Execution of programs with data parallel language constructs is either based on the fork/join or on the SPMD model. Whereas the former executes a program sequentially and confines parallel activity to the data parallel constructs, the latter executes the whole program in parallel: while data parallel constructs are performed cooperatively, the remaining code is replicated. However, in the prese...

An important problem in heterogeneous computing (HC) is predicting task execution time. A methodology is introduced for determining the execution time distribution for a given data parallel program that is to be executed in an SIMD, MIMD (SPMD), and/or mixed-mode SIMD/MIMD (SPMD) HC environment. The program is assumed to contain operations and constructs whose execution times depend on input-da...

Many embedded control systems work in different operating modes, for example start-up, stand-by, shut-down and failure mode. These different operating modes usually have different timing requirements, and the different functional behaviour also leads to differences in timing behaviour. A Worst-Case Execution Time (WCET) analysis of such a system needs to determine mode-specific bounds on execut...

Code Cloning Tracing is a new software annotation method that makes it possible to collect traces from time consuming applications. To this end, Code Cloning Tracing provides instrumented programs with two execution modes: a low overhead “no-trace collection” mode which serves to position the application in an interesting state with regard to tracing, and a “trace collection” mode. This paper d...

In order to reduce the impact on the grid scheduling caused by the resource error, for complex dependent tasks, designed a dynamic replication of fault-tolerant scheduling algorithm (DRFT). This algorithm build task model by applying hypergraph theory, using primary-backup task as backup mode, take the active execution mode combined with the passive execution mode to perform the backup task, se...

Containers are increasingly used as means to distribute and run Linux services and applications. In this paper we describe the architectural design and implementation of udocker a tool to execute Linux containers in user mode and we describe a few practical applications for a range of scientific codes meeting different requirements: from single core execution to MPI parallel execution and execu...

Mode information in logic programming is concerned with such things as inputs and outputs of procedures, producers and consumers of variable bindings, instantiation states of calls during execution and the order of execution. Modes seem inextricably tied to the procedural rather than the declarative view of logic programs. Despite this, we argue that purely declarative information can actually ...

A program mode is a regular trajectory of the execution of a program that is determined by the values of its input variables. By exploiting program modes, we may make worst-case execution time (WCET) analysis more precise. This paper presents a novel method to automatically find program modes and calculate the WCET estimates of programs. First, the modes of a program will be identified automati...

Layout tools for FPGAs can typically be run in two different modes: non-timing-driven and timing-driven. Non-timing-driven mode produces a solution quickly, without consideration of design performance. Timing-driven mode requires that a designer specify performance constraints and then produces a performance-optimized layout solution. The task of generating constraints is burdensome since desig...