Hot spot (computer programming): Difference between revisions

Revision as of 13:40, 15 April 2009

Revision as of 18:06, 26 May 2009

Line 1:

{{Unreferencedrefimprove|date=MarchMay 2009}}

The most usual definition of aA '''hot spot''' in [[computer science]] is most usually defined as a region of a [[computer program]] where thea highesthigh numberproportion of executed instructions occursoccur or where most time is spent during the programsprogram's execution (not necessarily the same thing since some instructions are faster than others).

==Definition==

The most usual definition of a hot spot in [[computer science]] is a region of a [[computer program]] where the highest number of executed instructions occurs or where most time is spent during the programs execution (not necessarily the same thing since some instructions are faster than others).

If a program is stopped randomly, the [[program counter]] (the [[Pointer (computing)|pointer]] to the next instruction to be executed) is frequently found to contain the address of an instruction within a certain range, possibly indicating code that is in need of optimization or even indicating the existence of a 'tight' [[CPU]] [[control flow#Loops|loop]]. See [[Performance analysis]]. This simple technique can actually be used as a method of detecting instructionshighly thatused are high usage,instructions although somewhat more sophisticated methods, such as [[instruction set simulator]]s or [[Performance analysis|performance analyzer]]s, achieve this more accurately and consistently.

===History of hot spot detection===

RenownedThe [[computer science|computer scientist]] [[Donald Knuth]] described his first encounter with what he refers to as a ''jump trace'' in an interview for "''[[Dr. Dobb's Journal]]"'' in 1996, saying:

<blockquote>In the [[1960s|'60s]], someone invented the concept of a 'jump trace'. This was a way of altering the [[machine code|machine language]] of a program so it would change the next branch or [[jump instruction]] to retain control, so you could execute the program at fairly high speed instead of interpreting each instruction one at a time and record in a file just where a program diverged from sequentiality. By processing this file you could figure out where the program was spending most of its time. So the first day we had this software running, we applied it to our [[Fortran]] [[compiler]] supplied by, I suppose it was in those days, [[Control Data Corporation]]. We found out it was spending 87 percent of its time reading [[Comment (computer programming)|comments]]! The reason was that it was translating from one code system into another into another."<ref>[http://www.ntg.nl/maps/16/14.pdf Jack Woehr: An interview with Donald Knuth, April 1996.]</ref></blockquote>

[http://www.ntg.nl/maps/16/14.pdf] saying: <blockquote> "..... In the ’[[1960's|60]]s, someone invented the concept

of a ‘jump trace.’ This was a way of altering the [[machine code|machine

language]] of a program so it would change the next branch or [[jump instruction]] to retain control, so you could execute the program at fairly high speed instead of interpreting each instruction one at a time and record in a file

just where a program diverged from sequentiality. By processing this file you could figure out where the program was spending most of its time. So the first day we had this software running, we applied it to our [[Fortran]] [[compiler]] supplied by, I suppose it was in those days, [[Control Data Corporation]]. We found out it was spending 87 percent of its time reading [[Comment (computer programming)|comments]]! The reason was that it was translating from one code system into another into another."</blockquote>

==See also==

[[Algorithmic efficiency#Hot spot analyzers|Hot spot analyzers]]<br>

[[Performance analysis]]

==References==