Browsing by Author "Servat, Harald"
Now showing items 1-20 of 21
-
Automating the application data placement in hybrid memory systems
(Institute of Electrical and Electronics Engineers (IEEE), 2017)
Conference report
Open AccessMulti-tiered memory systems, such as those based on Intel® Xeon Phi™processors, are equipped with several memory tiers with different characteristics including, among others, capacity, access latency, bandwidth, energy ... -
Bio-inspired call-stack reconstruction for performance analysis
(Institute of Electrical and Electronics Engineers (IEEE), 2016)
Conference report
Open AccessThe correlation of performance bottlenecks and their associated source code has become a cornerstone of performance analysis. It allows understanding why the efficiency of an application falls behind the computer's peak ... -
Detailed and simultaneous power and performance analysis
(2016-02)
Article
Open AccessOn the road to Exascale computing, both performance and power areas are meant to be tackled at different levels, from system to processor level. The processor itself is the main responsible for the serial node performance ... -
Detailed performance analysis using coarse grain sampling
(Springer, 2014)
Conference report
Restricted access - publisher's policyPerformance evaluation tools enable analysts to shed light on how applications behave both from a general point of view and at concrete execution points, but cannot provide detailed information beyond the monitored regions ... -
Enabling homomorphically encrypted inference for large DNN models
(Institute of Electrical and Electronics Engineers, 2021)
Article
Open AccessThe proliferation of machine learning services in the last few years has raised data privacy concerns. Homomorphic encryption (HE) enables inference using encrypted data but it incurs 100x-10,000x memory and runtime ... -
Folding: reporting instantaneous performance metrics and source-code references
(Barcelona Supercomputing Center, 2015-05-05)
Conference report
Open AccessDespite supercomputers deliver huge computational power, applications only reach a fraction of it. There are several factors limiting the application performance, and one of the most important is the single processor ... -
Framework for a productive performance optimization
(2013-08)
Article
Restricted access - publisher's policyModern supercomputers deliver large computational power, but it is difficult for an application to exploit such power. One factor that limits the application performance is the single node performance. While many performance ... -
Identifying code phases using piece-wise linear regressions
(Institute of Electrical and Electronics Engineers (IEEE), 2014)
Conference report
Restricted access - publisher's policyNode-level performance is one of the factors that may limit applications from reaching the supercomputers' peak performance. Studying node-level performance and attributing it to the source code results into valuable insight ... -
Integrating memory perspective into the BSC performance tools
(Institute of Electrical and Electronics Engineers (IEEE), 2017)
Conference report
Open AccessThe growing gap between processor and memory speeds results in complex memory hierarchies as processors evolve to mitigate such differences by taking advantage of locality of reference. In this direction, the BSC performance ... -
MetH: A family of high-resolution and variable-shape image challenges
(2019-11-20)
Research report
Open AccessHigh-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 ... -
On the instrumentation of OpenMP and OmpSs Tasking constructs
(Springer, 2012)
Conference report
Open AccessParallelism has become more and more commonplace with the advent of the multicore processors. Although different parallel pro- gramming models have arisen to exploit the computing capabilities of such processors, ... -
On the usefulness of object tracking techniques in performance analysis
(Association for Computing Machinery (ACM), 2013)
Conference report
Restricted access - publisher's policyUnderstanding the behavior of a parallel application is crucial if we are to tune it to achieve its maximum performance. Yet the behavior the application exhibits may change over time and depend on the actual execution ... -
On-line detection of large-scale parallel application's structure
(Institute of Electrical and Electronics Engineers (IEEE), 2010)
Conference report
Restricted access - publisher's policyWith larger and larger systems being constantly deployed, trace-based performance analysis of parallel applications has become a daunting task. Even if the amount of performance data gathered per single process is ... -
Studying performance changes with tracking analysis
(Springer, 2015)
Part of book or chapter of book
Open AccessNumerical simulation and modelling using High Performance Computing has evolved into an established technique in academic and industrial research. At the same time, the High Performance Computing infrastructure is becoming ... -
The HOPSA workflow and tools
(Springer, 2012)
Conference report
Restricted access - publisher's policyTo maximise the scientific output of a high-performance computing system, different stakeholders pursue different strategies. While individual application developers are trying to shorten the time to solution by optimising ... -
The Mont-Blanc prototype: an alternative approach for high-performance computing systems
(2016)
Research report
Open AccessHigh-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 ... -
The Mont-Blanc prototype: an alternative approach for HPC systems
(Institute of Electrical and Electronics Engineers (IEEE), 2016)
Conference report
Open AccessHigh-performance computing (HPC) is recognized as one of the pillars for further progress in science, industry, medicine, and education. Current HPC systems are being developed to overcome emerging architectural challenges ... -
The secrets of the accelerators unveiled: tracing heterogeneous executions through OMPT
(Springer, 2016)
Conference report
Restricted access - publisher's policyHeterogeneous systems are an important trend in the future of supercomputers, yet they can be hard to program and developers still lack powerful tools to gain understanding about how well their accelerated codes perform ... -
Trace spectral analysis toward dynamic levels of detail
(Institute of Electrical and Electronics Engineers (IEEE), 2011)
Conference report
Restricted access - publisher's policyThe emergence of Petascale systems has raised new challenges to performance analysis tools. Understanding every single detail of an execution is important to bridge the gap between the theoretical peak and the actual ... -
Understanding memory access patterns using the BSC performance tools
(Elsevier, 2018-10)
Article
Open AccessThe growing gap between processor and memory speeds has lead to complex memory hierarchies as processors evolve to mitigate such divergence by exploiting the locality of reference. In this direction, the BSC performance ...
