Publications

My publications are also listed on my Google Scholar profile.

2018

  • Kyunghun Kim et. al. Toward Developing a Unimem OFI Provider for MPI Support. EuroMPI 2018 (poster).

  • Milan Radulovic, Kazi Asifuzzaman, Darko Zivanovic, Nikola Rajovic, Guillaume Colin de Verdière, Dirk Pleiter, Manolis Marazakis, Nikolaos Kallimanis, Paul Carpenter, Petar Radojković and Eduard Ayguadé, Mainstream vs. Emerging HPC: Metrics, Trade-offs and Lessons Learned. Accepted to SBAC-PAD 2018

  • Renan Fischer e Silva, E-EON Energy-Efficient and Optimized Networks for Hadoop.pdf. PhD thesis, 3 May 2018. Advisor: Paul Carpenter. Excel·lent cum laude. pdf

  • Milan Radulovic, Kazi Asifuzzaman, Paul Carpenter, Petar Radojković and Eduard Ayguadé. HPC benchmarking: scaling right and looking beyond the average. Accepted to Euro-Par 2018.

  • Karthikeyan Saravanan and Paul Carpenter. PerfBound: Conserving energy with bounded overheads in On/Off-based HPC Interconnect. IEEE Transactions on Computers, Volume: 67, Issue: 7, July 1 2018. pdf doi

2017

  • Rajiv Nishtala, Paul Carpenter, Vinicius Petrucci and Xavier Martorell. The Hipster Approach for Improving Cloud System Efficiency. ACM Transactions on Computer Systems, Volume 35, Issue 3. preprint doi

  • Renan Fischer e Silva and Paul Carpenter. Energy Efficient Ethernet on MapReduce Clusters: Packet Coalescing To Improve 10GbE Links. IEEE/ACM Transactions on Networking, Volume 25, Issue 5. pdf doi

  • Luis A. Garrido and Paul Carpenter. vMCA: Memory Capacity Aggregation and Management in Cloud Environments. IEEE 23rd International Conference on Parallel and Distributed Systems (IEEE ICPADS 2017). pdf

  • Renan Fischer e Silva and Paul Carpenter. Interconnect Energy Savings and Lower Latency Networks in Hadoop Clusters: The Missing Link. 42nd Annual IEEE Conference on Local Computer Networks (LCN), 2017 pdf doi

  • Renan Fischer e Silva and Paul Carpenter. High Throughput and Low Latency on Hadoop Clusters using Explicit Congestion Notification: The Untold Truth. IEEE Cluster 2017. pdf doi

  • Alvise Rigo et al. Paving the way towards a highly energy-efficient and highly integrated compute node for the Exascale revolution: the ExaNoDe approach. Euromicro Symposium on Digital System Design, DSD 2017. pdf doi

  • Luis Garrido and Paul Carpenter. Aggregating and Managing Memory Across Computing Nodes in Cloud Environments. 12th Workshop on Virtualization in High-Performance Cloud Computing (VHPC'17). pdf doi
  • Ugljesa Milic, Alejandro Rico, Paul Carpenter and Alex Ramirez. Sharing the Instruction Cache Among Lean Cores on an Asymmetric CMP for HPC Applications. International Symposium on Performance Analysis of Systems and Software (ISPASS 2017). pdf doi

  • Darko Zivanovic, Milan Pavlovic, Milan Radulovic, Hyunsung Shin, Jongpil Son, Sally A. McKee, Paul M. Carpenter, Petar Radojkovic and Eduard Ayguade. Main Memory in HPC: Do We Need More, or Could We Live With Less? ACM Transactions on Architecture and Code Optimization (TACO), Volume 14, Issue 1, April 2017. pdf doi

  • Gina Alioto, Paul Carpenter, Christophe Avare, Marcus Leich, Adrián Cristal and Osman Unsal. RETHINK big: European Roadmap for Hardware and Networking Optimizations for Big Data. Design, Automation and Test in Europe (DATE 2017). pdf doi

  • Rajiv Nishtala, Paul Carpenter, Vinicius Petrucci, Xavier Martorell. Hipster: Hybrid Task Manager for Latency-Critical Cloud Workloads. 23rd IEEE Symposium on High Performance Computer Architecture (HPCA 2017). draft pdf doi HiPEAC Paper Award

  • Theo Ungerer and Paul Carpenter. EuroLab-4-HPC Long-Term Vision on High-Performance Computing. 2017 pdf arXiv

2016

  • Renan Fischer e Silva and Paul Carpenter. Controlling Network Latency in Mixed Hadoop Clusters: Do We Need Active Queue Management?. 41st Annual IEEE Conference on Local Computer Networks (LCN 2016). pdf doi

  • Karthikeyan P. Saravanan, Performance-aware Energy Optimisations in Networks for HPC. PhD thesis, 2 November 2016. Advisors: Alex Ramirez, Paul Carpenter. pdf

  • Ugljesa Milic, Paul Carpenter, Alejandro Rico, and Alex Ramirez. Rebalancing the Core Front-End through HPC Code Analysis. 2016 IEEE International Symposium on Workload Characterisation (IISWC 2016). pdf doi

  • Darko Zivanovic, Milan Radulovic, German Llort, David Zaragoza, Janko Strassburg, Paul Carpenter, Petar Radojkovic and Eduard Ayguade. Large-Memory Nodes for Energy Efficient High-Performance Computing. The International Symposium on Memory Systems (MEMSYS), 2016. pdf slides doi Best paper award.

  • Theo Ungerer, Paul Carpenter and Mike Knebel. Preliminary EuroLab-4-HPC Roadmap. 2016. pdf bibtex.

  • Victor Garcia, Alejandro Rico, Carlos Villavieja, Paul Carpenter, Nacho Navarro, and Alex Ramirez. Adaptive Runtime-Assisted Block Prefetching on Chip-Multiprocessors. International Journal of Parallel Programming, pp.1–21, 2016 bibtex doi.

  • Manolis Marazakis, John Goodacre, Didier Fuin, Paul Carpenter, John Thomson, Emil Matus, Antimo Bruno, Per Stenstrom, Jerome Martin, Yves Durand and Isabelle Dor. EUROSERVER: Share-Anything Scale-Out Micro-Server Design. Design, Automation and Test in Europe (DATE), 2016. pdf bibtex

  • Gina Alioto, Christophe Avare, Paul Carpenter, Marcus Leich and Osman Unsal. Rethink Big Roadmap (European Roadmap for Hardware and Networking Optimizations for Big Data). 2016. pdf bibtex.

  • Petar Radojković, Paul M. Carpenter, Miquel Moretó, Vladimir Čakarević, Javier Verdú, Alex Pajuelo, Francisco J. Cazorla, Mario Nemirovsky and Mateo Valero. Thread Assignment in Multicore/Multithreaded Processors: A Statistical Approach. IEEE Transactions on Computers, Vol. 65, Issue 1, Jan. 2016. Featured article of the month. pdf video bibtex doi.

2015

  • Branimir Dickov, Paul M. Carpenter, Miquel Pericas, and Eduard Ayguade. Self-Tuned Software-Managed Energy Reduction in InfiniBand Links. 21st IEEE International Conference on Parallel and Distributed Systems (ICPADS), 2015. pdf bibtex doi

  • Branimir Dickov. MPI Layer Techniques to Improve Network Energy Efficiency. PhD thesis, 10 December 2015. Advisors: Eduard Ayguade, Paul Carpenter, Miquel Pericas. Excel·lent cum laude. pdf tdx

  • Karthikeyan P. Saravanan, Paul M. Carpenter and Alex Ramirez. Exploring Multiple Sleep Modes in On/Off based Energy Efficient HPC Networks. 33rd IEEE International Conference on Computer Design (ICCD), 2015. pdf bibtex doi

  • Renan Fischer e Silva, Paul M. Carpenter. Exploring Interconnect Energy Savings Under East-West Traffic Pattern of MapReduce Clusters. 40th IEEE Conference on Local Computer Networks (LCN), 2015. pdf bibtex doi

2014

  • Branimir Dickov, Miquel Pericas, Paul Carpenter, Nacho Navarro, and Eduard Ayguade. Analyzing performance improvements and energy savings in Infiniband Architecture using network compression. IEEE 26th International Symposium on Computer Architecture and High Performance Computing, SBAC-PAD 2014. pdf bibtex doi

  • Yves Durand, Paul M. Carpenter, Stefano Adami, Angelos Bilas, Denis Dutoit, Alexis Farcy, Georgi Gaydadjiev, John Goodacre, Manolis Katevenis, Manolis Marazakis, Emil Matus, Iakovos Mavroidis, and John Thomson. EUROSERVER: Energy Efficient Node for European Micro-servers. Euromicro Symposium on Digital System Design, DSD-2014. pdf bibtex doi

  • Victor Garcia, Alejandro Rico, Carlos Villavieja, Paul Carpenter, Alex Ramirez, and Nacho Navarro. Adaptive Runtime-Assisted Block Prefetching on Chip-Multiprocessors. Second International Workshop on On-chip memory hierarchies and interconnects: organization, management and implementation, OMHI 2014. pdf Best paper award.

  • Branimir Dickov, Miquel Pericas, Paul Carpenter, Nacho Navarro, and Eduard Ayguade. Software-Managed Power Reduction in Infiniband Links. 43rd International Conference on Parallel Processing, ICPP-2014. pdf bibtex doi

  • Karthikeyan P. Saravanan, Paul M. Carpenter, and Alex Ramirez. A Performance Perspective on Energy Efficient HPC Links. 28th ACM international conference on Supercomputing, ICS14. pdf bibtex doi

2013

  • Nikola Rajovic, Paul Carpenter, Isaac Gelado, Nikola Puzovic, Alex Ramirez, and Mateo Valero. Supercomputing with Commodity CPUs: Are Mobile SoCs Ready for HPC? International Conference on High Performance Computing, Networking, Storage and Analysis, SC13. pdf bibtex doi Best student paper award

  • Karthikeyan P. Saravanan, Paul M. Carpenter, and Alex Ramirez. Power/Performance evaluation of Energy Efficient Ethernet (EEE) for High Performance Computing, 2013 IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS), 2013. pdf bibtex doi

2012

  • Petar Radojkovic, Paul M. Carpenter, Miquel Moreto, Alex Ramirez, and Francisco J. Cazorla. Kernel Partitioning of Streaming Applications: A Statistical Approach to an NP-complete Problem, 45th Annual IEEE/ACM International Symposium on Microarchitecture, MICRO 2012. pdf bibtex doi HiPEAC Paper Award

2011 or before

  • Paul M. Carpenter, Alex Ramirez, and Eduard Ayguade. The Abstract Streaming Machine: Compile-Time Performance Modelling of Stream Programs on Heterogeneous Multiprocessors. Transactions on HiPEAC, 5(3). pdf

  • Harm Munk, Eduard Ayguade, Cedric Bastoul, Paul Carpenter, Zbigniew Chamski, et al. ACOTES Project: Advanced Compiler Technologies for Embedded Streaming. International Journal of Parallel Programming, 39(3) pdf bibtex doi

  • Paul M. Carpenter, Alex Ramirez, and Eduard Ayguade. Starsscheck: A tool to find errors in task-based parallel programs. Euro-Par 2010 pdf bibtex doi

  • Paul M. Carpenter, Alex Ramirez, and Eduard Ayguade. Buffer sizing for self-timed stream programs on heterogeneous distributed memory multiprocessors. HiPEAC 2010 Conference pdf bibtex springerlink

  • Paul M. Carpenter, Alex Ramirez, and Eduard Ayguade. Mapping Stream Programs onto Heterogeneous Multiprocessor Systems. 2009 International Conference on Compilers, Architecture, and Synthesis for Embedded Systems, CASES 2009pdf bibtex doi
    © ACM 2009. This is the author's version of the work. It is posted here by permission of the ACM for your personal use. Not for redistribution. The definitive version is published in CASES 2009 http://doi.acm.org/10.1145/1629395.1629406

  • Paul M. Carpenter, Alex Ramirez, and Eduard Ayguade. The Abstract Streaming Machine: Compile-time Performance Modelling of Stream Programs on Heterogeneous Multiprocessors. SAMOS Workshop 2009, pages 12–23. pdf bibtex springerlink (best paper award)

PhD thesis

  • Paul M. Carpenter.Running Stream-like Programs on Heterogeneous Multi-core Systems, 24 October 2011, Excel·lent cum laude pdf HTML bibtex tdx
X