Reports de recerca
Enviaments recents
-
Towards resilient EU HPC systems: A blueprint
(2020-04)
Report de recerca
Accés obertThis document aims to spearhead a Europe-wide discussion on HPC system resilience and to help the European HPC community define best practices for resilience. We analyse a wide range of state-of-the-art resilience mechanisms ... -
MetH: A family of high-resolution and variable-shape image challenges
(2019-11-20)
Report de recerca
Accés obertHigh-resolution and variable-shape images have not yet been properly addressed by the AI community. The approach of down-sampling data often used with convolutional neural networks is sub-optimal for many tasks, and has ... -
Practical experience with Nebelung: the runtime support for transactional memory and OpenMP
(2007-08)
Report de recerca
Accés obertTransactional Memory (TM) is a key future technology for emerging many-cores. On the other hand, OpenMP provides a vast established base for writing parallel programs, especially for scientific applications. Combining TM ... -
The MS-processor's register file timing and power evaluation
(2008-09)
Report de recerca
Accés obertPower evaluation is an important issue in new proposal chip level architectures due to the big amount of power is dissipated as head and chips have limited head dissipation capacity. The evaluation shown in this technical ... -
Systolic implementation for deconvolution iterative algorithm
(1985)
Report de recerca
Accés obertSystolic architectures implement regular algorithms in hardware, in order to obtain high computational throughput. In this paper we provide a modular architecture for a deconvolution iterative algorithm. The basic module ... -
The Mont-Blanc prototype: an alternative approach for high-performance computing systems
(2016)
Report de recerca
Accés obertHigh-performance computing (HPC) is recognized as one of the pillars for further advance of science, industry, medicine, and education. Current HPC systems are being developed to overcome emerging challenges in order to ... -
Exploiting asynchrony from exact forward recovery for DUE in iterative solvers
(2015)
Report de recerca
Accés obertThis paper presents a method to protect iterative solvers from Detected and Uncorrected Errors (DUE) relying on error detection techniques already available in commodity hardware. Detection operates at the memory page ... -
Commit on overflow
(2014)
Report de recerca
Accés obertCurrent commercial CPUs have hardware support for speculative lock elision (SLE). SLE tries to elide the lock by speculatively executing lock protected critical section. If the speculation fails, SLE acquires the lock and ... -
Per-task energy accounting in computing systems
(2013)
Report de recerca
Accés obertWe present for the first time the concept of per-task energy accounting (PTEA) and relate it to per-task energy metering (PTEM). We show the benefits of supporting both in future computing systems. Using the shared last-level ... -
CUsched: multiprogrammed workload scheduling on GPU architectures
(2013)
Report de recerca
Accés obertGraphic Processing Units (GPUs) are currently widely used in High Performance Computing (HPC) applications to speed-up the execution of massively-parallel codes. GPUs are well-suited for such HPC environments because ... -
Solving matrix problems with no size restriction on a systolic array processor
(1986)
Report de recerca
Accés obertIn this paper we propose several data structures partitioning and transformation schemes, in order to get an efficient execution of various matrix algorithms without any size resriction. The following matrix operations are ... -
Computing size-independent matrix problems on systolic array processors
(1985)
Report de recerca
Accés obertA methodology to transform dense to banded matrices is presented in this paper. This transformation, is accomplished by triangular blocks partitioning, and allows the implementation of silutions to problems with any given ...