Scribd
Upload
8 views13 pages

Lecture Slides 07 074-Caches-Org

The document discusses cache organization, including the principles of locality, memory hierarchies, and program optimizations that consider caches. It explains how data is mapped to cache using indices and tags, the concept of cache blocks, and the challenges associated with direct-mapped caches. Additionally, it covers associativity in caches and strategies for block replacement, emphasizing the importance of efficient data storage and retrieval in computer memory systems.

Uploaded by

yihuangece
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
8 views13 pages

Lecture Slides 07 074-Caches-Org

The document discusses cache organization, including the principles of locality, memory hierarchies, and program optimizations that consider caches. It explains how data is mapped to cache using indices and tags, the concept of cache blocks, and the challenges associated with direct-mapped caches. Additionally, it covers associativity in caches and strategies for block replacement, emphasizing the importance of efficient data storage and retrieval in computer memory systems.

Uploaded by

yihuangece
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 13

University

 of  Washington  

Sec3on  7:  Memory  and  Caches  


¢ Cache  basics  
¢ Principle  of  locality  
¢ Memory  hierarchies  
¢ Cache  organiza3on  
¢ Program  op3miza3ons  that  consider  caches  
 

Cache  Organiza3on  
University  of  Washington  

Where should we put data in the cache?  


Memory Cache
0000
0001
0010
0011
0100
0101 Index Data
0110 00
0111 01
1000 10
1001 11
1010
1011
1100
1101
1110
1111
¢ How can we compute this mapping?
Cache  Organiza3on  
University  of  Washington  

Where should we put data in the cache?  


Memory Cache
0000
0001
0010
0011
0100
0101 Index Data
0110 00
0111 01
1000 10
1001 11
1010
1011
1100
1101
1110 Hmm.. The cache might get confused later!
1111
Why? And how do we solve that?
Cache  Organiza3on  
University  of  Washington  

Use  tags!  
Memory Cache
0000
0001
0010
0011
0100
0101 Index Tag Data
0110 00 00
0111 01 ??
1000 10 01
1001 11 01
1010
1011
1100
1101
1110
1111

Cache  Organiza3on  
University  of  Washington  

What’s  a  cache  block?  (or  cache  line)  


Byte Block (line)
Address number
0 0
1
2 1
3
4 2 Index
5
6 0
3
7 1
8 2
4
9 3
10 5
11
12 6
13
14 7
15

Cache  Organiza3on  
University  of  Washington  

A  puzzle.  
¢ What  can  you  infer  from  this:  

¢ Cache  starts  empty  


¢ Access  (addr,  hit/miss)  stream  
¢ (10,  miss),  (11,  hit),  (12,  miss)  

Cache  Organiza3on  
University  of  Washington  

Problems with direct mapped caches?


¢ What happens if a Memory
Address
program uses addresses
0000
2, 6, 2, 6, 2, …? 0001
0010
0011
0100 Index
0101
0110 00
0111 01
1000 10
1001 11
1010
1011
1100
1101
1110
1111

Cache  Organiza3on  
University  of  Washington  

Associa3vity  
¢ What  if  we  could  store  data  in  any  place  in  the  cache?  
¢ But  that  might  slow  down  caches…  so  we  do  something  in  
between.  
1-way 2-way 4-way 8-way
8 sets, 4 sets, 2 sets, 1 set,
1 block each 2 blocks each 4 blocks each 8 blocks

Set Set Set Set


0
1 0
2 0
1
3
0
4
2
5 1
6 3
7

direct mapped fully associative

Cache  Organiza3on  
University  of  Washington  

But  now  how  do  I  know  where  data  goes?  

(m-k-n) bits k bits


n-bit Block
m-bit Address Tag Index Offset

Our example used a 22-block cache with 21 bytes per


block. Where would 13 (1101) be stored?

? bits ? bits
?-bits Block
4-bit Address Offset

Cache  Organiza3on  
University  of  Washington  

Example placement in set-associative caches


¢ Where would data from address 0x1833 be placed?
§ Block size is 16 bytes.
¢ 0x1833in binary is 00...0110000 011 0011.

(m-k-n) bits k bits


n-bit Block
m-bit Address Tag Index Offset

k=? k=? k=?

1-way associativity 2-way associativity 4-way associativity


8 sets, 1 block each 4 sets, 2 blocks each 2 sets, 4 blocks each

Set Set Set


0
1 0
2 0
1
3
4
2
5 1
6 3
7
Cache  Organiza3on  
University  of  Washington  

Example placement in set-associative caches

¢ Where would data from address 0x1833 be placed?


§ Block size is 16 bytes.
¢ 0x1833in binary is 00...0110000 011 0011.
(m-k-4) bits k bits
4-bit Block
m-bit Address Tag Index Offset

k=3 k=2 k=1


1-way associativity 2-way associativity 4-way associativity
8 sets, 1 block each 4 sets, 2 blocks each 2 sets, 4 blocks each

Set Set Set


0
1 0
2 0
1
3
4
2
5 1
6 3
7

Cache  Organiza3on  
University  of  Washington  

Block replacement
¢ Any empty block in the correct set may be used for storing data.
¢ If there are no empty blocks, which one should we replace?
¢ Replace something, of course, but what?
§ Caches typically use something close to least-recently-used

1-way associativity 2-way associativity 4-way associativity


8 sets, 1 block each 4 sets, 2 blocks each 2 sets, 4 blocks each

Set Set Set


0
1 0
2 0
1
3
4
2
5 1
6 3
7

Cache  Organiza3on  
University  of  Washington  

Another  puzzle.  
¢ What  can  you  infer  from  this:  

¢ Cache  starts  empty  


¢ Access  (addr,  hit/miss)  stream  
¢ (10,  miss);  (12,  miss);  (10,  miss)  

Cache  Organiza3on  

You might also like