Diff for "AmdahlsLaw" - Dr. A's Wiki

Differences between revisions 1 and 31 (spanning 30 versions)

<<latex( $S p e e d u p = \frac{P e r f o r m a n c e u s i n g e n h a n c e m e n t w h e n p o s s i b l e}{P e r f o r m a n c e w i t h o u t e n h a n c e m e n t}$ )>>

See SpeedUp

Notice that we are talking about the entire task here and that performance (speedup) is defined in terms of execution time! So we have to define the following:

<<latex( $S p e e d u p O v e r a l l = \frac{O l d E x e c u t i o n T i m e}{N e w E x e c u t i o n T i m e}$ )>> (1)

This gives a new Execution time of

<<latex( $N e w E x e c T i m e = O l d E x e c T i m e (1 - F r a c t i o n E n h a n c e d + \frac{F r a c t i o n E n h a n c e d}{S p e e d u p E n h a n c e d})$ )>>

So we have

<<latex( $S p e e d u p O v e r a l l = (\frac{1}{1 - F r a c t i o n E n h a n c e d + \frac{F r a c t i o n E n h a n c e d}{S p e e d u p E n h a n c e d}})$ )>>

Back to ComputerTerms

-  ⇤ ← Revision 1 as of 2004-01-25 18:20:24 → 
  Size: 301
  Editor: yakko
  Comment:
+   ← Revision 31 as of 2008-10-24 02:24:20 → ⇥
  Size: 720
  Editor: 209-142-131-35
  Comment:
-Deletions are marked like this.
+Additions are marked like this.
 Line 3:
-{{{
           Performance for entire task using the enhancement when possible
Speedup = -----------------------------------------------------------------
              Performance for entire taks without using the enhancement
}}}
+<<latex( $S p e e d u p = \frac{P e r f o r m a n c e u s i n g e n h a n c e m e n t w h e n p o s s i b l e}{P e r f o r m a n c e w i t h o u t e n h a n c e m e n t}$ )>>
-Line 11:
+Line 7:
+Notice that we are talking about the entire task here and that performance (speedup) is defined in terms of execution time! So we have to define the following:

<<latex( $S p e e d u p O v e r a l l = \frac{O l d E x e c u t i o n T i m e}{N e w E x e c u t i o n T i m e}$ )>> (1)

This gives a new Execution time of 

<<latex( $N e w E x e c T i m e = O l d E x e c T i m e (1 - F r a c t i o n E n h a n c e d + \frac{F r a c t i o n E n h a n c e d}{S p e e d u p E n h a n c e d})$ )>>

So we have

<<latex( $S p e e d u p O v e r a l l = (\frac{1}{1 - F r a c t i o n E n h a n c e d + \frac{F r a c t i o n E n h a n c e d}{S p e e d u p E n h a n c e d}})$ )>>