Related papers: HPTMT: Operator-Based Architecture for Scalable Hi…
Python is the de-facto language for software development in artificial intelligence (AI). Commonly used libraries, such as PyTorch and TensorFlow, rely on parallelization built into their BLAS backends to achieve speedup on CPUs. However,…
OpenMP has been the de facto standard for single node parallelism for more than a decade. Recently, asynchronous many-task runtime (AMT) systems have increased in popularity as a new programming paradigm for high performance computing…
Despite the increasing adoption of Field-Programmable Gate Arrays (FPGAs) in compute clouds, there remains a significant gap in programming tools and abstractions which can leverage network-connected, cloud-scale, multi-die FPGAs to…
This work aims to bridge the existing knowledge gap in the optimisation of latency-critical code, specifically focusing on high-frequency trading (HFT) systems. The research culminates in three main contributions: the creation of a…
Training state-of-the-art large language models requires vast amounts of clean and diverse textual data. However, building suitable multilingual datasets remains a challenge. In this work, we present HPLT v2, a collection of high-quality…
Persistent topological Laplacians are operators that provide persistent Betti numbers and additional multiscale geometric information through the eigenvalues of the persistent topological Laplacian matrix. We introduce a framework and novel…
State-of-the-art Transformer-based models, with gigantic parameters, are difficult to be accommodated on resource constrained embedded devices. Moreover, with the development of technology, more and more embedded devices are available to…
Heterogeneous computing platforms consisting of general purpose processors (GPPs) and graphics processing units (GPUs) have become commonplace in personal mobile devices and embedded systems. For years, programming of these platforms was…
Dedicated tensor accelerators demonstrate the importance of linear algebra in modern applications. Such accelerators have the potential for impressive performance gains, but require programmers to rewrite code using vendor APIs - a barrier…
As we reach exascale, production High Performance Computing (HPC) systems are increasing in complexity. These systems now comprise multiple heterogeneous computing components (CPUs and GPUs) utilized through diverse, often vendor-specific…
Python has become the prime language for application development in the Data Science and Machine Learning domains. However, data scientists are not necessarily experienced programmers. While Python lets them quickly implement their…
The algorithm-to-hardware High-level synthesis (HLS) tools today are purported to produce hardware comparable in quality to handcrafted designs, particularly with user directive driven or domains specific HLS. However, HLS tools are not…
In this paper, we introduce MCTensor, a library based on PyTorch for providing general-purpose and high-precision arithmetic for DL training. MCTensor is used in the same way as PyTorch Tensor: we implement multiple basic, matrix-level…
Exceptions and errors occurring within mission critical applications due to hardware failures have a high cost. With the emerging Next Generation Platforms (NGPs), the rate of hardware failures will likely increase. Therefore, designing our…
Executing machine learning inference tasks on resource-constrained edge devices requires careful hardware-software co-design optimizations. Recent examples have shown how transformer-based deep neural network models such as ALBERT can be…
General matrix-matrix multiplication (GEMM) is a cornerstone of AI computations, making tensor processing engines (TPEs) increasingly critical in GPUs and domain-specific architectures. Existing architectures primarily optimize dataflow or…
The increasing complexity and diversity of hardware accelerators in modern computing systems demand flexible, low-overhead program analysis tools. We present PASTA, a low-overhead and modular Program AnalysiS Tool Framework for…
The rapid scaling of Large Language Models (LLMs) has pushed training workloads far beyond the limits of single-node analysis, demanding a deeper understanding of how these models behave across large-scale, multi-GPU systems. In this paper,…
Very few of the innovations in deep networking have seen data center scale implementation. Because the Data Center network's extreme scale performance requires hardware implementation, which is only accessible to a few. However, the…
Over recent years heterogeneous systems have become more prevalent across HPC systems, with over 100 supercomputers in the TOP500 incorporating GPUs or other accelerators. These hardware platforms have different performance characteristics…