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...
share
research
∙
07/17/2023
Maximum Flows in Parametric Graph Templates
Execution graphs of parallel loop programs exhibit a nested, repeating s...
research
∙
06/28/2023
FuzzyFlow: Leveraging Dataflow To Find and Squash Program Optimization Bugs
The current hardware landscape and application scale is driving performa...
research
∙
06/01/2023
Bridging Control-Centric and Data-Centric Optimization
With the rise of specialized hardware and new programming languages, cod...
research
∙
04/15/2023
STen: Productive and Efficient Sparsity in PyTorch
As deep learning models grow, sparsity is becoming an increasingly criti...
research
∙
03/14/2023
Performance Embeddings: A Similarity-based Approach to Automatic Performance Optimization
Performance optimization is an increasingly challenging but often repeti...
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 ...
research
∙
09/19/2022
Temporal Vectorization: A Compiler Approach to Automatic Multi-Pumping
The multi-pumping resource sharing technique can overcome the limitation...
research
∙
06/29/2022
ENS-10: A Dataset For Post-Processing Ensemble Weather Forecast
Post-processing ensemble prediction systems can improve weather forecast...
research
∙
06/21/2022
Boosting Performance Optimization with Interactive Data Movement Visualization
Optimizing application performance in today's hardware architecture land...
research
∙
06/16/2022
Deinsum: Practically I/O Optimal Multilinear Algebra
Multilinear algebra kernel performance on modern massively-parallel syst...
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...
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...
research
∙
12/22/2021
Lifting C Semantics for Dataflow Optimization
C is the lingua franca of programming and almost any device can be progr...
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...
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...
research
∙
07/01/2021
Productivity, Portability, Performance: Data-Centric Python
Python has become the de facto language for scientific computing. Progra...
research
∙
06/07/2021
Learning Combinatorial Node Labeling Algorithms
We present a graph neural network to learn graph coloring heuristics usi...
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...
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...
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...
research
∙
11/21/2020
Deep Data Flow Analysis
Compiler architects increasingly look to machine learning when building ...
research
∙
11/13/2020
Parametric Graph Templates: Properties and Algorithms
Hierarchical structure and repetition are prevalent in graphs originatin...
research
∙
10/28/2020
StencilFlow: Mapping Large Stencil Programs to Distributed Spatial Computing Systems
Spatial computing devices have been shown to significantly accelerate st...
research
∙
10/28/2020
Substream-Centric Maximum Matchings on FPGA
Developing high-performance and energy-efficient algorithms for maximum ...
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...
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 ...
research
∙
05/18/2020
Deep Learning for Post-Processing Ensemble Weather Forecasts
Quantifying uncertainty in weather forecasts typically employs ensemble ...
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 ...
research
∙
03/23/2020
ProGraML: Graph-based Deep Learning for Program Optimization and Analysis
The increasing complexity of computing systems places a tremendous burde...
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...
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...
research
∙
11/02/2019
Predicting Weather Uncertainty with Deep Convnets
Modern weather forecast models perform uncertainty quantification using ...
research
∙
08/12/2019
Taming Unbalanced Training Workloads in Deep Learning with Partial Collective Operations
Load imbalance pervasively exists in distributed deep learning training ...
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...
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...
research
∙
02/25/2019
Graph Processing on FPGAs: Taxonomy, Survey, Challenges
Graph processing has become an important part of various areas, such as ...
research
∙
01/29/2019
A Modular Benchmarking Infrastructure for High-Performance and Reproducible Deep Learning
We introduce Deep500: the first customizable benchmarking infrastructure...
research
∙
01/27/2019
Augment your batch: better training with larger batches
Large-batch SGD is important for scaling training of deep neural network...
research
∙
06/19/2018
Neural Code Comprehension: A Learnable Representation of Code Semantics
With the recent success of embeddings in natural language processing, re...
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...
research
∙
02/26/2018