Name
Abstract | ||
|---|---|---|
Power consumption and heat dissipation issues are pushing the microprocessors industry towards multicore design patterns. Given the cubic dependence between core frequency and power consumption, multicore technologies leverage the idea that doubling the number of cores and halving the cores frequency gives roughly the same performance reducing the power consumption by a factor of four. With the number of cores on multicore chips expected to reach tens in a few years, efficient implementations of numerical libraries using shared memory programming models is of high interest. The current message passing paradigm used in ScaLAPACK and elsewhere introduces unnecessary memory overhead and memory copy operations, which degrade performance, along with the making it harder to schedule operations that could be done in parallel. Limiting the use of shared memory to fork-join parallelism (perhaps with OpenMP) or to its use within the BLAS does not address all these issues. |
Year | Venue | Keywords |
|---|---|---|
2006 | PARA | multicore chip,multicore design pattern,memory copy operation,shared memory,cores frequency,math software,multicore technology,power consumption,core frequency,unnecessary memory overhead,memory programming model,design pattern,message passing,chip,programming model |
Field | DocType | Volume |
Programming paradigm,Shared memory,Computer science,Parallel computing,Software design pattern,Implementation,Software,ScaLAPACK,Multi-core processor,Message passing | Conference | 4699 |
ISSN | ISBN | Citations |
0302-9743 | 3-540-75754-6 | 48 |
PageRank | References | Authors |
3.83 | 2 | 6 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Alfredo Buttari | 1 | 647 | 53.60 |
| Jack J. Dongarra | 2 | 17625 | 2615.79 |
| Jakub Kurzak | 3 | 935 | 79.46 |
| Julien Langou | 4 | 1028 | 71.98 |
| Piotr Luszczek | 5 | 1144 | 99.50 |
| Stanimire Tomov | 6 | 1214 | 102.02 |