Register renaming - Revision history

Jnc: Clarify

2026-09-29T10:53:07Z

Clarify

← Older revision		Revision as of 10:53, 29 September 2026
Line 1:		Line 1:
	'''Register renaming''' is a technique used in the implementation of [[superscalar]] [[Central Processing Unit\|processors]], particularly in those using [[out-of-order execution]], to avoid 'stalls' caused by conflicts over [[register]] usage.		'''Register renaming''' is a technique used in the implementation of [[superscalar]] [[Central Processing Unit\|processors]], particularly in those using [[out-of-order execution]], to avoid 'stalls' caused by conflicts over [[general register]] usage.

	When an [[instruction]] wants to store its result in a register, the old contents of which some prior instruction (in [[program]] ~~terms, not~~ [[execute\|execution]] time terms) needs to use as an input, ~~the first~~ instruction cannot complete until the ~~second~~ has started. If the first instruction instead places its output in another, 'hidden' internal register, the conflict can be avoided. Later references to the output of the first instruction will of course have to use the value in the hidden internal register - this is the renaming.		When an [[instruction]] wants to store its result in a register, the old contents of which some prior instruction ('prior' in [[program]] logical [[execute\|execution]] terms, not actual, re-ordered, execution time terms) needs to use as an input, that instruction cannot complete until the other one has started. If the first instruction instead places its output in another, 'hidden' internal register, the conflict can be avoided. Later references to the output of the first instruction will of course have to use the value in the hidden internal register - this is the renaming.

	One cause of this is the fact that due to the fixed [[word]] size used for an [[instruction set]], not many bits are available to name registers, but modern processors can have a lot of registers, more than can be named in the instructions - use of these keeps the data in the CPU, where it is quickly accessible. Register renaming is however needed to make use of them.		One cause of this is the fact that due to the fixed [[word]] size used for an [[instruction set]], not many bits are available to name registers, but modern processors can have a lot of registers, more than can be named in the instructions - use of these keeps the data in the CPU, where it is quickly accessible. Register renaming is however needed to make use of them.

Jnc: better cat

2018-12-15T14:05:02Z

better cat

← Older revision		Revision as of 14:05, 15 December 2018
Line 7:		Line 7:
	{{semi-stub}}		{{semi-stub}}

	[[Category: CPU ~~Basics‎‎~~]]		[[Category: CPU Hardware]]
	`

Jnc: better cat

2018-12-14T21:57:33Z

better cat

← Older revision		Revision as of 21:57, 14 December 2018
Line 7:		Line 7:
	{{semi-stub}}		{{semi-stub}}

	[[Category: ~~Hardware~~ Basics‎‎]]		[[Category: CPU Basics‎‎]]
			`

Jnc: +cat

2018-12-13T03:12:57Z

+cat

← Older revision		Revision as of 03:12, 13 December 2018
Line 6:		Line 6:

	{{semi-stub}}		{{semi-stub}}

			[[Category: Hardware Basics‎‎]]

Jnc: typos

2018-12-05T19:37:36Z

typos

← Older revision		Revision as of 19:37, 5 December 2018
Line 1:		Line 1:
	'''Register renaming''' is a technique used in the implementation of [[superscalar]] [[Central Processing Unit\|processors]], particularly in those using [[out-of-order execution]], to avoid 'stalls' caused by conflicts over register usage.		'''Register renaming''' is a technique used in the implementation of [[superscalar]] [[Central Processing Unit\|processors]], particularly in those using [[out-of-order execution]], to avoid 'stalls' caused by conflicts over [[register]] usage.

	When an [[instruction]] wants to store its result in a [[register]], the old contents of which some prior (in [[program]] terms, not [[execute\|execution]] terms) needs to use as an input, the first instruction cannot complete until the second has started. If the first instruction instead places its output in another, 'hidden' internal register, the conflict can be avoided. Later references to the output of the first instruction will of course have to use the value in the hidden internal register - this is the renaming.		When an [[instruction]] wants to store its result in a register, the old contents of which some prior instruction (in [[program]] terms, not [[execute\|execution]] time terms) needs to use as an input, the first instruction cannot complete until the second has started. If the first instruction instead places its output in another, 'hidden' internal register, the conflict can be avoided. Later references to the output of the first instruction will of course have to use the value in the hidden internal register - this is the renaming.

	One cause of this is the fact that due to the fixed [[word]] size used for an [[instruction set]], not many bits are available to name registers, but modern processors can have a lot of registers, more than can be named in the instructions - use of these keeps the data in the CPU, where it is quickly accessible. Register renaming is however needed to make use of them.		One cause of this is the fact that due to the fixed [[word]] size used for an [[instruction set]], not many bits are available to name registers, but modern processors can have a lot of registers, more than can be named in the instructions - use of these keeps the data in the CPU, where it is quickly accessible. Register renaming is however needed to make use of them.

	{{semi-stub}}		{{semi-stub}}
	\

Jnc: A pretty good start

2018-12-05T16:19:46Z

A pretty good start

New page

'''Register renaming''' is a technique used in the implementation of [[superscalar]] [[Central Processing Unit|processors]], particularly in those using [[out-of-order execution]], to avoid 'stalls' caused by conflicts over register usage.

When an [[instruction]] wants to store its result in a [[register]], the old contents of which some prior (in [[program]] terms, not [[execute|execution]] terms) needs to use as an input, the first instruction cannot complete until the second has started. If the first instruction instead places its output in another, 'hidden' internal register, the conflict can be avoided. Later references to the output of the first instruction will of course have to use the value in the hidden internal register - this is the renaming.

One cause of this is the fact that due to the fixed [[word]] size used for an [[instruction set]], not many bits are available to name registers, but modern processors can have a lot of registers, more than can be named in the instructions - use of these keeps the data in the CPU, where it is quickly accessible. Register renaming is however needed to make use of them.

{{semi-stub}}
\