Related papers: Challenges and opportunities integrating LLAMA int…

On the way to Exascale, programmers face the increasing challenge of having to support multiple hardware architectures from the same code base. At the same time, portability of code and performance are increasingly difficult to achieve as…

The explosive growth of multi-source multimedia data has significantly increased the demands for transmission and storage, placing substantial pressure on bandwidth and storage infrastructures. While Autoregressive Compression Models (ACMs)…

We introduce the CUDA Tensor Transpose (cuTT) library that implements high-performance tensor transposes for NVIDIA GPUs with Kepler and above architectures. cuTT achieves high performance by (a) utilizing two GPU-optimized transpose…

Memory disaggregation is promising to scale memory capacity and improves utilization in HPC systems. However, the performance overhead of accessing remote memory poses a significant challenge, particularly for compute-intensive HPC…

In this work we present the porting to Graphics Processing Units (GPUs, using OpenMP target directives) and optimization of a key module within the cosmological {\pinocchio} code, a Lagrangian Perturbation Theory (LPT)-based framework…

With the increasing physical event rate and number of electronic channels, traditional readout scheme meets the challenge of improving readout speed caused by the limited bandwidth of crate backplane. In this paper, a high-speed data…

The substantial computational and memory demands of Large Language Models (LLMs) hinder their deployment. Block Floating Point (BFP) has proven effective in accelerating linear operations, a cornerstone of LLM workloads. However, as…

Transformers have become the backbone of neural network architecture for most machine learning applications. Their widespread use has resulted in multiple efforts on accelerating attention, the basic building block of transformers. This…

Tabular data streams are increasingly prevalent in real-time decision-making across healthcare, finance, and the Internet of Things, often generated and processed on resource-constrained edge and mobile devices. Continual learning (CL)…

Edge computing offers the distinct advantage of harnessing compute capabilities on resources located at the edge of the network to run workloads of relatively weak user devices. This is achieved by offloading computationally intensive…

Pipeline parallelism (PP) is widely used for training large language models (LLMs), yet its scalability is often constrained by high activation memory consumption as the number of in-flight microbatches grows with the degree of PP. In this…

The configurable building blocks of current FPGAs -- Logic blocks (LBs), Digital Signal Processing (DSP) slices, and Block RAMs (BRAMs) -- make them efficient hardware accelerators for the rapid-changing world of Deep Learning (DL).…

Large Language Models (LLMs) demand substantial computational resources, resulting in high energy consumption on GPUs. To address this challenge, we focus on Coarse-Grained Reconfigurable Arrays (CGRAs) as an effective alternative that…

The growing demand for efficient, high-performance processing in machine learning (ML) and image processing has made hardware accelerators, such as GPUs and Data Streaming Accelerators (DSAs), increasingly essential. These accelerators…

Transformer models serve as the backbone of many state-ofthe-art language models, and most use the scaled dot-product attention (SDPA) mechanism to capture relationships between tokens. However, the straightforward implementation of SDPA…

The growing demands in the training and inference of Large Language Models (LLMs) are accelerating the adoption of scale-up systems that extend server shared memory through the use of Compute Express Link (CXL)-based load/store…

Graphics processing units (GPU) had evolved from a specialized hardware capable to render high quality graphics in games to a commodity hardware for effective processing blocks of data in a parallel schema. This evolution is particularly…

We introduce a class of specially structured linear programming (LP) problems, which has favorable modeling capability for important application problems in different areas such as optimal transport, discrete tomography and economics. To…

Large Language Models (LLMs) have become essential in a variety of applications due to their advanced language understanding and generation capabilities. However, their computational and memory requirements pose significant challenges to…

Context. The magnetic field in the solar atmosphere continually reconnects and accelerates charged particles to high energies. Simulations of the atmosphere in three dimensions that include the effects of accelerated particles can aid our…