Related papers: Global Optimizations & Lightweight Dynamic Logic f…
Spatial Branch and Bound (B&B) algorithms are widely used for solving nonconvex problems to global optimality, yet they remain computationally expensive. Though some works have been carried out to speed up B&B via CPU parallelization, GPU…
Large inter-GPU all-reduce operations, prevalent throughout deep learning, are bottlenecked by communication costs. Emerging heterogeneous architectures are comprised of complex nodes, often containing $4$ GPUs and dozens to hundreds of CPU…
In Scientific Computing and modern Machine Learning (ML) workloads, sequences of dependent General Matrix Multiplications (GEMMs) often dominate execution time. While state-of-the-art BLAS libraries aggressively optimize individual GEMM…
Large matrix multiplication is a cornerstone of modern machine learning workloads, yet traditional approaches suffer from cubic computational complexity (e.g., $\mathcal{O}(n^3)$ for a matrix of size $n\times n$). We present Low-Rank GEMM,…
We present a global optimizer, based on a conditional generative neural network, which can output ensembles of highly efficient topology-optimized metasurfaces operating across a range of parameters. A key feature of the network is that it…
Video analytics pipelines have steadily shifted to edge deployments to reduce bandwidth overheads and privacy violations, but in doing so, face an ever-growing resource tension. Most notably, edge-box GPUs lack the memory needed to…
We introduce Stream-K, a work-centric parallelization of matrix multiplication (GEMM) and related computations in dense linear algebra. Whereas contemporary decompositions are primarily tile-based, our method operates by partitioning an…
Analytical framework for predicting General Matrix Multiplication (GEMM) performance on modern GPUs, focusing on runtime, power consumption, and energy efficiency. Our study employs two approaches: a custom-implemented tiled matrix…
Large-language models (LLMs) are rapidly being applied to radiology, enabling automated image interpretation and report generation tasks. Their deployment in clinical practice requires both high diagnostic accuracy and low inference…
We present a versatile GPU-based parallel version of Logistic Regression (LR), aiming to address the increasing demand for faster algorithms in binary classification due to large data sets. Our implementation is a direct translation of the…
GPUs are vastly underutilized, even when running resource-intensive AI applications, as GPU kernels within each job have diverse resource profiles that may saturate some parts of a device while often leaving other parts idle. Colocating…
High-performance GPU kernels are critical to modern machine learning systems, yet developing efficient implementations remains a challenging, expert-driven process due to the tight coupling between algorithmic structure, memory hierarchy…
Modern deployment of large language models (LLMs) frequently involves both inference serving and continuous retraining to stay aligned with evolving data and user feedback. Common practices separate these workloads onto distinct servers in…
Deep neural networks (DNNs) face significant challenges when deployed on resource-constrained extreme edge devices due to their computational and data-intensive nature. While standalone accelerators tailored for specific application…
The performance of graph programs depends highly on the algorithm, the size and structure of the input graphs, as well as the features of the underlying hardware. No single set of optimizations or one hardware platform works well across all…
Training LLMs relies on distributed implementations using multiple GPUs to compute gradients in parallel with sharded optimizers. However, synchronizing gradients in data parallel setups introduces communication overhead that grows with the…
We propose a GPU-accelerated distributed optimization algorithm for controlling multi-phase optimal power flow in active distribution systems with dynamically changing topologies. To handle varying network configurations and enable…
Developing kernels for Processing-In-Memory (PIM) platforms poses unique challenges in data management and parallel programming on limited processing units. Although software development kits (SDKs) for PIM, such as the UPMEM SDK, provide…
The significant resource demands in LLM serving prompts production clusters to fully utilize heterogeneous hardware by partitioning LLM models across a mix of high-end and low-end GPUs. However, existing parallelization approaches often…
Bloom filters are a fundamental data structure for approximate membership queries, with applications ranging from data analytics to databases and genomics. Several variants have been proposed to accommodate parallel architectures. GPUs,…