Related papers: TpuGraphs: A Performance Prediction Dataset on Lar…
This paper presents Tofu, a system that partitions very large DNN models across multiple GPU devices to reduce per-GPU memory footprint. Tofu is designed to partition a dataflow graph of fine-grained tensor operators in order to work…
GPU-based HPC clusters are attracting more scientific application developers due to their extensive parallelism and energy efficiency. In order to achieve portability among a variety of multi/many core architectures, a popular choice for an…
Graphics Processing Units (GPUs) have become an integral part of High-Performance Computing to achieve an Exascale performance. The main goal of application developers of GPU is to tune their code extensively to obtain optimal performance,…
Many architects believe that major improvements in cost-energy-performance must now come from domain-specific hardware. This paper evaluates a custom ASIC---called a Tensor Processing Unit (TPU)---deployed in datacenters since 2015 that…
Graph Neural Networks (GNNs) have shown significant promise in various domains, such as recommendation systems, bioinformatics, and network analysis. However, the irregularity of graph data poses unique challenges for efficient computation,…
Characterizing and predicting the training performance of modern machine learning (ML) workloads on compute systems with compute and communication spread between CPUs, GPUs, and network devices is not only the key to optimization and…
The Deep Learning (DL) community sees many novel topologies published each year. Achieving high performance on each new topology remains challenging, as each requires some level of manual effort. This issue is compounded by the…
Graph-based data structures have drawn great attention in recent years. The large and rapidly growing trend on developing graph processing systems focuses mostly on improving the performance by preprocessing the input graph and modifying…
Graphs are a commonly used construct for representing relationships between elements in complex high dimensional datasets. Many real-world phenomenon are dynamic in nature, meaning that any graph used to represent them is inherently…
We have developed several autotuning benchmarks in CUDA that take into account performance-relevant source-code parameters and reach near peak-performance on various GPU architectures. We have used them during the development and evaluation…
We present GraphTensor, a comprehensive open-source framework that supports efficient parallel neural network processing on large graphs. GraphTensor offers a set of easy-to-use programming primitives that appreciate both graph and neural…
The graphics processing unit (GPU) has emerged as a powerful and cost effective processor for general performance computing. GPUs are capable of an order of magnitude more floating-point operations per second as compared to modern central…
Developing efficient GPU kernels can be difficult because of the complexity of GPU architectures and programming models. Existing performance tools only provide coarse-grained suggestions at the kernel level, if any. In this paper, we…
High-performance deep learning depends on efficient tensor programs. In recent years, automatic tensor program optimization, also known as tensor compilation, has emerged as the primary approach to generating efficient tensor programs.…
Deep learning has been successful in automating the design of features in machine learning pipelines. However, the algorithms optimizing neural network parameters remain largely hand-designed and computationally inefficient. We study if we…
Tuning tensor program generation involves searching for various possible program transformation combinations for a given program on target hardware to optimize the tensor program execution. It is already a complex process because of the…
Processing large-scale graph datasets is computationally intensive and time-consuming. Processor-centric CPU and GPU architectures, commonly used for graph applications, often face bottlenecks caused by extensive data movement between the…
High-performance tensor programs are crucial to guarantee efficient execution of deep neural networks. However, obtaining performant tensor programs for different operators on various hardware platforms is notoriously challenging.…
Deep learning (DL) compilers rely on cost models and auto-tuning to optimize tensor programs for target hardware. However, existing approaches depend on large offline datasets, incurring high collection costs and offering suboptimal…
Training machine learning models requires feeding input data for models to ingest. Input pipelines for machine learning jobs are often challenging to implement efficiently as they require reading large volumes of data, applying complex…