相关论文: Configurable Non-uniform All-to-all Algorithms

The Mixtures-of-Experts (MoE) model is a widespread distributed and integrated learning method for large language models (LLM), which is favored due to its ability to sparsify and expand models efficiently. However, the performance of MoE…

Large Language Models (LLMs) show promise for automated code optimization but struggle without performance context. This work introduces Opal, a modular framework that connects performance analytics insights with the vast body of published…

The evolution towards a more distributed and interconnected grid necessitates large-scale decision-making within strict temporal constraints. Machine learning (ML) paradigms have demonstrated significant potential in improving the efficacy…

Numerical investigation of compressible flows faces two main challenges. In order to accurately describe the flow characteristics, high-resolution nonlinear numerical schemes are needed to capture discontinuities and resolve wide…

This work demonstrates that fine-tuning transforms foundational machine-learned interatomic potentials (MLIPs) to achieve consistent, near-ab initio accuracy across diverse architectures. Benchmarking five leading MLIP frameworks (MACE,…

Computing systems rarely deliver best possible performance due to ever increasing hardware and software complexity and limitations of the current optimization technology. Additional code and architecture optimizations are often required to…

A hybrid scheme that utilizes MPI for distributed memory parallelism and OpenMP for shared memory parallelism is presented. The work is motivated by the desire to achieve exceptionally high Reynolds numbers in pseudospectral computations of…

In this work, we develop an adaptive, multivariate partitioning algorithm for solving mixed-integer nonlinear programs (MINLP) with multi-linear terms to global optimality. This iterative algorithm primarily exploits the advantages of…

Fine-tuning on task-specific question-answer pairs is a predominant method for enhancing the performance of instruction-tuned large language models (LLMs) on downstream tasks. However, in certain specialized domains, such as healthcare or…

Machine learning models made up of millions or billions of parameters are trained and served on large multi-GPU systems. As models grow in size and execute on more GPUs, the collective communications used in these applications become a…

The progression of communication in the Message Passing Interface (MPI) is not well defined, yet it is critical for application performance, particularly in achieving effective computation and communication overlap. The opaque nature of MPI…

Multi-task learning (MTL) has achieved great success in various research domains, such as CV, NLP and IR etc. Due to the complex and competing task correlation, naive training all tasks may lead to inequitable learning, i.e. some tasks are…

Hybrid MPI+threads programming is gaining prominence, but, in practice, applications perform slower with it compared to the MPI everywhere model. The most critical challenge to the parallel efficiency of MPI+threads applications is slow…

We investigate on large-scale deployment of non-orthogonal multiple access (NOMA) for improved spectral and power efficiency in cellular networks to provide massive wireless connectivity (e.g. for machine-type communication [mMTC]). First,…

Despite the advancements of open-source large language models (LLMs), e.g., LLaMA, they remain significantly limited in tool-use capabilities, i.e., using external tools (APIs) to fulfill human instructions. The reason is that current…

In the Fully Sharded Data Parallel (FSDP) training pipeline, collective operations can be interleaved to maximize the communication/computation overlap. In this scenario, outstanding operations such as Allgather and Reduce-Scatter can…

In this paper, we develop a deep learning-based bandwidth allocation policy that is: 1) scalable with the number of users and 2) transferable to different communication scenarios, such as non-stationary wireless channels, different…

As core counts and heterogeneity rise in HPC, traditional hybrid programming models face challenges in managing distributed GPU memory and ensuring portability. This paper presents DiOMP, a distributed OpenMP framework that unifies OpenMP…

In $k$-ported message-passing systems, a processor can simultaneously receive $k$ different messages from $k$ other processors, and send $k$ different messages to $k$ other processors that may or may not be different from the processors…

Large Language Models (LLMs) have become indispensable across various domains, but this comes at the cost of substantial computational and memory resources. Model pruning addresses this by removing redundant components from models. In…