Paul Matthew Carpenter

Paul Matthew Carpenter

Auto-generated profile, based on publicly available information

Paul Matthew Carpenter

Barcelona Supercomputing Center, Barcelona, Spain

Research Focus & Metrics

Academic Career Length

27Years (2000-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 November 2013
Verified
Conference Paper
Open access
PDF file
NRNikola Rajovic
Nikola Rajovic
PCPaul M. Carpenter
Paul M. Carpenter
IGIsaac Gelado
Isaac Gelado
NPNikola Puzovic
Nikola Puzovic
ARAlex Ramirez
Alex Ramirez
MVMateo Valero
Mateo Valero
In the late 1990s, powerful economic forces led to the adoption of commodity desktop processors in high-performance computing. This transformation has been so effective that the June 2013 TOP500 list is still dominated by x86.\ud In 2013, the largest commodity market in computing is not PCs or servers, but mobile computing, comprising smart-phones and tablets, most of which are built with ARM-based SoCs. This leads to the suggestion that once mobile SoCs deliver sufficient performance, mobile SoCs can help reduce the cost of HPC.\ud This paper addresses this question in detail. We analyze the trend in mobile SoC performance, comparing it with the similar trend in the 1990s. We also present our experience evaluating performance and efficiency of mobile SoCs, deploying a cluster and evaluating the network and scalability of production applications. In summary, we give a first answer as to whether mobile SoCs are ready for HPC.Peer ReviewedPostprint (published version

1 February 2017
Verified
Conference Paper
Closed access
RNRajiv Nishtala
Rajiv Nishtala
PCPaul Carpenter
Paul Carpenter
VPVinicius Petrucci
Vinicius Petrucci
XMXavier Martorell
Xavier Martorell
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 strict levels of quality-of-service (QoS) to meet user expectations, making it challenging to reduce power consumption due to increasing performance demands. This paper introduces Hipster, a technique that combines heuristics and reinforcement learning to manage latency-critical workloads. Hipster's goal is to improve resource efficiency in data centers while respecting the QoS of the latency-critical workloads. Hipster achieves its goal by exploring heterogeneous multi-cores and dynamic voltage and frequency scaling (DVFS). To improve data center utilization and make best usage of the available resources, Hipster can dynamically assign remaining cores to batch workloads without violating the QoS constraints for the latency-critical workloads. We perform experiments using a 64-bit ARM big.LITTLE platform, and show that, compared to prior work, Hipster improves the QoS guarantee for Web-Search from 80% to 96%, and for Memcached from 92% to 99%, while reducing the energy consumption by up to 18%.

29 May 2024 in IEEE Transactions on Parallel and Distributed Systems
Verified
Journal Article
Open access
ATAhmad Tarraf
Ahmad Tarraf
MSMartin Schreiber
Martin Schreiber
ACAlberto Cascajo
Alberto Cascajo
JBJean-Baptiste Besnard
Jean-Baptiste Besnard
MVMarc-André Vef
Marc-André Vef
FWFelix Wolf
Felix Wolf
With the increase of complex scientific simulations driven by workflows and heterogeneous workload profiles, managing system resources effectively is essential for improving performance and system throughput, especially due to trends like heterogeneous HPC and deeply integrated systems with on-chip accelerators. For optimal resource utilization, dynamic resource allocation can improve productivity across all system and application levels, by adapting the applications' configurations to the system's resources. In this context, malleable jobs, which can change resources at runtime, can increase the system throughput and resource utilization while bringing various advantages for HPC users (e.g., shorter waiting time). Malleability has received much attention recently, even though it has been an active research area for almost two decades [1]. This paper presents the state-of-the-art of malleable implementations in HPC systems, targeting mainly malleability in compute and I/O resources. Based on our experiences, we state our current concerns and list future opportunities for research.

6 March 2017 in ACM Transactions on Architecture and Code Optimization
Verified
Journal Article
Open access
DZDarko Zivanovic
Darko Zivanovic
MPMilan Pavlovic
Milan Pavlovic
MRMilan Radulovic
Milan Radulovic
HSHyunsung Shin
Hyunsung Shin
JSJongpil Son
Jongpil Son
EAEduard Ayguadé
Eduard Ayguadé
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 conventional Dual In-line Memory Modules (DIMMs), 3D memory chiplets provide better performance and energy efficiency but lower memory capacities. Therefore, the adoption of 3D-stacked memories in the HPC domain depends on whether we can find use cases that require much less memory than is available now. This study analyzes the memory capacity requirements of important HPC benchmarks and applications. We find that the High-Performance Conjugate Gradients (HPCG) benchmark could be an important success story for 3D-stacked memories in HPC, but High-Performance Linpack (HPL) is likely to be constrained by 3D memory capacity. The study also emphasizes that the analysis of memory footprints of production HPC applications is complex and that it requires an understanding of application scalability and target category, i.e., whether the users target capability or capacity computing. The results show that most of the HPC applications under study have per-core memory footprints in the range of hundreds of megabytes, but we also detect applications and use cases that require gigabytes per core. Overall, the study identifies the HPC applications and use cases with memory footprints that could be provided by 3D-stacked memory chiplets, making a first step toward adoption of this novel technology in the HPC domain.

1 August 2014
Verified
Conference Paper
Closed access
YDYves Durand
Yves Durand
PCPaul M. Carpenter
Paul M. Carpenter
SAStefano Adami
Stefano Adami
ABAngelos Bilas
Angelos Bilas
DDDenis Dutoit
Denis Dutoit
JTJohn Thomson
John Thomson
EUROSERVER is a collaborative project that aims to dramatically improve data centre energy-efficiency, cost, and software efficiency. It is addressing these important challenges through the coordinated application of several key recent innovations: 64-bit ARM cores, 3D heterogeneous silicon-on-silicon integration, and fully-depleted silicon-on-insulator (FD SOI) process technology, together with new software techniques for efficient resource management, including resource sharing and workload isolation. We are pioneering a system architecture approach that allows specialized silicon devices to be built even for low-volume markets where NRE costs are currently prohibitive. The EUROSERVER device will embed multiple silicon "chiplets" on an active silicon interposer. Its system architecture is being driven by requirements from three use cases: data centres and cloud computing, telecom infrastructures, and high-end embedded systems. We will build two fully integrated full-system prototypes, based on a common micro-server board, and targeting embedded servers and enterprise servers.

11 October 2009
Verified
Conference Paper
Open access
PDF file
PCPaul M. Carpenter
Paul M. Carpenter
ARAlex Ramirez
Alex Ramirez
EAEduard Ayguadé
Eduard Ayguadé
This paper presents a partitioning and allocation algorithm\ud for an iterative stream compiler, targeting heterogeneous\ud multiprocessors with constrained distributed memory and\ud any communications topology. We introduce a novel definition\ud of connectedness that enables the algorithm to model\ud the capabilities of the compiler. The algorithm uses convexity\ud and connectedness constraints to produce partitions that\ud are easier to compile and require short pipelines. Software\ud pipelining is an effective transformation, but it increases\ud memory footprint and latency, and has a startup overhead.\ud Our algorithm takes account of these downstream costs.\ud We show results for the StreamIt 2.1.1 benchmarks for\ud an SMP, 2 × 2 mesh, SMP plus accelerator, and IBM QS20\ud blade, which has two Cell processors. Our results show that\ud the average performance is within 5% of the unrestricted\ud optimum found using a brute force search, while seldom requiring\ud software pipelining. The heuristic is robust, and fast\ud enough to be inside the feedback loop of an iterative compiler.Postprint (published version