Y. Yan. Exploiting Cache Locality at Run-time. PhD thesis, Computer Science Department, College of William & Mary, May 1998.  Home/Search   Document Details and Download   Summary   Related Articles

....to find a partitioning vector k(k 1 ; k 2 ; Delta Delta Delta ; kn ) so that the above conditions are satisfied. Because finding an optimal partition vector is a NP complete problem, we propose a heuristic algorithm based on the following partitioning rules. Detailed proofs can be found in [21]. Theorem 1 Ordering Rule For a given partitioning vector k(k 1 ; k 2 ; Delta Delta Delta ; kn ) not in decreasing order, the partitioning vector resulting by sorting k in decreasing order is at least as good as k in terms of the sharing degree. Theorem 2 Increment Rule 1 For an ....

....partitions from X and Y dimensions. a 3 dimensional hash table where task bins in each partition are chained together to be pointed by a record in a Task Control Linked (TCL) list. The hashing of tasks into the hash table is finished by the space transformation functions (details are presented in [21]) 2.4. Task scheduling In order to minimize the parallel computing time of partitioned tasks, we present a Locality preserved Adaptive Scheduling (LAS) algorithm by extending our linearly adaptive algorithm proposed in [22] Initially, the i th task group chain in the TCL list is considered to ....

[Article contains additional citation context not shown here]

Y. Yan. Exploiting Cache Locality at Run-time. PhD thesis, Computer Science Department, College of William & Mary, May 1998.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC