Semipredicate problem

Abstract: The solution of the general nonlinear programing problem by means of a subroutine called VMCON is described. VMCON uses an algorithm that solves a sequence of positive-definite quadratic programing subproblems. Each solution determines a direction in which a one-dimensional minimization is performed. In developing this code, changes in the original implementation were made to make the program easier to use and maintain and to incorporate some recently developed LINPACK subprograms. The current implementation contains extensive in-line documentation; an interface subroutine, VMCON1, with a simplified calling sequence; and print options to aid the user in interpreting results. 2 figures.

Abstract: : This paper discusses the problems involved in using linear programming as a subroutine of a larger routine. Proposals are made for eliminating the tolerance selection problem, and for improving the accuracy of inversions. Sample programs are given in FORTRAN IV and in ALGOL.

Abstract: A method and apparatus for constructing subroutines to define the behavior of simulation objects is provided. The apparatus includes a display, a processor, and an input device. The processor generates on the display a GRR set region associated with a simulation object. A user operates the input device to place visual representations of rules and/or subroutines within the GRR set region. When a visual representation of a rule or subroutine is placed within a GRR set, computer step sequences that implement the behavior specified for the rule or subroutine are generated for the simulation object. A user may operate the input device to activate a control on a visual subroutine indicator to cause a subroutine region to appear. When a visual representation of a rule or subroutine is placed within a subroutine region, the behavior specified for the rule or subroutine is incorporated into the subroutine associated with the subroutine region. Different types of subroutines are provided, where the type of a subroutine determines how the rules within the subroutine are processed during a simulation. Pretests may be specified for subroutines so that the behavior represented by the rules within the subroutine will not be exhibited unless the current state of the simulation satisfies the conditions of the pretest. During the performance of a simulation, the processor displays images associated with simulation objects on the display. The processor causes the images to behave according to the generalized computer step sequences that have been generated based upon the rules and/or subroutines represented in the GRR set regions for the respective objects.

Abstract: Exploiting speculative thread-level parallelism on multi-core architecture to speedup serial applications,which are traditionally difficult to be parallelized manually or automatically,has been a feasible technique The performance of TLS,however,mostly depends on how to partition threads It has been known that speculating only on loops does not yield sufficient parallelism,but speculative subroutines execution as a means to increase the available parallelism has been proved more difficult than loops In this paper we present a design criterion for speculative execution subroutine By using ProRV ProFun,two dynamic profiling tools extended from Simplescalar,we analyzed the potential performance available from speculative subroutine execution of SPEC CPU2000 Our experiment show that 1) Subroutine without a return value take about 40% of total running time,and subroutine with a sparse integer return value takes about 10% of total running time and about 70% of return values can be predicted correctly 2) The simple last-value scheme is good enough for return value prediction 3) Explicit synchronization is necessary because of the common existence of data dependent between subroutine structure and its following code