VENOM: A Vectorized N:M Format for Unleashing the Power of Sparse Tensor Cores

The increasing success and scaling of Deep Learning models demands higher computational efficiency and power. Sparsification can lead to both smaller models as well as higher compute efficiency, and accelerated hardware is becoming available. However, exploiting it efficiently requires kernel implementations, pruning algorithms, and storage formats, to utilize hardware support of specialized sparse vector units. An example of those are the NVIDIA's Sparse Tensor Cores (SPTCs), which promise a 2x speedup. However, SPTCs only support the 2:4 format, limiting achievable sparsity ratios to 50%. We present the V:N:M format, which enables the execution of arbitrary N:M ratios on SPTCs. To efficiently exploit the resulting format, we propose Spatha, a high-performance sparse-library for DL routines. We show that Spatha achieves up to 37x speedup over cuBLAS. We also demonstrate a second-order pruning technique that enables sparsification to high sparsity ratios with V:N:M and little to no loss in accuracy in modern transformers.

Cached Operator Reordering: A Unified View for Fast GNN Training

Graph Neural Networks (GNNs) are a powerful tool for handling structured graph data and addressing tasks such as node classification, graph classification, and clustering. However, the sparse nature of GNN computation poses new challenges for performance optimization compared to traditional deep neural networks. We address these challenges by providing a unified view of GNN computation, I/O, and memory. By analyzing the computational graphs of the Graph Convolutional Network (GCN) and Graph Attention (GAT) layers -- two widely used GNN layers -- we propose alternative computation strategies. We present adaptive operator reordering with caching, which achieves a speedup of up to 2.43x for GCN compared to the current state-of-the-art. Furthermore, an exploration of different caching schemes for GAT yields a speedup of up to 1.94x. The proposed optimizations save memory, are easily implemented across various hardware platforms, and have the potential to alleviate performance bottlenecks in training large-scale GNN models.

STen: Productive and Efficient Sparsity in PyTorch

As deep learning models grow, sparsity is becoming an increasingly critical component of deep neural networks, enabling improved performance and reduced storage. However, existing frameworks offer poor support for sparsity. Specialized sparsity engines focus exclusively on sparse inference, while general frameworks primarily focus on sparse tensors in classical formats and neglect the broader sparsification pipeline necessary for using sparse models, especially during training. Further, existing frameworks are not easily extensible: adding a new sparse tensor format or operator is challenging and time-consuming. To address this, we propose STen, a sparsity programming model and interface for PyTorch, which incorporates sparsity layouts, operators, and sparsifiers, in an efficient, customizable, and extensible framework that supports virtually all sparsification methods. We demonstrate this by developing a high-performance grouped n:m sparsity layout for CPU inference at moderate sparsity. STen brings high performance and ease of use to the ML community, making sparsity easily accessible.

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

Performance optimization is an increasingly challenging but often repetitive task. While each platform has its quirks, the underlying code transformations rely on data movement and computational characteristics that recur across applications. This paper proposes to leverage those similarities by constructing an embedding space for subprograms. The continuous space captures both static and dynamic properties of loop nests via symbolic code analysis and performance profiling, respectively. Performance embeddings enable direct knowledge transfer of performance tuning between applications, which can result from autotuning or tailored improvements. We demonstrate this transfer tuning approach on case studies in deep neural networks, dense and sparse linear algebra compositions, and numerical weather prediction stencils. Transfer tuning reduces the search complexity by up to four orders of magnitude and outperforms the MKL library in sparse-dense matrix multiplication. The results exhibit clear correspondences between program characteristics and optimizations, outperforming prior specialized state-of-the-art approaches and generalizing beyond their capabilities.

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

As the accuracy of machine learning models increases at a fast rate, so does their demand for energy and compute resources. On a low level, the major part of these resources is consumed by data movement between different memory units. Modern hardware architectures contain a form of fast memory (e.g., cache, registers), which is small, and a slow memory (e.g., DRAM), which is larger but expensive to access. We can only process data that is stored in fast memory, which incurs data movement (input/output-operations, or I/Os) between the two units. In this paper, we provide a rigorous theoretical analysis of the I/Os needed in sparse feedforward neural network (FFNN) inference. We establish bounds that determine the optimal number of I/Os up to a factor of 2 and present a method that uses a number of I/Os within that range. Much of the I/O-complexity is determined by a few high-level properties of the FFNN (number of inputs, outputs, neurons, and connections), but if we want to get closer to the exact lower bound, the instance-specific sparsity patterns need to be considered. Departing from the 2-optimal computation strategy, we show how to reduce the number of I/Os further with simulated annealing. Complementing this result, we provide an algorithm that constructively generates networks with maximum I/O-efficiency for inference. We test the algorithms and empirically verify our theoretical and algorithmic contributions. In our experiments on real hardware we observe speedups of up to 45$\times$ relative to the standard way of performing inference.

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

Post-processing ensemble prediction systems can improve weather forecasting, especially for extreme event prediction. In recent years, different machine learning models have been developed to improve the quality of the post-processing step. However, these models heavily rely on the data and generating such ensemble members requires multiple runs of numerical weather prediction models, at high computational cost. This paper introduces the ENS-10 dataset, consisting of ten ensemble members spread over 20 years (1998-2017). The ensemble members are generated by perturbing numerical weather simulations to capture the chaotic behavior of the Earth. To represent the three-dimensional state of the atmosphere, ENS-10 provides the most relevant atmospheric variables in 11 distinct pressure levels as well as the surface at 0.5-degree resolution. The dataset targets the prediction correction task at 48-hour lead time, which is essentially improving the forecast quality by removing the biases of the ensemble members. To this end, ENS-10 provides the weather variables for forecast lead times T=0, 24, and 48 hours (two data points per week). We provide a set of baselines for this task on ENS-10 and compare their performance in correcting the prediction of different weather variables. We also assess our baselines for predicting extreme events using our dataset. The ENS-10 dataset is available under the Creative Commons Attribution 4.0 International (CC BY 4.0) licence.

A Data-Centric Optimization Framework for Machine Learning

Rapid progress in deep learning is leading to a diverse set of quickly changing models, with a dramatically growing demand for compute. However, as frameworks specialize optimization to patterns in popular networks, they implicitly constrain novel and diverse models that drive progress in research. We empower deep learning researchers by defining a flexible and user-customizable pipeline for optimizing training of arbitrary deep neural networks, based on data movement minimization. The pipeline begins with standard networks in PyTorch or ONNX and transforms computation through progressive lowering. We define four levels of general-purpose transformations, from local intra-operator optimizations to global data movement reduction. These operate on a data-centric graph intermediate representation that expresses computation and data movement at all levels of abstraction, including expanding basic operators such as convolutions to their underlying computations. Central to the design is the interactive and introspectable nature of the pipeline. Every part is extensible through a Python API, and can be tuned interactively using a GUI. We demonstrate competitive performance or speedups on ten different networks, with interactive optimizations discovering new opportunities in EfficientNet.

Learning Combinatorial Node Labeling Algorithms

We present a graph neural network to learn graph coloring heuristics using reinforcement learning. Our learned deterministic heuristics give better solutions than classical degree-based greedy heuristics and only take seconds to evaluate on graphs with tens of thousands of vertices. As our approach is based on policy-gradients, it also learns a probabilistic policy as well. These probabilistic policies outperform all greedy coloring baselines and a machine learning baseline. Our approach generalizes several previous machine-learning frameworks, which applied to problems like minimum vertex cover. We also demonstrate that our approach outperforms two greedy heuristics on minimum vertex cover.

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 the community to reduce the size of neural networks by selectively pruning components. Similarly to their biological counterparts, sparse networks generalize just as well, if not better than, the original dense networks. Sparsity can reduce the memory footprint of regular networks to fit mobile devices, as well as shorten training time for ever growing networks. In this paper, we survey prior work on sparsity in deep learning and provide an extensive tutorial of sparsification for both inference and training. We describe approaches to remove and add elements of neural networks, different training strategies to achieve model sparsity, and mechanisms to exploit sparsity in practice. Our work distills ideas from more than 300 research papers and provides guidance to practitioners who wish to utilize sparsity today, as well as to researchers whose goal is to push the frontier forward. We include the necessary background on mathematical methods in sparsification, describe phenomena such as early structure adaptation, the intricate relations between sparsity and the training process, and show techniques for achieving acceleration on real hardware. We also define a metric of pruned parameter efficiency that could serve as a baseline for comparison of different sparse networks. We close by speculating on how sparsity can improve future workloads and outline major open problems in the field.

Clairvoyant Prefetching for Distributed Machine Learning I/O

I/O is emerging as a major bottleneck for machine learning training, especially in distributed environments such as clouds and supercomputers. Optimal data ingestion pipelines differ between systems, and increasing efficiency requires a delicate balance between access to local storage, external filesystems, and remote workers; yet existing frameworks fail to efficiently utilize such resources. We observe that, given the seed generating the random access pattern for training with SGD, we have clairvoyance and can exactly predict when a given sample will be accessed. We combine this with a theoretical analysis of access patterns in training and performance modeling to produce a novel machine learning I/O middleware, HDMLP, to tackle the I/O bottleneck. HDMLP provides an easy-to-use, flexible, and scalable solution that delivers better performance than state-of-the-art approaches while requiring very few changes to existing codebases and supporting a broad range of environments.