Telefonaktiebolaget Lm Ericsson (publ)

Arm Limited

Carl Von Platen

Johan Eker

Björn Johansson

Charles Chen Xu

Song Yuan

Bjorn Inge Johansson

Georgia Kouveli

Mohammed Javed Absar

Marco Cornero

A method of compiling a sequence of program instructions, a method of parallel execution of a sequence of program instructions and apparatuses and software supporting such methods are disclosed. The sequence of program instructions is analyzed in terms of basic blocks forming a control flow graph and execution paths through that control flow graph are identified. When more than one execution path leads to a given basic block, or when a loop path is found leading from a given basic block back to the same basic block, a potential convergence point may be identified. A convergence marker is added to the computer program associated with the basic blocks identified in this way and then when the program is executed, the convergence markers found are used to trigger a determination of a subset of the multiple execution threads which are executed following that convergence marker.

Determination of branch convergence in a sequence of program instruction

A method of statically testing dependence in a dataflow program is provided, the method comprising receiving a dataflow program which provides parameters, including consumption rates, production rates on connections between actors in the program and a number of initial samples (delays) on the connections, generating from the parameters a model of a precedence graph for the dataflow program representing dependence constraints between distinct firings of the number of actors. For the model, determining a feedback distance between multiple firings of a same actor, determining sets of parallel regions comprising a given number of actor firings of a same actor, composing mutually independent component regions comprising at least a part of the sets of parallel regions, and composing one or more composite regions comprising one or more component regions and/or one or more sets of parallel regions, being composed so that a pre-determined criteria is satisfied.

Method for exploiting massive parallelism

Processing a dataflow program by a program development tool includes detecting a pair of actors defined by dataflow program instructions, wherein the pair of actors include a producer actor and a consumer actor, the producer actor supplying a data structure to the consumer actor via a path that comprises at least one connection and possibly also intervening other actors. An analysis is performed including analyzing one or more operations of the producer actor that involve the data structure and/or analyzing one or more operations of the consumer actor that involve the data structure. A result of the analysis is used as a basis for selecting a minimal amount of information from among a plurality of data handling possibilities concerning the data structure. A transformed program is produced in which the selected minimal amount of information is caused to be passed from the producer actor to the consumer actor.

Data handling among actors in a dataflow programming environment

Processing a dataflow program by a program development tool includes analyzing an actor defined by the dataflow program to identify original sequences of actions that can be reformulated to achieve greater execution parallelism while maintaining the same functionality as the original sequences. A processed dataflow program is produced comprising processed dataflow program instructions and decision point program instructions. The processed dataflow program instructions comprise alternative sequences of reformulated actions that achieve greater execution parallelism while maintaining the same functionality as the identified one or more original sequences. The decision point program instructions direct processing equipment to select and execute one or more of the alternative sequences of reformulated actions, wherein selection is based on state and token information in existence at the time of selection. When more than one alternative sequence can be selected, selection of sequence with highest parallelism is preferred.

Parallelization of dataflow actors with local state

A computer-implemented method of generating tamper-protected computer program code. The method comprises obtaining a representation of the computer program code, the computer program being adapted to cause a data processing system to perform a plurality of computational tasks in a first order of execution, each computational task being represented in the representation of the computer program code by at least one program statement; obtaining a plurality of alternative orders of execution of the computational tasks; generating an executable representation of the program code adapted to cause a data processing system to select a randomized order of execution from the plurality of alternative orders of execution and to execute the computational tasks in the selected randomized order of execution.

Obfuscating execution traces of computer program code

A computer-implemented method of tamper-protecting computer program code. The method comprises: obtaining an input representation of the computer program code; identifying a conditional program statement for causing a data processing system to selectively execute one of at least a first and a second sets of program statements when said computer program is executed by a data processing system; replacing said identified conditional program statement and the first and second sets of program statements with a set of transformed program statements to obtain obfuscated program code, wherein the set of transformed program statements is adapted to cause the data processing system to execute at least a part of each of the transformed program statements when said computer program is executed by the data processing system.

Obfuscating computer program code

A method of generating a delta file, the delta file including update instructions for causing a target processing device to transform a current memory image module into an updated memory image module. The method includes: incorporating a parametric representation of a first memory address in the delta file, the parametric representation being parametric with respect to at least one parameter; and incorporating parameter resolution instructions in the delta file, wherein the parameter resolution instructions are adapted to cause the target processing device to determine a value of said at least one parameter and to determine an address value of the first memory address from the parametric representation and the determined value of said at least one parameter.

Generating incremental program updates

A computer-implemented method of tamper-protecting a computer program, the method comprising: processing an input representation of the computer program to identify a function call for causing a data processing system to continue execution of the computer program at a predetermined entry point memory address when said computer program is executed by a data processing system; replacing the identified function call with a modified function call, wherein the modified function call includes an algebraic expression for causing the data processing system to compute the entry point memory address when said computer program is executed by the data processing system.

Growing community of inventors

Malmö, Sweden

Carl Von Platen