Related papers: Lemon: an MPI parallel I/O library for data encaps…
Scaling large multimodal models (LMMs) to 3D understanding poses unique challenges: point cloud data is sparse and irregular, existing models rely on fragmented architectures with modality-specific encoders, and training pipelines often…
Containers represent a convenient way of packing applications with dependencies for easy user-level installation and productivity. When running on supercomputers, it becomes crucial to optimize the containers to exploit the performance…
Graphics Processing Units (GPUs) are having a transformational effect on numerical lattice quantum chromodynamics (LQCD) calculations of importance in nuclear and particle physics. The QUDA library provides a package of mixed precision…
We present Lyncs-API, a Python API for Lattice QCD applications currently under development. Lyncs aims to bring several widely used libraries for Lattice QCD under a common framework. Lyncs flexibly links to libraries for CPUs and GPUs in…
Large language model (LLM) inference has been a prevalent demand in daily life and industries. The large tensor sizes and computing complexities in LLMs have brought challenges to memory, computing, and databus. This paper proposes a…
In this paper, we address the problem of designing a distributed application meant to run both classical and asynchronous iterations. MPI libraries are very popular and widely used in the scientific community, however asynchronous iterative…
The classical-quantum system heterogeneity (different data characteristics, execution paradigms and synchronization mechanism etc.) renders existing distributed communication mechanisms (e.g. MPI, NCCL etc.) inadequate. This bottleneck…
The evolution of architectures, programming models, and algorithms is driving communication towards greater asynchrony and concurrency, usually in multithreaded environments. We present LCI, a communication library designed for efficient…
Machine Learning and Data Mining (MLDM) algorithms are becoming increasingly important in analyzing large volume of data generated by simulations, experiments and mobile devices. With increasing data volume, distributed memory systems (such…
Upcoming HPC clusters will feature hybrid memories and storage devices per compute node. In this work, we propose to use the MPI one-sided communication model and MPI windows as unique interface for programming memory and storage. We…
On many parallel machines, the time LQCD applications spent in communication is a significant contribution to the total wall-clock time, especially in the strong-scaling limit. We present a novel high-performance communication library that…
Parallel I/O refers to the ability of scientific programs to concurrently read/write from/to a single file from multiple processes executing on distributed memory platforms like compute clusters. In the HPC world, I/O becomes a significant…
Large Language Models (LLMs) are increasingly deployed on edge devices with Neural Processing Units (NPUs), yet the decode phase remains memory-intensive, limiting performance. Processing-in-Memory (PIM) offers a promising solution, but…
Pre-training decoder-only language models relies on vast amounts of high-quality data, yet the availability of such data is increasingly reaching its limits. While metadata is commonly used to create and curate these datasets, its potential…
We present a set of programming tools (classes and functions written in C++ and based on Message Passing Interface) for fast development of generic parallel (and non-parallel) lattice simulations. They are collectively called MDP 1.2. These…
High-level I/O libraries, such as HDF5 and PnetCDF, are commonly used by large-scale scientific applications to perform I/O tasks in parallel. These I/O libraries store the metadata such as data types and dimensionality along with the raw…
A quick review of the features of FermiQCD, a C++ library for fast development of parallel Lattice QCD applications. FermiQCD is fully Object Oriented and is based on MPI but, it required no previsius knowledge of parallel programming. It…
One-sided communication is a useful paradigm for irregular parallel applications, but most one-sided programming environments, including MPI's one-sided interface and PGAS programming languages, lack application level libraries to support…
Tuning hyperparameters for machine learning algorithms is a tedious task, one that is typically done manually. To enable automated hyperparameter tuning, recent works have started to use techniques based on Bayesian optimization. However,…
This paper describes a state-of-the-art parallel Lattice QCD Monte Carlo code for staggered fermions, purposely designed to be portable across different computer architectures, including GPUs and commodity CPUs. Portability is achieved…