RT Journal Article
JF IEEE Micro
YR 2010
VO 31
IS
SP 56
TI Data Marshaling for Multicore Systems
A1 Onur Mutlu,
A1 Yale Patt,
A1 M. Aater Suleman,
A1 Jose A. Joao,
A1 Khubaib .,
A1 Khubaib Khubaib,
A1 Yale N. Patt,
K1 Staged execution
K1 critical sections
K1 pipelining
K1 CMP
K1 multicore
K1 pipeline parallelism
K1 parallel programming
K1 communication misses
K1 heterogeneous multicore
K1 remote execution
AB <p>Dividing a program into segments and executing each segment at the core best suited to run it can improve performance and save power. When consecutive segments run on different cores, accesses to intersegment data incur cache misses. Data Marshaling eliminates such cache misses by identifying and marshaling the necessary intersegment data when a segment is shipped to a remote core.</p>
PB IEEE Computer Society, [URL:http://www.computer.org]
SN 0272-1732
LA English
DO 10.1109/MM.2010.105
LK http://doi.ieeecomputersociety.org/10.1109/MM.2010.105