| 摘要 |
<p>A data storage structure and its complementary selection data storage structure is provided with a complementary predictive annotation storage structure comprising a number of corresponding predictive annotation vectors, each having a number of predictive annotation tuples. To retrieve data from a data block tuple of a data vector, a data vector and its corresponding data selection and predictive annotation vectors are read out concurrently. Determination is made as to whether there is a selection hit and a prediction hit. Concurrently, one of the predictive annotation tuples is selected and recorded for the next access based on the predictive annotation selected and recorded in the previous access. Also concurrently, a data block tuple is selected based on the predictive annotation selected and recorded in the previous access, and a data element is selected from the selected data block tuple based on the access key, without waiting for the determination results. Remedial actions are subsequently taken if it is determined that either there is no selection hit or no prediction hit. Additionally, the data vector, selection vector, the predictive annotation vector and the previously recorded predictive annotations are conditionally updated depending on the selection and prediction hit determinations. <IMAGE></p> |
