Loading...
Please wait, while we are loading the content...
Similar Documents
Exploiting data parallelism for efficient execution of logic programs on associative . . . (1990)
| Content Provider | CiteSeerX |
|---|---|
| Author | Bansal, Arvind K. Potter, Jerry L. |
| Description | We describe a model to exploit data parallelism present in associative computers for efficient execution of logic programs on associative supercomputers. We present an alternate scheme for logical structure representation which naturally interfaces lists and vectors on associative computers for efficient integration of symbolic and numerical computation on existing associative supercomputers. We also propose a scheme for efficient data parallel goal reduction which is almost independent of number of clauses. The data parallel goal reduction scheme efficiently pruns non unifiable clauses and performs binding of variables with single occurrence in goal and the clauses. The data parallel model reduces the cost of shallow backtracking, deep backtracking and detrailing significantly. The independence of parallel goal reduction scheme from number of clauses has been demonstrated by experimental results. |
| File Format | |
| Language | English |
| Publisher Date | 1990-01-01 |
| Publisher Institution | IN: PROCEEDINGS OF THE 2ND INTERNATIONAL IEEE CONFERENCE ON TOOLS FOR ARTIFICIAL INTELLIGENCE |
| Access Restriction | Open |
| Subject Keyword | Logical Structure Representation Single Occurrence Data Parallelism Present Non Unifiable Clause Parallel Goal Reduction Scheme Data Parallelism Efficient Data Parallel Goal Reduction Deep Backtracking Numerical Computation Alternate Scheme Data Parallel Model Efficient Integration Associative Supercomputer Logic Program Efficient Execution Associative Computer Experimental Result Shallow Backtracking Data Parallel Goal Reduction Scheme |
| Content Type | Text |
| Resource Type | Article |
