b'Tal Ben-Nun'

research

∙ 08/23/2023

Cached Operator Reordering: A Unified View for Fast GNN Training

Graph Neural Networks (GNNs) are a powerful tool for handling structured...

0 Julia Bazinska, et al. ∙

research

∙ 07/17/2023

Maximum Flows in Parametric Graph Templates

Execution graphs of parallel loop programs exhibit a nested, repeating s...

0 Tal Ben-Nun, et al. ∙

research

∙ 06/28/2023

FuzzyFlow: Leveraging Dataflow To Find and Squash Program Optimization Bugs

The current hardware landscape and application scale is driving performa...

0 Philipp Schaad, et al. ∙

research

∙ 06/01/2023

Bridging Control-Centric and Data-Centric Optimization

With the rise of specialized hardware and new programming languages, cod...

0 Tal Ben-Nun, et al. ∙

research

∙ 04/15/2023

STen: Productive and Efficient Sparsity in PyTorch

As deep learning models grow, sparsity is becoming an increasingly criti...

0 Andrei Ivanov, et al. ∙

research

∙ 03/14/2023

Performance Embeddings: A Similarity-based Approach to Automatic Performance Optimization

Performance optimization is an increasingly challenging but often repeti...

0 Lukas Trümper, et al. ∙

research

∙ 01/03/2023

A Theory of I/O-Efficient Sparse Neural Network Inference

As the accuracy of machine learning models increases at a fast rate, so ...

0 Niels Gleinig, et al. ∙

research

∙ 09/19/2022

Temporal Vectorization: A Compiler Approach to Automatic Multi-Pumping

The multi-pumping resource sharing technique can overcome the limitation...

0 Carl-Johannes Johnsen, et al. ∙

research

∙ 06/29/2022

ENS-10: A Dataset For Post-Processing Ensemble Weather Forecast

Post-processing ensemble prediction systems can improve weather forecast...

14 Saleh Ashkboos, et al. ∙

research

∙ 06/21/2022

Boosting Performance Optimization with Interactive Data Movement Visualization

Optimizing application performance in today's hardware architecture land...

0 Philipp Schaad, et al. ∙

research

∙ 06/16/2022

Deinsum: Practically I/O Optimal Multilinear Algebra

Multilinear algebra kernel performance on modern massively-parallel syst...

0 Alexandros Nikolaos Ziogas, et al. ∙

research

∙ 05/10/2022

The spatial computer: A model for energy-efficient parallel computation

We present a new parallel model of computation suitable for spatial arch...

0 Lukas Gianinazzi, et al. ∙

research

∙ 05/09/2022

Productive Performance Engineering for Weather and Climate Modeling with Python

Earth system models are developed with a tight coupling to target hardwa...

0 Tal Ben-Nun, et al. ∙

research

∙ 12/22/2021

Lifting C Semantics for Dataflow Optimization

C is the lingua franca of programming and almost any device can be progr...

0 Alexandru Calotoiu, et al. ∙

research

∙ 10/20/2021

A Data-Centric Optimization Framework for Machine Learning

Rapid progress in deep learning is leading to a diverse set of quickly c...

19 Oliver Rausch, et al. ∙

research

∙ 08/20/2021

On the Parallel I/O Optimality of Linear Algebra Kernels: Near-Optimal Matrix Factorizations

Matrix factorizations are among the most important building blocks of sc...

0 Grzegorz Kwasniewski, et al. ∙

research

∙ 07/01/2021

Productivity, Portability, Performance: Data-Centric Python

Python has become the de facto language for scientific computing. Progra...

0 Alexandros Nikolaos Ziogas, et al. ∙

research

∙ 06/07/2021

Learning Combinatorial Node Labeling Algorithms

We present a graph neural network to learn graph coloring heuristics usi...

6 Lukas Gianinazzi, et al. ∙

research

∙ 05/15/2021

Pebbles, Graphs, and a Pinch of Combinatorics: Towards Tight I/O Lower Bounds for Statically Analyzable Programs

Determining I/O lower bounds is a crucial step in obtaining communicatio...

0 Grzegorz Kwasniewski, et al. ∙

research

∙ 01/31/2021

Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks

The growing energy and performance costs of deep learning have driven th...

85 Torsten Hoefler, et al. ∙

research

∙ 01/21/2021

Clairvoyant Prefetching for Distributed Machine Learning I/O

I/O is emerging as a major bottleneck for machine learning training, esp...

28 Roman Böhringer, et al. ∙

research

∙ 11/21/2020

Deep Data Flow Analysis

Compiler architects increasingly look to machine learning when building ...

0 Chris Cummins, et al. ∙

research

∙ 11/13/2020

Parametric Graph Templates: Properties and Algorithms

Hierarchical structure and repetition are prevalent in graphs originatin...

0 Tal Ben-Nun, et al. ∙

research

∙ 10/28/2020

StencilFlow: Mapping Large Stencil Programs to Distributed Spatial Computing Systems

Spatial computing devices have been shown to significantly accelerate st...

0 Johannes de Fine Licht, et al. ∙

research

∙ 10/28/2020

Substream-Centric Maximum Matchings on FPGA

Developing high-performance and energy-efficient algorithms for maximum ...

0 Maciej Besta, et al. ∙

research

∙ 10/12/2020

On the Parallel I/O Optimality of Linear Algebra Kernels: Near-Optimal LU Factorization

Dense linear algebra kernels, such as linear solvers or tensor contracti...

0 Grzegorz Kwasniewski, et al. ∙

research

∙ 06/30/2020

Data Movement Is All You Need: A Case Study on Optimizing Transformers

Transformers have become widely used for language modeling and sequence ...

45 Andrei Ivanov, et al. ∙

research

∙ 05/18/2020

Deep Learning for Post-Processing Ensemble Weather Forecasts

Quantifying uncertainty in weather forecasts typically employs ensemble ...

42 Peter Grönquist, et al. ∙

research

∙ 04/30/2020

Breaking (Global) Barriers in Parallel Stochastic Optimization with Wait-Avoiding Group Averaging

Deep learning at scale is dominated by communication time. Distributing ...

1 Shigang Li, et al. ∙

research

∙ 03/23/2020

ProGraML: Graph-based Deep Learning for Program Optimization and Analysis

The increasing complexity of computing systems places a tremendous burde...

23 Chris Cummins, et al. ∙

research

∙ 12/18/2019

Optimizing the Data Movement in Quantum Transport Simulations via Data-Centric Parallel Programming

Designing efficient cooling systems for integrated circuits (ICs) relies...

0 Alexandros Nikolaos Ziogas, et al. ∙

research

∙ 12/18/2019

A Data-Centric Approach to Extreme-Scale Ab initio Dissipative Quantum Transport Simulations

The computational efficiency of a state of the art ab initio quantum tra...

0 Alexandros Nikolaos Ziogas, et al. ∙

research

∙ 11/02/2019

Predicting Weather Uncertainty with Deep Convnets

Modern weather forecast models perform uncertainty quantification using ...

1 Peter Grönquist, et al. ∙

research

∙ 08/12/2019

Taming Unbalanced Training Workloads in Deep Learning with Partial Collective Operations

Load imbalance pervasively exists in distributed deep learning training ...

0 Shigang Li, et al. ∙

research

∙ 02/27/2019

Stateful Dataflow Multigraphs: A Data-Centric Model for Performance Portability on Heterogeneous Architectures

The ubiquity of accelerators in high-performance computing has driven pr...

0 Tal Ben-Nun, et al. ∙

research

∙ 02/27/2019

Stateful Dataflow Multigraphs: A Data-Centric Model for High-Performance Parallel Programs

With the ubiquity of accelerators, such as FPGAs and GPUs, the complexit...

0 Tal Ben-Nun, et al. ∙

research

∙ 02/25/2019

Graph Processing on FPGAs: Taxonomy, Survey, Challenges

Graph processing has become an important part of various areas, such as ...

0 Maciej Besta, et al. ∙

research

∙ 01/29/2019

A Modular Benchmarking Infrastructure for High-Performance and Reproducible Deep Learning

We introduce Deep500: the first customizable benchmarking infrastructure...

0 Tal Ben-Nun, et al. ∙

research

∙ 01/27/2019

Augment your batch: better training with larger batches

Large-batch SGD is important for scaling training of deep neural network...

0 Elad Hoffer, et al. ∙

research

∙ 06/19/2018

Neural Code Comprehension: A Learnable Representation of Code Semantics

With the recent success of embeddings in natural language processing, re...

0 Tal Ben-Nun, et al. ∙

research

∙ 04/13/2018

μ-cuDNN: Accelerating Deep Learning Frameworks with Micro-Batching

NVIDIA cuDNN is a low-level library that provides GPU kernels frequently...

0 Yosuke Oyama, et al. ∙

research

∙ 02/26/2018

Demystifying Parallel and Distributed Deep Learning: An In-Depth Concurrency Analysis

Deep Neural Networks (DNNs) are becoming an important tool in modern com...

0 Tal Ben-Nun, et al. ∙

Tal Ben-Nun

Featured Co-authors