CHAPTER 6: Memory Hierarchy

Question 1

temporal locality

Answer 1

locality principle stating that if a data location is referenced then it will tend to be referenced again soon

Question 2

spatial locality

Answer 2

locality principle stating that if a data location is referenced, data locations with nearby addresses will tend to be referenced soon

Question 3

memory hierarchy

Answer 3

structure that uses multiple levels of memories; as the distance from the processor increases, the size of the memories and the access time both increase

Question 4

block (line)

Answer 4

minimum unit of information that can be either present or not present in a cache

Question 5

hit rate

Answer 5

fraction of memory accesses found in a level of the memory hierarchy

Question 6

miss rate

Answer 6

fraction of memory accesses not found in a level of the memory hierarchy

Question 7

hit time

Answer 7

time required to access a level of the memory hierarchy, including the time needed to determine whether the access is a hit or a miss

Question 8

miss penalty

Answer 8

time required to fetch a block into a level of the memory hierarchy from the lower level, including the time to access the block, transmit it from one level to the other, insert it in the level that experienced the miss, and then pass the block to the requestor

Question 9

SRAM (static ram)

Answer 9

• memory arrays with (usually) a single access port that can provide either a read or a write - have a fixed access time to any datum, though the read and write access times may differ - don’t need to refresh and so the access time is very close to the cycle time - typically use six to eight transistors per bit to prevent the information from being disturbed when read

Question 10

DRAM (dynamic ram)

Answer 10

• value kept in a cell is stored as a charge in a capacitor - use only one transistor per bit of storage, they are much denser and cheaper - store the charge on a capacitor, it cannot be kept indefinitely and must periodically be refreshed - use a two-level decoding structure, and this allows us to refresh an entire row (which shares a word line) with a read cycle followed immediately by a write cycle

Question 11

seek

Answer 11

process of positioning a read/write head over the proper track on a disk

Question 12

direct-mapped cache

Answer 12

cache structure in which each memory location is mapped to exactly one location in the cache

Question 13

tag

Answer 13

field in a table used for a memory hierarchy that contains the address information required to identify whether the associated block in the hierarchy corresponds to a requested word

Question 14

valid bit

Answer 14

field in the tables of a memory hierarchy that indicates that the associated block in the hierarchy contains valid data

Question 15

cache miss

Answer 15

request for data from the cache that cannot be filled because the data are not present in the cache

Question 16

write-through

Answer 16

scheme in which writes always update both the cache and the next lower level of the memory hierarchy, ensuring that data are always consistent between the two.

Question 17

write buffer

Answer 17

queue that holds data while the data are waiting to be written to memory

Question 18

write-back

Answer 18

scheme that handles writes by updating values only to the block in the cache, then writing the modified block to the lower level of the hierarchy when the block is replaced

Question 19

split-cache

Answer 19

scheme in which a level of the memory hierarchy is composed of two independent caches that operate in parallel with each other, with one handling instructions and one handling data

Question 20

fully associative cache

Answer 20

cache structure in which a block can be placed in any location in the cache

Question 21

set-associative cache

Answer 21

cache that has a fixed number of locations (at least two) where each block can be placed

Question 22

multilevel cache

Answer 22

memory hierarchy with multiple levels of caches, rather than just a cache and main memory

Question 23

global miss rate

Answer 23

fraction of references that miss in all levels of a mutlilevel cache

Question 24

local miss rate

Answer 24

fraction of references to one level of a cache that miss; used in multilevel hierarchies

Question 25

error detection code

Answer 25

code that enables the detection of an error in data, but not the precise location and, hence, correction of the error

Question 26

virtual memory

Answer 26

technique that uses main memory as a "cache" for secondary storage

Question 27

protection

Answer 27

set of mechanisms for ensuring that multiple processes sharing the processor, memory, or I/O devices cannot interfere, intentionally or unintentionally, with one another by reading or writing each other's data. These mechanisms also isolate the operating system from a user process

Question 28

address translation (address mapping)

Answer 28

process by which a virtual address is mapped to an address used to access memory

Question 29

virtually addressed cache

Answer 29

cache that is accessed with a virtual address rather than a physical address

Question 30

aliasing

Answer 30

situation in which two addresses access the same object; it can occur in virtual memory when there are two virtual addresses for the same physical page

Question 31

physically address cache

Answer 31

cache that is addressed by a physical address

Question 32

exception enable (interrupt enable)

Answer 32

signal or action that controls whether the process responds to an exception or not; necessary for preventing the occurrence of exceptions during intervals before the processor has safely saved the state needed to restart

Question 33

restartable instruction

Answer 33

instruction that can resume execution after an exception is resolved without the exception's affecting the result of the instruction

Question 34

virtual memory

Answer 34

name for the level of memory hierarchy that manages caching between the main memory and secondary memory

Question 35

three Cs model

Answer 35

cache model in which all cache misses are classified into one of three categories: compulsory misses, capacity misses, and conflict misses

Question 36

compulsory miss (cold-start miss)

Answer 36

cache miss caused by the first access to a block that has never been in the cache

Question 37

capacity miss

Answer 37

cache miss that occurs because the cache, even with full associativity, cannot contain all the blocks needed to satisfy the request

Question 38

conflict miss (collision miss)

Answer 38

cache miss that occurs in a set-associative or direct-mapped cache when multiple blocks compete for the same set and that are eliminated in a fully associative cache of the same size

Question 39

finite-state machine

Answer 39

sequential logic function consisting of a set of inputs and outputs, a next-state function that maps the current state and the inputs to a new state, and an output function that maps the current state and possibly the inputs to a set of asserted outputs

Question 40

next-state machine

Answer 40

combinational function that, given the inputs and the current state, determines the next state of a finite-state machine

Question 41

false sharing

Answer 41

two unrelated shared variables are located in the same cache block and the full block is exchanged between processors even though the processors are accessing different variables

Question 42

redundancy arrays of inexpensive disks

Answer 42

organization of disks that uses an array of small and inexpensive disks so as to increase both performance and reliability

Question 43

raid 0

Answer 43

- striping across a set of disks makes the collection appear to software as a single large disk, which simplifies storage management - improves performance for large accesses, since many disks can operate at once - Video-editing systems, for example, frequently stripe their data and may not worry about dependability as much as, say, databases. - no redundancy

Question 44

striping

Answer 44

allocation of logically sequential blocks to separate disks to allow higher performance than a single disk can deliver

Question 45

raid 1

Answer 45

- data are written to one disk, those data are also written to a redundant disk, so that there are always two copies of the information - If a disk fails, the system just goes to the "mirror" and reads its contents to get the desired information - most expensive RAID solution, since it requires the most disks

Question 46

mirroring

Answer 46

writing identical data to multiple disks to increase data availability

Question 47

raid 3

Answer 47

- reads or writes go to all disks in the group, with one extra disk to hold the check information in case there is a failure - popular in applications with large data sets, such as multimedia and some scientific codes - bit-interleaved parity

Question 48

protection group

Answer 48

group of data disks or blocks that share a common check disk or block

Question 49

raid 4

Answer 49

- parity is stored as blocks and associated with a set of data blocks

Question 50

raid 5

Answer 50

- parity associated with each row of data blocks is no longer restricted to a single disk - distributed parity organization - organization allows multiple writes to occur simultaneously as long as the parity blocks are not located on the same disk

Question 51

raid 6

Answer 51

- P & Q redundancy - parity-based schemes protect against a single self-identifying failure - single failure correction is not sufficient, parity can be generalized to have a second calculation over the data and another check disk of information

Question 52

nonblocking cache

Answer 52

cache that allows the processor to make references to the cache while the cache is handling an earlier miss

Question 53

pitfall: ignoring memory system behavior when writing programs or when generating code in a compiler

Answer 53

programmers can easily double performance if they factor the behavior of the memory system into the design of their algorithms

Question 54

pitfall: forgetting to account for byte addressing or the cache block size in simulating a cache

Answer 54

catches many people, including the authors (in earlier drafts) and instructors who forget whether they intended the addresses to be in doublewords, words, bytes, or block numbers

Question 55

pitfall: having less set associativity for a shared cache than the number of cores or threads sharing that cache

Answer 55

programmers could face apparently mysterious performance bugs—actually due to L2 conflict misses—when migrating from, say, a 16-core design to 32-core design if both use 16-way associative L2 caches

Question 56

pitfall: using average memory access time to evaluate the memory hierarchy of an out-of-order processor

Answer 56

processor stalls during a cache miss, then you can separately calculate the memory-stall time and the processor execution time, and hence evaluate the memory hierarchy independently using average memory access time

Question 57

pitfall: extending an address space by adding segments on top of an unsegmented address space

Answer 57

adding segments can turn every address into two words—one for the segment number and one for the segment offset—causing problems in the use of addresses in registers

Question 58

fallacy: disk failure rates in the field match their specifications

Answer 58

- 100,000 disks that had quoted MTTF of 1,000,000 to 1,500,000 hours, or AFR of 0.6% to 0.8% - 100,000 disks at Google, which had a quoted AFR of about 1.5%, saw failure rates of 1.7% for drives in their first year rise to 8.6% for drives in their third year, or about five to six times the declared rate

Question 59

fallacy: operating systems are the best place to schedule disk accesses

Answer 59

- higher-level disk interfaces offer logical block addresses to the host operating system - the best an OS can do to try to help performance is to sort the logical block addresses into increasing order

Question 60

pitfall: implementing a virtual machine monitor on an instruction set architecture that wasn't designed to be virtualizable

Answer 60

make small changes to the operating system to avoid using the troublesome pieces of the architecture

Question 61

prefetching

Answer 61

technique in which data blocks needed in the future are brought into the cache early by using special instructions that specify the address of the block