US 7,096,462 B2Granted

System and method for using data address sequences of a program in a software development tool

AssigneeMicrosoft Corporation

InventorsHon Keat Chan, Hoi H. Vo

Life of this patent

Estimating the term…

Loading patent…

Abstract

Rapid determination of placement for code and data for optimal access of the code and data during execution of software applications. An application that is to be efficiently arranged in a software carrier medium is instrumented such that the status of whether a particular unit of code or data has been accessed during a time interval is recorded in a time-ordered bit sequence for each such unit. A sort routine is used to sort the order of time-ordered bit sequences within an array of such sequences. The sort routine invokes a comparison function that operates upon the temporal information stored in the two time-ordered bit sequences that are being compared for the routine. The order of the code and data in the software application is reordered in accordance with the results of the sort routine.

Claims9

Dependent claims

A computer-implemented method for optimizing the ordering of data units for access by a target application, comprising the steps of:

executing the target application such that the data units are accessed by the target application;
generating time-ordered sequences that indicate the status of whether a data unit of the target application has been accessed during each time interval within a sequence of time intervals, wherein the sequence of time intervals is contemporaneous with the executing of the target application;
determining a first position in a first time-ordered sequence for a first data unit, wherein the first position in the first time-ordered sequence indicates the first time interval in which the first data unit of the target application has been accessed;
determining a length of consecutive positions from the first position in the first time-ordered sequence, wherein the length of consecutive positions from the first position in the first time-ordered sequence is indicative of the number of successive time intervals in which the first data unit of target application has been accessed;
determining a first position in a second time-ordered sequence for a second data unit, wherein the first position in the second time-ordered sequence indicates the first time interval in which the second data unit of the target application has been accessed;
determining a length of consecutive positions from the first position in the second time-ordered sequence, wherein the length of consecutive positions from the first position in the second time-ordered sequence is indicative of the number of successive time intervals in which the second data unit of target application has been accessed, wherein the first positions of the first and second time-ordered sequences are selected in accordance with the latest time intervals in which the respective first and second data units have been accessed, and the lengths of the consecutive positions from the first positions of the first and second time-ordered sequences reflect time intervals that occur before the respective first positions of the first and second time-ordered sequences;
sorting the array of time-ordered sequences by comparing the first position in the first time-ordered sequence and the length of consecutive positions from the first position in the first time-ordered sequence with the first position in the second time-ordered sequence and the length of consecutive positions from the first position in the second time-ordered sequence, mapping the correspondence between the generated and the sorted time-ordered sequences;
and
arranging the accessed data units in a computer-readable medium according to the mapped correspondence of the generated and the sorted time ordered sequences.

6 more elements

A system for optimizing the ordering of data units for access by a target application, comprising:

means for executing the target application such that the data units are accessed by the target application;
means for determining a length of consecutive positions from the first position in the second time ordered sequence, wherein the length of consecutive positions from the first position in the second time-ordered sequence is indicative of the number of successive time intervals in which the second data unit of target application has been accessed, wherein the first positions of the first and second time-ordered sequences are selected in accordance with the latest time intervals in which the respective first and second data units have been accessed, and the lengths of the consecutive positions from the first positions of the first and second time-ordered sequences reflect time intervals that occur before the respective first positions of the first and second time-ordered sequences;
means for generating time-ordered bit sequences that indicate the status of whether a data unit of the target application has been accessed during each time interval within a sequence of time intervals, wherein the sequence of time intervals is contemporaneous with the executing of the target application;
means for sorting the array of time-ordered bit sequences by comparing consecutive data contained within the time-ordered bit sequences, wherein the length of the consecutive data is changed in response to an equal comparison between consecutive data from a first time-ordered bit sequence and consecutive data from a second time-ordered sequence, wherein the first and the second time-ordered bit sequences are contemporaneous, wherein a first sequence of bits from a first sequence of a first time-ordered bit sequence is compared with a first sequence of bits from a second time-ordered bit sequence;
means for mapping the correspondence between the generated and the sorted time-ordered bit sequences;
and
means for arranging the accessed data units in a computer-readable medium according to the mapped correspondence of the generated and the sorted time ordered bit sequences.

4 more elements

Dependencies are inferred from the claim text.