TY - JOUR
T1 - Accelerating the execution of matrix languages on the cell broadband engine architecture
AU - Khoury, Raymes
AU - Burgstaller, Bernd
AU - Scholz, Bernhard
PY - 2011
Y1 - 2011
N2 - Matrix languages, including MATLAB and Octave, are established standards for applications in science and engineering. They provide interactive programming environments that are easy to use due to their script languages with matrix data types. Current implementations of matrix languages do not fully utilize high-performance, special-purpose chip architectures, such as the IBM PowerXCell processor (Cell). We present a new framework that extends Octave to harvest the computational power of the Cell. With this framework, the programmer is alleviated of the burden of introducing explicit notions of parallelism. Instead, the programmer uses a new matrix data type to execute matrix operations in parallel on the synergistic processing elements (SPEs) of the Cell. We employ lazy evaluation semantics for our new matrix data type to obtain execution traces of matrix operations. Traces are converted to data dependence graphs; operations in the data dependence graph are lowered (split into submatrices), scheduled and executed on the SPEs. Thereby, we exploit 1) data parallelism, 2) instruction level parallelism, 3) pipeline parallelism, and 4) task parallelism of matrix language programs. We conducted extensive experiments to show the validity of our approach. Our Cell-based implementation achieves speedups of up to a factor of 12 over code run on recent Intel Core2 Quad processors.
AB - Matrix languages, including MATLAB and Octave, are established standards for applications in science and engineering. They provide interactive programming environments that are easy to use due to their script languages with matrix data types. Current implementations of matrix languages do not fully utilize high-performance, special-purpose chip architectures, such as the IBM PowerXCell processor (Cell). We present a new framework that extends Octave to harvest the computational power of the Cell. With this framework, the programmer is alleviated of the burden of introducing explicit notions of parallelism. Instead, the programmer uses a new matrix data type to execute matrix operations in parallel on the synergistic processing elements (SPEs) of the Cell. We employ lazy evaluation semantics for our new matrix data type to obtain execution traces of matrix operations. Traces are converted to data dependence graphs; operations in the data dependence graph are lowered (split into submatrices), scheduled and executed on the SPEs. Thereby, we exploit 1) data parallelism, 2) instruction level parallelism, 3) pipeline parallelism, and 4) task parallelism of matrix language programs. We conducted extensive experiments to show the validity of our approach. Our Cell-based implementation achieves speedups of up to a factor of 12 over code run on recent Intel Core2 Quad processors.
KW - Cell Broadband Engine architecture
KW - Programming languages
KW - data partitioning
KW - lazy evaluation
KW - math script languages
KW - scheduling
UR - http://www.scopus.com/inward/record.url?scp=78649893133&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=78649893133&partnerID=8YFLogxK
U2 - 10.1109/TPDS.2010.58
DO - 10.1109/TPDS.2010.58
M3 - Article
AN - SCOPUS:78649893133
SN - 1045-9219
VL - 23
SP - 7
EP - 21
JO - IEEE Transactions on Parallel and Distributed Systems
JF - IEEE Transactions on Parallel and Distributed Systems
IS - 1
M1 - 5441290
ER -