Memory timing - Revision history

Rice: /* Cache */

2024-06-05T15:25:33Z

Cache

← Older revision		Revision as of 15:25, 5 June 2024
Line 25:		Line 25:
	'''Compulsory misses''' cannot be prevented. '''Conflict misses''' happen when there is already another loaded thing in the cache blocking a new item.		'''Compulsory misses''' cannot be prevented. '''Conflict misses''' happen when there is already another loaded thing in the cache blocking a new item.

	To implement spatial locality, increase the block size to multiple words and use a block offset to select between them. This way, surrounding words are loaded in.		To implement spatial locality to reduce compulsory misses, increase the block size to multiple words and use a block offset to select between them. This way, surrounding words are loaded in.

Rice: /* Cache */

2024-06-05T15:15:25Z

Cache

← Older revision		Revision as of 15:15, 5 June 2024
Line 24:		Line 24:

	'''Compulsory misses''' cannot be prevented. '''Conflict misses''' happen when there is already another loaded thing in the cache blocking a new item.		'''Compulsory misses''' cannot be prevented. '''Conflict misses''' happen when there is already another loaded thing in the cache blocking a new item.

			To implement spatial locality, increase the block size to multiple words and use a block offset to select between them. This way, surrounding words are loaded in.

Rice: /* Cache */

2024-06-03T15:40:06Z

Cache

← Older revision		Revision as of 15:40, 3 June 2024
Line 23:		Line 23:
	The '''tag''' is used to detect misses.		The '''tag''' is used to detect misses.

	'''Compulsory misses''' cannot be prevented.		'''Compulsory misses''' cannot be prevented. '''Conflict misses''' happen when there is already another loaded thing in the cache blocking a new item.

Rice at 15:38, 3 June 2024

2024-06-03T15:38:42Z

← Older revision		Revision as of 15:38, 3 June 2024
Line 12:		Line 12:

	Note that if memory is not in main, it must be in virtual		Note that if memory is not in main, it must be in virtual

			= Cache =
			Fastest, ideally predict the future to put needed stuff into the cache using spatial and temporal locality.

			A cache is organized into S sets, each address mapping to exactly one set.
			* Direct mapped: 1 block per set
			* N-way set associative: N blocks per set
			* Fully associative: all cache blocks in 1 set

			The '''tag''' is used to detect misses.

			'''Compulsory misses''' cannot be prevented.

Rice: Rice moved page Cache to Memory timing

2024-06-03T15:25:30Z

Rice moved page Cache to Memory timing

← Older revision		Revision as of 15:25, 3 June 2024
(No difference)

Rice: Rice moved page Locality to Cache

2024-06-03T15:25:18Z

Rice moved page Locality to Cache

← Older revision		Revision as of 15:25, 3 June 2024
(No difference)

Rice: /* Average memory access time */

2024-06-03T15:22:45Z

Average memory access time

← Older revision		Revision as of 15:22, 3 June 2024
Line 10:		Line 10:
	AMAT=t_{cache}+MR_{cache}[t_{MM}+MR_{MM}(t_{VM})]		AMAT=t_{cache}+MR_{cache}[t_{MM}+MR_{MM}(t_{VM})]
	</math>		</math>

			Note that if memory is not in main, it must be in virtual

Rice: Created page with "Keep recently accessed data in higher levels of memory hierarchy (i.e. use better memory). = Hit or miss = '''Hit''' is when data is found in that level of memory hierarchy. '''Miss''' is the complement. = Average memory access time = $AMAT=t_{cache}+MR_{cache}[t_{MM}+MR_{MM}(t_{VM})]$ "

2024-06-03T15:20:29Z

Created page with "Keep recently accessed data in higher levels of memory hierarchy (i.e. use better memory). = Hit or miss = '''Hit''' is when data is found in that level of memory hierarchy. '''Miss''' is the complement. = Average memory access time = <math> AMAT=t_{cache}+MR_{cache}[t_{MM}+MR_{MM}(t_{VM})] </math>"

New page

Keep recently accessed data in higher levels of memory hierarchy (i.e. use better memory).

= Hit or miss =

'''Hit''' is when data is found in that level of memory hierarchy. '''Miss''' is the complement.

= Average memory access time =

<math>
AMAT=t_{cache}+MR_{cache}[t_{MM}+MR_{MM}(t_{VM})]
</math>