Folgen
Benjamin Klenk
Benjamin Klenk
Research Scientist, NVIDIA Corp.
Bestätigte E-Mail-Adresse bei nvidia.com
Titel
Zitiert von
Zitiert von
Jahr
An Overview of MPI Characteristics of Exascale Proxy Applications
B Klenk, H Fröning
International Supercomputing Conference, 217-236, 2017
462017
An in-network architecture for accelerating shared-memory multiprocessor collectives
B Klenk, N Jiang, G Thorson, L Dennison
2020 ACM/IEEE 47th Annual International Symposium on Computer Architecture …, 2020
312020
Relaxations for High-Performance Message Passing on Massively Parallel SIMT Processors
B Klenk, H Fröning, H Eberle, L Dennison
IEEE International Parallel and Distributed Processing Symposium (IPDPS …, 2017
272017
Energy-efficient collective reduce and allreduce operations on distributed GPUs
L Oden, B Klenk, H Fröning
Cluster, Cloud and Grid Computing (CCGrid), 2014 14th IEEE/ACM International …, 2014
252014
Analyzing communication models for distributed thread-collaborative processors in terms of energy and time
B Klenk, L Oden, H Froning
2015 IEEE International Symposium on Performance Analysis of Systems and …, 2015
162015
Analyzing put/get apis for thread-collaborative processors
B Klenk, L Oden, H Fröning
2014 43rd International Conference on Parallel Processing Workshops, 411-418, 2014
162014
Energy-efficient stencil computations on distributed gpus using dynamic parallelism and gpu-controlled communication
L Oden, B Klenk, H Fröning
Energy Efficient Supercomputing Workshop (E2SC), 2014, 31-40, 2014
42014
TeraRack: A Tbps Rack for Machine Learning Training
M Khani, M Ghobadi, M Alizadeh, Z Zhu, M Glick, K Bergman, A Vahdat, ...
4*
Why Data Science and Machine Learning Need Silicon Photonics
B Klenk, L Dennison
Optical Fiber Communication Conference, M4F. 6, 2020
32020
Energy-efficient Computing on Distributed GPUs using Dynamic Parallelism and GPU controlled Communication
L Oden, B Klenk, H Froning
2nd Workshop on Energy-efficient SuperComputing (E2SC), 2014
22014
GPU-centric communication for improved efficiency
B Klenk, L Oden, H Fröning
International Workshop on Green Programming, Computing and Data Processing …, 2014
22014
Analyzing GPU-controlled communication with dynamic parallelism in terms of performance and energy
L Oden, B Klenk, H Fröning
Parallel Computing 57, 125-134, 2016
12016
DISTRIBUTED BATCH NORMALIZATION USING ESTIMATES AND ROLLBACK
LR Dennison, B Klenk
US Patent App. 16/669,979, 2020
2020
DISTRIBUTED BATCH NORMALIZATION USING PARTIAL POPULATIONS
LR Dennison, B Klenk
US Patent App. 16/669,925, 2020
2020
Communication Architectures for Scalable GPU-centric Computing Systems
B Klenk
2018
Scalable Communication Architectures for GPU-centric Systems
B Klenk, H Fröning
Energy-efficient Distributed GPU Communication
B Klenk, L Oden, H Fröning
Future Memory Technologies
B Klenk
Das System kann den Vorgang jetzt nicht ausführen. Versuchen Sie es später erneut.
Artikel 1–18