, while reducing energy consumption, size, and cost
Which CPU’s does Xbox and Playstation use?
AMD APU
The Accelerated Processing Unit contains an integrated GPU.
CPU security
CPU’s employ NX bit technology that enables the CPU to protect certain sections of memory. This feature, coupled with
implementation by the operating system, stops malicious attacks from getting to essential operating system files.
Called:
Microsoft: Data Execution Prevention
INTEL: XD bit (execute disable)
AMD: Enhanced Virus Protection
ARM: Execute Never
Zero insertion force sockets
zero insertion force (ZIF) sockets, which means
you never have to use any force at all.
Active and Passive Cooling
A heat sink by itself (no fan) on a chip provides passive cooling. A heat sink and fan combination provide active cooling. You’ll sometimes hear the latter described as an active heat sink
Heat sink
A heat sink is a copper or other metal device designed to dissipate heat from whatever it touches
OEM CPU cooler
Original equipment manufacturer heatsink and fan assemblies are included with boxed cpu
Fanless cooling
Systems that have no fans, usually passive cooling
Consequences of overclocking
- Void warranties
- Burnout CPU
- System malfunction
Clearing the CMOS Jumper to reset BIOS
- Power off the system.
- Open up the system so you can see the motherboard.
- Locate the CMOS jumper by referring to the motherboard manual and how to clear the CMOS. In general, the CMOS jumper is three pins located near the battery.
- In general, CMOS jumper has positions 1–2 and 2–3. Move the jumper from the default position 1–2 to position 2–3 to clear CMOS. Wait 1–5 minutes then move it back to the default position.
- Power on the system. In some systems, you might need to enter BIOS to reset to the factory defaults.
Symptoms of overheating and troubleshooting
Symptoms:
- Computer running slow
- Computer constantly shutting down
- Automatic Restarts
- proprietary crash screens (Blue Screen Of Death, PinWheel)
- Black Screen, Acompanied by smoke, smell of burned electronics or ozone
if it is a new installation, it is likely a faulty Heatsink and fan installation
The fan and heat-sink installation failures can be tricky the first few times you encounter them. You might see the text from the system setup. You might even get into an installation of Windows before the crash happens. The
key is that as soon as you put the CPU under load—that is, make it work for a
living—it heats up beyond where the faulty heat-sink connection can dissipate the heat and then shuts down.
- Too much thermal paste can impede the flow of heat from the CPU to
the heat sink and cause the CPU to heat up rapidly. All modern CPUs
have built-in fail-safes that tell them to shut down before getting
damaged by heat. - Not enough thermal paste or thermal paste spread unevenly can cause
the CPU to heat up and consequently shut itself down. - Failure to connect the fan power to the motherboard can cause the
CPU to heat up and shut itself down.
If it is a system that has been running for a while, it is likely an environmental issue
- Office Aircon
- Room temperature
- Clogged up fan
- intake and exhaust vents are clogged
Intel Core M
The Intel Core M runs cool and sips juice for incredibly long battery life in mobile devices. The official TDP is just 4.5 watts—compared to a mobile version of a Core i7 that demands 57 watts. The trade-off Intel makes with the Core M is in raw processing power. It’s a little less powerful than a mobile Core i3—enough to get the job done, but not enough to run a serious game or other demanding application. On the other hand, the incredibly low
electricity
Two categories of CPU Problems
- Catastrophic failure
2. OverHeating
What do register provide for the CPU?
A. Registers determine the clock speed.
B. The CPU uses registers for temporary storage of internal commands and data.
C. Registers enable the CPU to address RAM.
D. Registers enable the CPU to control the address bus.
B. The CPU uses registers for temporary storage of internal commands and data.
What function does the external data bus have in the PC?
A. The external data bus determines the clock speed for the CPU.
B. The CPU uses the external data bus to address RAM.
C. The external data bus provides a channel for the flow of data and
commands between the CPU and RAM.
D. The CPU uses the external data bus to access registers.
C. The external data bus provides a channel for the flow of data and
commands between the CPU and RAM.
- What is the function of the address bus in the PC?
A. The address bus enables the CPU to communicate with the
memory controller chip.
B. The address bus enables the memory controller chip to
communicate with the RAM.
C. The address bus provides a channel for the flow of data and
commands between the CPU and RAM.
D. The address bus enables the CPU to access registers
A. The address bus enables the CPU to communicate with the
memory controller chip.
- Which of the following terms are measures of CPU speed?
A. Megahertz and gigahertz
B. Megabytes and gigabytes
C. Megahertz and gigabytes
D. Frontside bus, backside bus
A. Megahertz and gigahertz
Which CPU feature enables the microprocessor to support running
multiple operating systems at the same time?
A. Clock multiplying
B. Caching
C. Pipelining
D. Virtualization support
D. Virtualization support
Into which socket could you place an Intel Core i5? A. Socket LGA 2011 B. Socket LGA 1151 C. Socket C D. Socket AM3+
B. Socket LGA 1151
You’ll find Core i5 processors in several socket types, notably
LGA 1150 and LGA 1151.
- Which feature enables a single-core CPU to function like two CPUs?
A. Hyper-Threading
B. SpeedStep
C. Virtualization
D. x64
A. Hyper-Threading
- What steps do you need to take to install a Core i3 CPU into an FM2+
motherboard?
A. Lift the ZIF socket arm; place the CPU according to the
orientation markings; snap on the heat-sink and fan assembly.
B. Lift the ZIF socket arm; place the CPU according to the
orientation markings; add a dash of thermal paste; snap on the
heat-sink and fan assembly.
C. Lift the ZIF socket arm; place the CPU according to the
orientation markings; snap on the heat-sink and fan assembly;
plug in the fan.
D. Take all of the steps you want to take because it’s not going to work.
D. Take all of the steps you want to take because it’s not going to work. Intel and AMD processors are not compatible at all.
- A client calls to complain that his computer starts up, but crashes when Windows starts to load. After a brief set of questions, you find out that his nephew upgraded his RAM for him over the weekend and
couldn’t get the computer to work right afterward. What could be the problem?
A. Thermal paste degradation B. Disconnected CPU fan C. Bad CPU cache D. There’s nothing wrong. It usually takes a couple of days for RAM to acclimate to the new system.
B. Most likely, the nephew disconnected the CPU fan to get at the RAM slots and simply forgot to plug it back in.
Darren has installed a new CPU in a client’s computer, but nothing
happens when he pushes the power button on the case. The LED on the motherboard is lit up, so he knows the system has power. What
could the problem be?
A. He forgot to disconnect the CPU fan.
B. He forgot to apply thermal paste between the CPU and the heatsink and fan assembly.
C. He used an AMD CPU in an Intel motherboard.
D. He used an Intel CPU in an AMD motherboard.
B. The best answer here is that he forgot the thermal paste, though you can also make an argument for a disconnected fan.
