Efficient sparse matrix-vector multiplication on cache-based GPUs
Sparse matrix-vector multiplication is an integral part of many scientific algorithms. Several studies have shown that it is a bandwidth-limited operation on current hardware. On cache-based architectures the main factors that influence performance are spatial locality in accessing the matrix, and t...
Szerzők: | |
---|---|
Dokumentumtípus: | Könyv része |
Megjelent: |
IEEE Communications Society
Piscataway (NJ)
2012
|
Sorozat: | Innovative Parallel Computing (InPar), 2012
|
Tárgyszavak: | |
mtmt: | 2724105 |
Online Access: | https://publikacio.ppke.hu/1901 |
Tartalmi kivonat: | Sparse matrix-vector multiplication is an integral part of many scientific algorithms. Several studies have shown that it is a bandwidth-limited operation on current hardware. On cache-based architectures the main factors that influence performance are spatial locality in accessing the matrix, and temporal locality in re-using the elements of the vector. © 2012 IEEE. |
---|---|
Terjedelem/Fizikai jellemzők: | 12 1-12 |
ISBN: | 9781467326322 |