Abstract:- An approach, permitting us to build free schedules for affine loops with affine dependences represented with a single dependence relation, is described. The iterations of each time under the free schedule can be executed as soon as their operands are available. This allows us to extract maximal fine-grained loop parallelism. The approach requires an exact dependence analysis. To describe the approach and carry out experiments, the dependence analysis by Pugh and Wonnacott has been chosen where dependences are represented in the form of tuple relations. The approach can be applied to both non-parameterized and parameterized loops. Problems to be resolved in the future to utilize the entire power of the presented technique are disc...
[[abstract]]A dependence relation between two data references is linear if it generates dependence v...
Abstract — The parallelization of computa-tional intensive programs can lead to dramatic performance...
Special issue on "Optimizing Compilers for Parallel Languages"International audienceWe explore the l...
Introduction This short report is a companion paper of the research report [1]. It cannot be read w...
This paper proposes an efficient run-time system to schedule general nested loops on multiprocessors...
A novel approach to form affine time partitioning for statement instances of arbitrary nested loops ...
In a nested loop the indexes form an index vector and the index vectors of all iterations form the i...
Three related problems, among others, are faced when trying to execute an algorithm on a parallel ma...
This paper presents an algorithm to find the optimal affine partitions that maximize the degree of p...
Using parallel processing systems to execute scientific applications is one of the most common solut...
In this paper, we survey loop parallelization algorithms, analyzing the dependence representations t...
[[abstract]]A dependence relation between two data references is linear if it generates dependence v...
It is extremely difficult to parallelize DOACROSS loops with non-uniform loop-carried dependences. I...
A dependence relation between two data references is linear if it generates dependence vectors that ...
Executing a program in parallel machines needs not only to find sufficient parallelism in a program,...
[[abstract]]A dependence relation between two data references is linear if it generates dependence v...
Abstract — The parallelization of computa-tional intensive programs can lead to dramatic performance...
Special issue on "Optimizing Compilers for Parallel Languages"International audienceWe explore the l...
Introduction This short report is a companion paper of the research report [1]. It cannot be read w...
This paper proposes an efficient run-time system to schedule general nested loops on multiprocessors...
A novel approach to form affine time partitioning for statement instances of arbitrary nested loops ...
In a nested loop the indexes form an index vector and the index vectors of all iterations form the i...
Three related problems, among others, are faced when trying to execute an algorithm on a parallel ma...
This paper presents an algorithm to find the optimal affine partitions that maximize the degree of p...
Using parallel processing systems to execute scientific applications is one of the most common solut...
In this paper, we survey loop parallelization algorithms, analyzing the dependence representations t...
[[abstract]]A dependence relation between two data references is linear if it generates dependence v...
It is extremely difficult to parallelize DOACROSS loops with non-uniform loop-carried dependences. I...
A dependence relation between two data references is linear if it generates dependence vectors that ...
Executing a program in parallel machines needs not only to find sufficient parallelism in a program,...
[[abstract]]A dependence relation between two data references is linear if it generates dependence v...
Abstract — The parallelization of computa-tional intensive programs can lead to dramatic performance...
Special issue on "Optimizing Compilers for Parallel Languages"International audienceWe explore the l...