What is he best known for?
The fields of study he is best known for:
- Operating system
- Programming language
- Computer network
His main research concerns Distributed computing, Parallel computing, Message Passing Interface, Scalability and Supercomputer.
Torsten Hoefler studies Distributed computing, focusing on Message passing in particular.
His Parallel computing research includes elements of Conjugate gradient solver, Computation, Stencil and Programming paradigm.
His study on Message Passing Interface also encompasses disciplines like
- Semantics which connect with Remote memory access and Shared memory,
- Interface that connect with fields like Memory footprint and SIMPLE.
His Scalability research focuses on subjects like Fortran, which are linked to Programmer, Volume and Remote direct memory access.
In his study, Memory bandwidth, Atmospheric model and Bottleneck is inextricably linked to Compiler, which falls within the broad field of Supercomputer.
His most cited work include:
- Demystifying Parallel and Distributed Deep Learning: An In-depth Concurrency Analysis (229 citations)
- The PERCS High-Performance Interconnect (173 citations)
- Characterizing the Influence of System Noise on Large-Scale Applications by Simulation (166 citations)
What are the main themes of his work throughout his whole career to date?
His primary scientific interests are in Distributed computing, Parallel computing, Scalability, Computer network and Network topology.
His Distributed computing research includes themes of Implementation, Computation and InfiniBand.
As a part of the same scientific family, he mostly works in the field of Parallel computing, focusing on Programming paradigm and, on occasion, Theoretical computer science.
The Scalability study combines topics in areas such as Computer architecture and Supercomputer.
His Network packet and Multipath routing study are his primary interests in Computer network.
His Message Passing Interface study frequently draws connections to adjacent fields such as Interface.
He most often published in these fields:
- Distributed computing (28.87%)
- Parallel computing (22.94%)
- Scalability (18.30%)
What were the highlights of his more recent work (between 2019-2021)?
- Parallel computing (22.94%)
- Artificial intelligence (6.70%)
- Scalability (18.30%)
In recent papers he was focusing on the following fields of study:
His primary areas of study are Parallel computing, Artificial intelligence, Scalability, Graph and Deep learning.
As a part of the same scientific study, Torsten Hoefler usually deals with the Artificial intelligence, concentrating on Machine learning and frequently concerns with Set.
His research in Scalability intersects with topics in Computer architecture, Compiler, Middleware, Distributed computing and Latency.
His Compiler study integrates concerns from other disciplines, such as Supercomputer and Solver.
His study in Distributed computing is interdisciplinary in nature, drawing from both Interconnection, Ethernet protocol and Interoperability.
Torsten Hoefler works mostly in the field of Graph, limiting it down to concerns involving Graph and, occasionally, Graph theory, Heuristics and Algorithm.
Between 2019 and 2021, his most popular works were:
- Kilometer-scale climate models: Prospects and challenges (18 citations)
- Augment Your Batch: Improving Generalization Through Instance Repetition (17 citations)
- Taming unbalanced training workloads in deep learning with partial collective operations (14 citations)
In his most recent research, the most cited papers focused on:
- Operating system
- Programming language
- Computer network
His primary areas of investigation include Artificial intelligence, Set, Deep learning, Artificial neural network and Compiler.
As a member of one scientific family, he mostly works in the field of Artificial intelligence, focusing on Machine learning and, on occasion, Scalability and Forecast skill.
His Set research is multidisciplinary, incorporating perspectives in Software, Reusability, Sparse matrix, Distributed algorithm and System on a chip.
His Deep learning study incorporates themes from Stochastic gradient descent, Convergence, Asynchronous communication, Training and Phrase.
His work carried out in the field of Compiler brings together such families of science as Source lines of code and Code.
His work on Parallel computing is being expanded to include thematically relevant topics such as Stencil.
This overview was generated by a machine learning system which analysed the scientist’s
body of work. If you have any feedback, you can
contact us
here.
