Related papers: Tawa: Automatic Warp Specialization for Modern GPU…
Graph algorithms and techniques are increasingly being used in scientific and commercial applications to express relations and explore large data sets. Although conventional or commodity computer architectures, like CPU or GPU, can compute…
FPGA programming is more complex as compared to Central Processing Units (CPUs) and Graphics Processing Units (GPUs). The coding languages to define the abstraction of Register Transfer Level (RTL) in High Level Synthesis (HLS) for FPGA…
Deep learning has emerged as a powerful method for extracting valuable information from large volumes of data. However, when new training data arrives continuously (i.e., is not fully available from the beginning), incremental training…
Path planning is critical for autonomous driving, generating smooth, collision-free, feasible paths based on perception and localization inputs. However, its computationally intensive nature poses significant challenges for…
In this paper, we present NUWA-Infinity, a generative model for infinite visual synthesis, which is defined as the task of generating arbitrarily-sized high-resolution images or long-duration videos. An autoregressive over autoregressive…
GPUs are the most popular platform for accelerating HPC workloads, such as artificial intelligence and science simulations. However, most microarchitectural research in academia relies on GPU core pipeline designs based on architectures…
Modern GPUs synchronize threads grouped in a warp at every instruction. These results in improving SIMD efficiency and makes sharing fetch and decode resources possible. The number of threads included in each warp (or warp size) affects…
Traditional congestion control algorithms struggle to maintain the consistent and satisfactory data transmission performance over time-varying networking condition. Simultaneously, as video traffic becomes dominant, the loose coupling…
Pipelining between data loading and computation is a critical tensor program optimization for GPUs. In order to unleash the high performance of latest GPUs, we must perform a synergetic optimization of multi-stage pipelining across the…
FPGAs are well-suited for dataflow architectures that process data in a streaming or pipelined manner, thus satisfying the high computational and communication demands of emerging applications. However, manually implementing an efficient…
High-resolution volumetric imaging techniques, such as X-ray tomography and advanced microscopy, generate increasingly large datasets that challenge existing tools for efficient processing, segmentation, and interactive exploration. This…
NVIDIA's Multi-Instance GPU (MIG) is a feature that enables system designers to reconfigure one large GPU into multiple smaller GPU slices. This work characterizes this emerging GPU and evaluates its effectiveness in designing…
Brain-inspired computing has emerged as a promising paradigm to overcome the energy-efficiency limitations of conventional intelligent systems by emulating the brain's partitioned architecture and event-driven sparse computation. However,…
Specialized Deep Learning (DL) acceleration stacks, designed for a specific set of frameworks, model architectures, operators, and data types, offer the allure of high performance while sacrificing flexibility. Changes in algorithms,…
The Streaming Multiprocessors (SMs) of a Graphics Processing Unit (GPU) execute instructions from a group of consecutive threads, called warps. At each cycle, an SM schedules a warp from a group of active warps and can context switch among…
Efficient inference of Multi-Head Latent Attention (MLA) is challenged by deploying the DeepSeek-R1 671B model on a single Multi-GPU server. This paper introduces FlashMLA-ETAP, a novel framework that enhances MLA inference for the…
Hash tables are ubiquitous. Properties such as an amortized constant time complexity for insertion and querying as well as a compact memory layout make them versatile associative data structures with manifold applications. The rapidly…
Customized processors are attractive solutions for vast domain-specific applications due to their high energy efficiency. However, designing a processor in traditional flows is time-consuming and expensive. To address this, researchers have…
While Model Predictive Control (MPC) delivers strong performance across robotics applications, solving the underlying (batches of) nonlinear trajectory optimization (TO) problems online remains computationally demanding. Existing…
We present Graphite, a GPU-accelerated nonlinear least squares graph optimization framework. It provides a CUDA C++ interface to enable the sharing of code between a real-time application, such as a SLAM system, and its optimization tasks.…