• Publications
  • Influence
Exploring Traditional and Emerging Parallel Programming Models Using a Proxy Application
TLDR
In this paper, we compare several implementations of LULESH, a proxy application for shock hydrodynamics, to determine strengths and weaknesses of different programming models for parallel computation. Expand
  • 151
  • 29
  • PDF
Efficiently exploring architectural design spaces via predictive modeling
TLDR
An automated approach that builds accurate, confident predictive design-space models that can be queried to predict performance impacts of architectural changes. Expand
  • 322
  • 28
  • PDF
Pathways of Relevance: Exploring Inflows of Knowledge into Subunits of Multinational Corporations
  • M. Schulz
  • Business, Computer Science
  • Organ. Sci.
  • 1 July 2003
TLDR
To understand what determines knowledge flows into organizational subunits, the study reported here examines the relevance of the knowledge to the operations performed at the receiving subunit. Expand
  • 262
  • 22
Bounding energy consumption in large-scale MPI programs
TLDR
We developed a system that determines a bound on the energy savings for an application by taking as inputs the application communication trace and the cluster power characteristics and outputs a schedule that realizes this bound. Expand
  • 167
  • 16
  • PDF
A regression-based approach to scalability prediction
TLDR
We explore novel regression-based approaches to predict parallel program scalability using several program executions on a small subset of the processors to predict execution time on larger numbers of processors. Expand
  • 165
  • 12
  • PDF
Stack Trace Analysis for Large Scale Debugging
TLDR
We present the Stack Trace Analysis Tool (STAT) to aid in debugging extreme-scale applications. Expand
  • 140
  • 11
  • PDF
Beyond DVFS: A First Look at Performance under a Hardware-Enforced Power Bound
TLDR
Dynamic Voltage Frequency Scaling (DVFS) has been the tool of choice for balancing power and performance in high-performance computing (HPC). Expand
  • 170
  • 9
  • PDF
Hybrid MPI/OpenMP power-aware computing
TLDR
We use a new power-aware performance prediction model of hybrid MPI/OpenMP applications to derive a novel algorithm for power-efficient execution of realis tic applications from ASCS equoia and N PB MZ bench marks. Expand
  • 138
  • 8
  • PDF
Fault resilience of the algebraic multi-grid solver
TLDR
We present an approach that analyzes the vulnerability of applications to faults, systematically reduces it by protecting the most vulnerable components and predicts application vulnerability at large scales. Expand
  • 69
  • 8
ARCHER: Effectively Spotting Data Races in Large OpenMP Applications
TLDR
We propose the first OpenMP data race checker, ARCHER, that achieves high accuracy, low overheads on large applications, and portability. Expand
  • 41
  • 7
  • PDF