Home

About

Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network
FAQHELPSITE MAPCONTACT US


  Advanced Search  

 
Fusion of Loops for Parallelism and Locality Naraig Manjikian and Tarek S. Abdelrahman
 

Summary: Fusion of Loops for Parallelism and Locality
Naraig Manjikian and Tarek S. Abdelrahman
Department of Electrical and Computer Engineering
The University of Toronto
Toronto, Ontario, Canada M5S 1A4
email: {nmanjiki,tsa}@eecg.toronto.edu
Abstract--Loop fusion improves data locality and re-
duces synchronization in data-parallel applications. How-
ever, loop fusion is not always legal. Even when legal,
fusion may introduce loop-carried dependences which re-
duce parallelism. In addition, performance losses result
from cache conflicts in fused loops. We present new, sys-
tematic techniques which: (1) allow fusion of loop nests in
the presence of fusion-preventing dependences, (2) allow
parallel execution of fused loops with minimal synchro-
nization, and (3) eliminate cache conflicts in fused loops.
We evaluate our techniques on a 56-processor KSR2 mul-
tiprocessor, and show improvements of up to 20% for rep-
resentative loop nest sequences. The results also indicate
a performance tradeoff as more processors are used, sug-

  

Source: Abdelrahman, Tarek S. - Department of Electrical and Computer Engineering, University of Toronto

 

Collections: Computer Technologies and Information Sciences