G
Gokcen Kestor
Researcher at Pacific Northwest National Laboratory
Publications - 52
Citations - 718
Gokcen Kestor is an academic researcher from Pacific Northwest National Laboratory. The author has contributed to research in topics: Transactional memory & Supercomputer. The author has an hindex of 12, co-authored 52 publications receiving 591 citations. Previous affiliations of Gokcen Kestor include Barcelona Supercomputing Center & Oak Ridge National Laboratory.
Papers
More filters
Proceedings ArticleDOI
Quantifying the energy cost of data movement in scientific applications
TL;DR: In the exascale era, the energy cost of moving data across the memory hierarchy is expected to be two orders of magnitude higher than the cost of performing a double-precision floating point operation.
Proceedings ArticleDOI
Understanding the propagation of transient errors in HPC applications
TL;DR: This work proposes a fault propagation framework to analyze how faults propagate in MPI applications and to understand their vulnerability to faults, and employs machine learning technique to derive application fault propagation models that can be used to estimate the number of corrupted memory locations at runtime.
Proceedings ArticleDOI
RTHMS: a tool for data placement on hybrid memory system
TL;DR: This work argues that intelligent, fine-grained data placement can achieve higher performance than default setups and presents an algorithm for data placement on hybrid-memory systems, based on a set of single-object allocation rules and global data placement decisions.
Proceedings ArticleDOI
RMS-TM: a comprehensive benchmark suite for transactional memory systems
TL;DR: RMS-TM is introduced, a Transactional Memory benchmark suite composed of seven real-world applications from the Recognition, Mining and Synthesis domain that provide a mix of short and long transactions with small/large read and write sets with low/medium/high contention rates.
Proceedings ArticleDOI
Exploring the Performance Benefit of Hybrid Memory System on HPC Environments
TL;DR: This paper analyzes the Intel KNL system and quantifies the impact of the most important factors on the application performance by using a set of applications that are representative of scientific and data-analytics workloads to show that applications with regular memory access benefit from MCDRAM.