Architecture of an automatically tuned linear algebra library
J Cuenca, D Giménez, J González - Parallel Computing, 2004 - Elsevier
One approach for a hierarchical architecture of a set of linear algebra libraries with self-
optimisation capacity is shown. In previous works the optimisation of several routines was …
optimisation capacity is shown. In previous works the optimisation of several routines was …
Modeling performance through memory-stalls
R Iakymchuk, P Bientinesi - ACM SIGMETRICS Performance Evaluation …, 2012 - dl.acm.org
We aim at modeling the performance of linear algebra algorithms without executing either
them or parts of them. The performance of an algorithm can be expressed in terms of the …
them or parts of them. The performance of an algorithm can be expressed in terms of the …
Automatic optimisation of parallel linear algebra routines in systems with variable load
J Cuenca, D Giménez, J González… - … and Network-Based …, 2003 - ieeexplore.ieee.org
The architecture of an automatically tuned linear algebra library proposed in previous works
is extended in order to adapt itself to platforms where both the CPU load and the network …
is extended in order to adapt itself to platforms where both the CPU load and the network …
Designing polylibraries to speed up linear algebra computations
In this paper, we analyse the design of polylibraries, where the programs call for routines
from different libraries according to the characteristics of the problem and of the system used …
from different libraries according to the characteristics of the problem and of the system used …
Towards the design of an automatically tuned linear algebra library
J Cuenca, D Giménez… - … 10th Euromicro Workshop …, 2002 - ieeexplore.ieee.org
In this work we propose the architecture of an automatically tuned linear algebra library,
which is composed by a set of linear algebra routines along with their installation routines …
which is composed by a set of linear algebra routines along with their installation routines …
A proposal of metaheuristics to schedule independent tasks in heterogeneous memory-constrained systems
This paper proposes some metaheuristics for the solution of a tasks scheduling problem.
Independent tasks with different computational costs and memory requirements are …
Independent tasks with different computational costs and memory requirements are …
[PDF][PDF] Performance prediction through time measurements
R Iakymchuk - International Conference on High Performance …, 2011 - hpac.cs.umu.se
Performance Prediction through Time Measurements Page 1 Performance Prediction through
Time Measurements Roman Iakymchuk AICES Graduate School, RWTH Aachen …
Time Measurements Roman Iakymchuk AICES Graduate School, RWTH Aachen …
[PDF][PDF] Auto-optimization of linear algebra parallel routines: the Cholesky factorization
LP Garcıa, J Cuenca, D Giménez - … & Future Issues of High-End …, 2005 - juser.fz-juelich.de
In recent years different techniques to obtain software able to tune automatically to the
conditions of parallel platforms have been studied [3, 9, 10, 12, 16]. Such developments will …
conditions of parallel platforms have been studied [3, 9, 10, 12, 16]. Such developments will …
[PDF][PDF] Parametrización de esquemas algorıtmicos paralelos para autooptimización
En este artıculo se estudia la técnica de autooptimización de rutinas paralelas por medio de
la parametrización del modelo de tiempo de ejecución. Se analizan las peculiaridades de …
la parametrización del modelo de tiempo de ejecución. Se analizan las peculiaridades de …
[引用][C] Técnicas de optimización de rutinas paralelas de álgebra lineal en sistemas heterogéneos
J Camara Moreno - Proyecto de investigación:, 2021 - Universidad de Murcia