Related papers: LEO: Tracing GPU Stall Root Causes via Cross-Vendo…
Large Language Models (LLMs) can enhance reasoning capabilities through test-time scaling by generating multiple traces. However, the combination of lengthy reasoning traces with multiple sampling introduces substantial computation and high…
Recent years have witnessed phenomenal growth in the application, and capabilities of Graphical Processing Units (GPUs) due to their high parallel computation power at relatively low cost. However, writing a computationally efficient GPU…
Google's congestion control (GCC) has become a cornerstone for real-time video and audio communication, yet its performance remains fragile in emerging Low Earth Orbit (LEO) networks. In this paper, we study the behavior of…
This paper studies rule-based blocking in Entity Resolution (ER). We propose HyperBlocker, a GPU-accelerated system for blocking in ER. As opposed to previous blocking algorithms and parallel blocking solvers, HyperBlocker employs a…
Real-time trajectory optimization for nonlinear constrained autonomous systems is critical and typically performed by CPU-based sequential solvers. Specifically, reliance on global sparse linear algebra or the serial nature of dynamic…
5G wireless networks are complex, leveraging layers of scheduling, retransmission, and adaptation mechanisms to maximize their efficiency. But these mechanisms interact to produce significant fluctuations in uplink and downlink capacity and…
Profile Guided Optimization (PGO) uses runtime profiling to direct compiler optimization decisions, effectively combining static analysis with actual execution behavior to enhance performance. Runtime profiles, collected through…
Connected components and spanning forest are fundamental graph algorithms due to their use in many important applications, such as graph clustering and image segmentation. GPUs are an ideal platform for graph algorithms due to their high…
The complex regulatory dynamics of a biological network can be succinctly captured using discrete logic models. Given even sparse time-course data from the system of interest, previous work has shown that global optimization schemes are…
As GPU availability has increased and programming support has matured, a wider variety of applications are being ported to these platforms. Many parallel applications contain fine-grained synchronization idioms; as such, their correct…
Deep learning models are trained on servers with many GPUs, and training must scale with the number of GPUs. Systems such as TensorFlow and Caffe2 train models with parallel synchronous stochastic gradient descent: they process a batch of…
Program slicing is a critical technique in software engineering, enabling developers to isolate relevant portions of code for tasks such as bug detection, code comprehension, and debugging. In this study, we investigate the application of…
AI accelerator processing capabilities and memory constraints largely dictate the scale in which machine learning workloads (e.g., training and inference) can be executed within a desirable time frame. Training a state of the art,…
Existing GPU-sharing techniques, including spatial and temporal sharing, aim to improve utilization but face challenges in simultaneously ensuring SLO adherence and maximizing efficiency due to the lack of fine-grained task scheduling on…
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…
Query optimization is a hallmark of database systems enabling complex SQL queries of today's applications to be run efficiently. The query optimizer often fails to find the best plan, when logical subtleties in business queries and schemas…
In high-performance computing, hotspot GPU kernels are primary bottlenecks, and expert manual tuning is costly and hard to port. Large language model methods often assume kernels can be compiled and executed cheaply, which fails in large…
I/O performance is crucial to efficiency in data-intensive scientific computing; but tuning large-scale storage systems is complex, costly, and notoriously manpower-intensive, making it inaccessible for most domain scientists. To address…
Large Language Models (LLMs), as the foundational architecture for next-generation interactive AI applications, not only power intelligent dialogue systems but also drive the evolution of embodied intelligence on edge devices, including…
Modern machine learning workloads such as large language model training, fine-tuning jobs are highly distributed and span across hundreds of systems with multiple GPUs. Job completion time for these workloads is the artifact of the…