Suchergebnisse - Parallel program execution tracing

Making applications faster by asynchronous execution: Slowing down processes or relaxing MPI collectives von Afzal, Ayesha, Hager, Georg, Markidis, Stefano, Wellein, Gerhard

“… Comprehending the performance bottlenecks at the core of the intricate hardware–software interactions exhibited by highly parallel programs on HPC clusters is crucial …”
Volltext

HPCTOOLKIT: tools for performance analysis of optimized parallel programs von Adhianto, L., Banerjee, S., Fagan, M., Krentel, M., Marin, G., Mellor-Crummey, J., Tallent, N. R.

“… HPCTOOLKIT is an integrated suite of tools that supports measurement, analysis, attribution, and presentation of application performance for both sequential and parallel programs …”
Volltext

Interactive Performance Visualization and Analysis of Execution Traces for Pattern-Based Parallel Programming von Ernstsson, August, Frankell, Elin, Kessler, Christoph

“… We introduce the design and implementation of a performance visualization system for high-level programming of heterogeneous parallel systems …”
Volltext

Reinforcement Learning for Load-Balanced Parallel Particle Tracing von Xu, Jiayi, Guo, Hanqi, Shen, Han-Wei, Raj, Mukund, Wurster, Skylar W., Peterka, Tom

“… We explore an online reinforcement learning (RL) paradigm to dynamically optimize parallel particle tracing performance in distributed-memory systems …”
Volltext

Parallel execution tracing: An alternative solution to exploit under-utilized resources in multi-core architectures for control-flow checking von Maghsoudloo, Mohammad, Zarandi, Hamid

“… The analysis of a key point leads to introduction of the proposed technique: employing under-utilized CPU resources in multi-core processors to check the execution flow of the programs concurrently and in parallel with the main executions …”
Volltext

Making Applications Faster by Asynchronous Execution: Slowing Down Processes or Relaxing MPI Collectives von Afzal, Ayesha, Hager, Georg, Markidis, Stefano, Wellein, Gerhard

“… Comprehending the performance bottlenecks at the core of the intricate hardware-software interactions exhibited by highly parallel programs on HPC clusters is crucial …”
Volltext

Loop-level parallelism in numeric and symbolic programs von Larus, J.R.

“… A parallelism analyzer uses information from the trace to simulate parallel execution of the program …”
Volltext

Memory Considerations for Low Energy Ray Tracing von Kopta, D., Shkurko, K., Spjut, J., Brunvand, E., Davis, A.

“… We propose two hardware mechanisms to decrease energy consumption on massively parallel graphics processors for ray tracing …”
Volltext

HardTaint: Production-Run Dynamic Taint Analysis via Selective Hardware Tracing von Zhang, Yiyu, Liu, Tianyi, Wang, Yueyang, Qi, Yun, Ji, Kai, Tang, Jian, Wang, Xiaoliang, Li, Xuandong, Zuo, Zhiqiang

“… HardTaint adopts a hybrid and systematic design which combines static analysis, selective hardware tracing and parallel graph processing techniques …”
Volltext

Efficient large-scale heterogeneous debugging using dynamic tracing von Nadeau, Didier, Ezzati-Jivan, Naser, Dagenais, Michel R.

“… An alternative, to interactively follow the execution flow of a program, is tracing within the debugging environment, as long as the tracer has a minimal overhead …”
Volltext

EVMTracer: Dynamic Analysis of the Parallelization and Redundancy Potential in the Ethereum Virtual Machine von Hu, Xiaowen, Burgstaller, Bernd, Scholz, Bernhard

“… From the runtime dependence graphs, we can deduce valuable metrics about program execution characteristics, including the degree of parallelization and computational redundancies …”
Volltext

Trace profiling: Scalable event tracing on high-end parallel systems von Mohror, Kathryn, Karavanic, Karen L.

“… ► Trace profiling can reduce program perturbation by reducing write overheads. ► Scalable visualization is achieved through pattern detection-based trace reduction …”
Volltext

Wait Analysis of Distributed Systems Using Kernel Tracing von Giraldeau, Francis, Dagenais, Michel

“… We propose a new class of profiler for distributed and heterogeneous systems. In these systems, a task may wait for the result of another task, either locally …”
Volltext

GPU-based four-dimensional general-relativistic ray tracing von Kuchelmeister, Daniel, Müller, Thomas, Ament, Marco, Wunner, Günter, Weiskopf, Daniel

“… The ray tracing code itself is implemented for parallel …”
Volltext

Exploring hidden coherency of Ray-Tracing for heterogeneous systems using online feedback methodology von Kao, Chih-Chen, Hsu, Wei-Chung

“… Although naturally adopting an embarrassingly parallel paradigm, Ray-Tracing is also categorized as an irregular program that is troublesome to run on graphics processing units (GPUs …”
Volltext

Debugging and analysis of large-scale parallel programs von Mellor-Crummey, John Michael

“… Second, invasive, interactive analysis can distort a parallel program's execution beyond recognition …”
Volltext

Reinforcement Learning for Load-balanced Parallel Particle Tracing von Xu, Jiayi, Guo, Hanqi, Han-Wei, Shen, Raj, Mukund, Wurster, Skylar W, Peterka, Tom

“… We explore an online reinforcement learning (RL) paradigm to dynamically optimize parallel particle tracing performance in distributed-memory systems …”
Volltext

SEED: A Statically Greedy and Dynamically Adaptive Approach for Speculative Loop Execution von Gao, Lin, Li, Lian, Xue, Jingling, Yew, Pen-Chung

“… Research on compiler techniques for thread-level loop speculation has so far remained on studying its performance limits: loop candidates that are worthy of …”
Volltext

RAMP: A prototype for massively parallelized Monte Carlo raytracing von Cassella, G., Nilsen, G.J.

“… Graphics processing unit (GPU) acceleration is a promising strategy to reduce the hardware cost and execution time of simulations, thanks to the massively parallelizable nature of the MCR algorithm …”
Volltext

Efficient Methods for Trace Analysis Parallelization von Reumont-Locke, Fabien, Ezzati-Jivan, Naser, Dagenais, Michel R.

“… Tracing provides a low-impact, high-resolution way to observe the execution of a system …”
Volltext