Now showing items 21-40 of 60

    • Hipster: hybrid task manager for latency-critical cloud workloads 

      Nishtala, Rajiv; Carpenter, Paul Matthew; Petrucci, Vinicius; Martorell Bofill, Xavier (Institute of Electrical and Electronics Engineers (IEEE), 2017)
      Conference report
      Open Access
      In 2013, U. S. data centers accounted for 2.2% of the country's total electricity consumption, a figure that is projected to increase rapidly over the next decade. Many important workloads are interactive, and they demand ...
    • HPC benchmarking: scaling right and looking beyond the average 

      Radulović, Milan; Asifuzzaman, Kazi; Carpenter, Paul Matthew; Radojković, Petar; Ayguadé Parra, Eduard (Springer, 2018)
      Conference report
      Open Access
      Designing a balanced HPC system requires an understanding of the dominant performance bottlenecks. There is as yet no well established methodology for a unified evaluation of HPC systems and workloads that quantifies the ...
    • Improving HPC system throughput and response time using memory disaggregation 

      Vieira Zacarias, Felippe; Carpenter, Paul Matthew; Petrucci, Vinicius (Institute of Electrical and Electronics Engineers (IEEE), 2021)
      Conference report
      Open Access
      HPC clusters are cost-effective, well understood, and scalable, but the rigid boundaries between compute nodes may lead to poor utilization of compute and memory resources. HPC jobs may vary, by orders of magnitude, in ...
    • Inception: we need to go wider 

      Nishtala, Rajiv; Carpenter, Paul Matthew; Martorell, Xavier (Barcelona Supercomputing Center, 2018-04-24)
      Conference report
      Open Access
    • Intelligent colocation of HPC workloads 

      Vieira Zacarias, Felippe; Petrucci, Vinicius; Nishtala, Rajiv; Carpenter, Paul Matthew; Mossé, Daniel (Elsevier, 2021-05)
      Article
      Open Access
      Many server applications suffer from a bottleneck in the shared caches, instruction execution units, I/O or memory bandwidth, even though the remaining resources may be underutilized. It is hard for developers and runtime ...
    • Interconnect Energy Savings and Lower Latency Networks in Hadoop Clusters: The Missing Link 

      Fischer e Silva, Renan; Carpenter, Paul Matthew (IEEE, 2017)
      Conference lecture
      Open Access
      An important challenge of modern data centres running Hadoop workloads is to minimise energy consumption, a significant proportion of which is due to the network. Significant network savings are already possible using ...
    • Large-memory nodes for energy efficient high-performance computing 

      Živanovič, Darko; Radulović, Milan; Llort, German; Zaragoza, David; Strassburg, Janko; Carpenter, Paul Matthew; Radojković, Petar; Ayguadé Parra, Eduard (Association for Computing Machinery (ACM), 2016)
      Conference report
      Open Access
      Energy consumption is by far the most important contributor to HPC cluster operational costs, and it accounts for a significant share of the total cost of ownership. Advanced energy-saving techniques in HPC components have ...
    • LEGaTO: first steps towards energy-efficient toolset for heterogeneous computing 

      Cristal, Adrian; Unsal, Osman S.; Martorell, Xavier; Carpenter, Paul Matthew; de la Cruz, Raul; Bautista Gomez, Leonardo; Jimenez, Daniel; Alvarez, Carlos; Salami, Behzad; Madonar, Sergi; Pericàs Gleim, Miquel; Trancoso, Pedro; vor dem Berge, Micha; Billung-Meyer, Gunnar; Krupop, Stefan; Christmann, Wolfgang; Klawonn, Frank; Mihklafi, Amani; Becker, Tobias; Gaydadjiev, Georgi; Salomonsson, Hans; Dubhashi, Devdatt; Port, Oron; Hadar, Elad; Etsion, Yoav; Fetzer, Christof; Hagemeyer, Jens; Jungeblut, Thorsten; Kucza, Nils; Kaiser, Martin; Porrmann, Mario; Pasin, Marcelo; Schiavoni, Valerio; Rocha, Isabelly; Göttel, Christian; Felber, Pascal (ACM, 2018-07-15)
      Conference lecture
      Open Access
      LEGaTO is a three-year EU H2020 project which started in December 2017. The LEGaTO project will leverage task-based programming models to provide a software ecosystem for Made-in-Europe heterogeneous hardware composed of ...
    • LEGaTO: Low-energy, secure, and resilient toolset for heterogeneous computing 

      Salami, Behzad; Parasyris, Konstantinos; Cristal Kestelman, Adrián; Unsal, Osman Sabri; Martorell Bofill, Xavier; Carpenter, Paul Matthew; De la Cruz Martínez, Raul; Bautista Gomez, Leonardo; Jiménez González, Daniel; Álvarez Martínez, Carlos; Nabavilarimi, Seyed Saber; Madonar Soria, Sergi (Institute of Electrical and Electronics Engineers (IEEE), 2020)
      Conference report
      Open Access
      The LEGaTO project leverages task-based programming models to provide a software ecosystem for Made in-Europe heterogeneous hardware composed of CPUs, GPUs, FPGAs and dataflow engines. The aim is to attain one order of ...
    • LEGaTO: towards energy-efficient, secure, fault-tolerant toolset for heterogeneous computing 

      Cristal Kestelman, Adrián; Unsal, Osman S.; Martorell, Xavier; Carpenter, Paul Matthew; de la Cruz, Raul; Bautista Gomez, Leonardo; Jimenez, Daniel; Alvarez, Carlos; Salami, Behzad; Madonar, Sergi; Pericàs, Miquel; Trancoso, Pedro; von dem Berge, Micha; Billung-Meyer, Gunnar; Krupop, Stefan; Christmann, Wolfgang; Klawonn, Frank; Mihklafi, Amani; Becker, Tobias; Gaydadjiev, Georgi; Salomonsson, Hans; Dubhashi, Devdatt; Port, Oron; Etsion, Yoav; Nowack, Vesna; Fetzer, Christof; Hagemeyer, Jens; Jungeblut, Thorsten; Kucza, Nils; Kaiser, Martin; Porrmann, Mario; Pasin, Marcelo; Schiavoni, Valerio; Rocha, Isabelly; Göttel, Christian; Felber, Pascal (Association for Computing Machinery (ACM), 2018-05-08)
      Conference lecture
      Open Access
      LEGaTO is a three-year EU H2020 project which started in December 2017. The LEGaTO project will leverage task-based programming models to provide a software ecosystem for Made-in-Europe heterogeneous hardware composed of ...
    • Main memory in HPC: do we need more, or could we live with less? 

      Živanovič, Darko; Pavlovic, Milan; Radulović, Milan; Shin, Hyunsung; Son, Jongpil; McKee, Sally A.; Carpenter, Paul Matthew; Radojković, Petar; Ayguadé Parra, Eduard (2017-03)
      Article
      Open Access
      An important aspect of High-Performance Computing (HPC) system design is the choice of main memory capacity. This choice becomes increasingly important now that 3D-stacked memories are entering the market. Compared with ...
    • Mainstream vs. emerging HPC: metrics, trade-offs and lessons learned 

      Radulović, Milan; Asifuzzaman, Kazi; Živanovič, Darko; Rajovic, Nikola; Colin de Verdiére, Guillaume; Pleiter, Dirk; Marazakis, Manolis; Kallimanis, Nikolaos; Carpenter, Paul Matthew; Radojković, Petar; Ayguadé Parra, Eduard (Institute of Electrical and Electronics Engineers (IEEE), 2018)
      Conference report
      Open Access
      Various servers with different characteristics and architectures are hitting the market, and their evaluation and comparison in terms of HPC features is complex and multidimensional. In this paper, we share our experience ...
    • Mapping stream programs onto heterogeneous multiprocessor systems 

      Carpenter, Paul Matthew; Ramírez Bellido, Alejandro; Ayguadé Parra, Eduard (ACM Press, NY, 2009)
      Conference lecture
      Restricted access - publisher's policy
      This paper presents a partitioning and allocation algorithm for an iterative stream compiler, targeting heterogeneous multiprocessors with constrained distributed memory and any communications topology. We introduce a ...
    • Memory demands in disaggregated HPC: How accurate do we need to be? 

      Vieira Zacarias, Felippe; Carpenter, Paul Matthew; Petrucci, Vinicius (Institute of Electrical and Electronics Engineers (IEEE), 2021)
      Conference report
      Open Access
      Disaggregated memory has recently been proposed as a way to allow flexible and fine-grained allocation of memory capacity, mitigating the mismatch between fixed per-node resource provisioning and the needs of the submitted ...
    • OmpSs-2@Cluster: Distributed memory execution of nested OpenMP-style tasks 

      Aguilar Mena, Jimmy; Ali, Omar Shaaban Ibrahim; Beltran Querol, Vicenç; Carpenter, Paul Matthew; Ayguadé Parra, Eduard; Labarta Mancho, Jesús José (Springer Nature, 2022)
      Conference report
      Open Access
      State-of-the-art programming approaches generally have a strict division between intra-node shared memory parallelism and inter-node MPI communication. Tasking with dependencies offers a clean, dependable abstraction for ...
    • Paving the Way Towards a Highly Energy-Efficient and Highly Integrated Compute Node for the Exascale Revolution: The ExaNoDe Approach 

      Rigo, Alvise; Pinto, Christian; Pouget, Kevin; Raho, Daniel; Dutoit, Denis; Martinez, Pierre-Yves; Doran, Chris; Benini, Luca; Mavroidis, Iakovos; Marazakis, Manolis; Bartsch, Valeria; Lonsdale, Guy; Pop, Antoniu; Goodacre, John; Colliot, Annaïk; Carpenter, Paul Matthew; Radojković, Petar; Pleiter, Dirk; Drouin, Dominique; Dupont de Dinechin, Benoît (IEEE, 2017-09-28)
      Conference lecture
      Open Access
      Power consumption and high compute density are the key factors to be considered when building a compute node for the upcoming Exascale revolution. Current architectural design and manufacturing technologies are not able ...
    • PerfBound: Conserving Energy with Bounded Overheads in On/Off-Based HPC Interconnects 

      Saravanan, Karthikeyan P.; Carpenter, Paul Matthew (IEEE, 2018-07-01)
      Article
      Open Access
      Energy and power are key challenges in high-performance computing. System energy efficiency must be significantly improved, and this requires greater efficiency in all subcomponents. An important target of optimization is ...
    • Power/performance evaluation of Energy Efficient Ethernet (EEE) for High Performance Computing 

      Karthikeyan Palavedu, Saravanan; Carpenter, Paul Matthew; Ramírez Bellido, Alejandro (Institute of Electrical and Electronics Engineers (IEEE), 2013)
      Conference report
      Restricted access - publisher's policy
      As of June 2012, 41 % of all systems in the TOP5OO use Gigabit Ethernet. Ethernet has been a strong contender in the HPC interconnect market for its competitive performance and low cost. However, until recently, little ...
    • PROFET: modeling system performance and energy without simulating the CPU 

      Radulović, Milan; Sánchez-Verdejo, Rommel; Carpenter, Paul Matthew; Radojković, Petar; Jacob, Bruce; Ayguadé Parra, Eduard (2019-06)
      Article
      Open Access
      The approaching end of DRAM scaling and expansion of emerging memory technologies is motivating a lot of research in future memory systems. Novel memory systems are typically explored by hardware simulators that are slow ...
    • Rebalancing the core front-end through HPC code analysis 

      Milic, Ugljesa; Carpenter, Paul Matthew; Rico, Alejandro; Ramirez, Alex (IEEE, 2016-09-25)
      Conference lecture
      Open Access
      There is a need to increase performance under the same power and area envelope to achieve Exascale technology in high performance computing (HPC). The today's chip multiprocessor (CMP) design is tailored by traditional ...