公开(公告)号：US5327561A

公开(公告)日：1994-07-05

申请号：US763099

申请日：1991-09-20

申请人： Jong-Deok Choi ,  Ron K. Cytron ,  Jeanne Ferrante

发明人： Jong-Deok Choi ,  Ron K. Cytron ,  Jeanne Ferrante

IPC分类号： G06F9/45 ,  G06F9/00 ,  G06F9/44

CPC分类号： G06F8/433

摘要： 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.

摘要翻译： 提供了一种构建用于正向或反向单调数据流问题的稀疏评估图的方法和系统。 稀疏图尽可能早地组合信息，但是直接连接生成和使用信息的节点。 这样就可以从庞大的一般类别的单调数据流问题中获得基于静态单一分配（SSA）形式的解决方案的优势。 本发明包括被配置为将源程序转换成优化的可执行代码的编译器。 编译器包含优化器，该优化器被配置为优化源程序，其中源程序和优化程序由数据流框架表示。 优化器包括稀疏评估图生成器，其产生稀疏评估图和连接的评估器，以评估与数据流框架相关的稀疏评估图。

公开(公告)号：US5548761A

公开(公告)日：1996-08-20

申请号：US28493

申请日：1993-03-09

申请人： Vasanth Balasundaram ,  John L. Carter ,  Jeanne Ferrante

发明人： Vasanth Balasundaram ,  John L. Carter ,  Jeanne Ferrante

IPC分类号： G06F9/45

CPC分类号： G06F8/443

摘要： A method and apparatus designed to expose the power of manipulating data transfer and ownership to the compiler has been given. The key ideas behind the XDP methodology are its separation of data transfer from local computation, its non-blocking semantics to allow overlapping of communication with computation, and its unified treatment of data and ownership transfer. In addition, XDP offers the compiler a convenient platform for doing optimizations involving data movement by providing mechanisms for delayed communication binding and generating generalized compute rules. Compile-time data and data ownership transfers are accomplished independent of the target machine architecture. The run-time symbol table given here to support XDP is implementable as an extension to most high-level compiler intermediate languages. The applicability of XDP is quite general, and is not restricted to the optimization of communication for distributed memory machines. For instance, it can be used to optimize data transfers across different levels of a memory hierarchy.

摘要翻译： 已经给出了一种方法和设备，用于将操纵数据传输和所有权的权力暴露给编译器。 XDP方法背后的关键思想是将数据传输与本地计算分离，其非阻塞语义允许通信与计算重叠，以及统一处理数据和所有权转移。 此外，XDP为编译器提供了一个方便的平台，用于通过提供延迟通信绑定和生成广义计算规则的机制来进行涉及数据移动的优化。 编译时数据和数据所有权转移是独立于目标机器架构完成的。 这里给出的支持XDP的运行时符号表可以作为大多数高级编译器中间语言的扩展来实现。 XDP的适用性相当普遍，并不局限于分布式存储器的通信优化。 例如，它可以用于优化跨存储器层次结构的不同级别的数据传输。