Abstract: The invention provides a method for improving the precision of interprocedural alias analysis by efficiently qualifying (naming) dynamically allocated storage locations with call path information and identifying as identical qualified name pairs, one of which is a prefix substring of another. The invention also provides a compact method for representing alias information which improves the efficiency and in some cases, the precision, of alias analysis, by eliminating alias relations that involve more than one level of dereferencing and by eliminating all alias relations that do not contain at least one dereferenced object.

Abstract: By novel use of the Program Call Graph representation of computer programs, this method and apparatus provides a general analysis method for interprocedural bidirection data flow problems in computer software programs. The invention has many uses, including the determination of interprocedural alias analysis of computer software programs which contain pointers.The method starts by constructing a Program Call Graph representation of a computer program with each node of the graph representing a routine of the program. An internal representation of each node is then constructed and initial interprocedural values are associated with appropriate nodes. An interprocedural traversal of the Program Call Graph is performed in which each node is visited; an intraprocedural propagation is performed to develop a new set of interim solution values; and the new interim solution values are interprocedurally propagated. The new interim solution is propagated in a forward and backward direction in one pass of the traversal.

Abstract: The present invention provides a system and method for optimizing or parallelizing computer code typically represented by a source program. The source program is represented by a control flow graph. The present invention includes an optimizer for constructing a compact data flow representation from the control flow graph and a mechanism for evaluating the compact data flow representation in relation to a data flow framework in order to determine a solution to a particular data flow problem. The present invention represents data flow chains compactly, obtaining some of the advantages of Static Single Assignment (SSA) form without modification of program text (i.e., renaming). In addition, the present invention represents compactly certain data flow chains which SSA form fails to represent (i.e. def-def, use-def, and use-use chains).

Abstract: A method and system is provided for constructing sparse evaluation graphs for forward or backward monotone data flow problems. The sparse graph combines information as early as possible, yet directly connects nodes that generate and use information. This allows problems from the large, general class of monotone data flow problems to enjoy the advantages of solutions based on Static Single Assignment (SSA) form.The present invention includes a compiler configured to transform a source program into optimized executable code. The compiler contains an optimizer which is configured to optimize the source program, in which the source program and optimization program are represented by a data flow framework. The optimizer includes a sparse evaluation graph generator which generates a sparse evaluation graph and an evaluator connected to evaluate the sparse evaluation graph in relation to the data flow framework.