Related papers: AIM: Accelerating Arbitrary-precision Integer Mult…

The use of reconfigurable computing, and FPGAs in particular, to accelerate computational kernels has the potential to be of great benefit to scientific codes and the HPC community in general. However, whilst recent advanced in FPGA tooling…

The deployment of large language models (LLMs) presents significant challenges due to their enormous memory footprints, low arithmetic intensity, and stringent latency requirements, particularly during the autoregressive decoding stage.…

The increasing computational and memory requirements of Deep Learning (DL) workloads has led to outstanding innovations in hardware architectures. An archetype of such architectures is the novel Versal AI Engine (AIE) by AMD/Xilinx. The AIE…

The rise of generative AI for tasks like Automatic Speech Recognition (ASR) has created a critical energy consumption challenge. While ASICs offer high efficiency, they lack the programmability to adapt to evolving algorithms. To address…

In recent years, quantum Ising machines have drawn a lot of attention, but due to physical implementation constraints, it has been difficult to achieve dense coupling, such as full coupling with sufficient spins to handle practical…

In the era of artificial intelligence (AI), Transformer demonstrates its performance across various applications. The excessive amount of parameters incurs high latency and energy overhead when processed in the von Neumann architecture.…

The demand for energy-efficient and high performance embedded systems drives the evolution of new hardware architectures, including concepts like approximate computing. This paper presents a novel reconfigurable embedded platform named…

Convolutional Neural Networks (CNNs) are widely used in deep learning applications, e.g. visual systems, robotics etc. However, existing software solutions are not efficient. Therefore, many hardware accelerators have been proposed…

Emerging machine learning (ML) models (e.g., transformers) involve memory pin bandwidth-bound matrix-vector (MV) computation in inference. By avoiding pin crossings, processing in memory (PIM) can improve performance and energy for…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources to improve factual accuracy and verifiability. However, this reliance introduces new attack surfaces within…

ADAPT-VQE stands out as a robust algorithm for constructing compact ans\"atze for molecular simulation. It enables to significantly reduce the circuit depth with respect to other methods, such as UCCSD, while achieving higher accuracy and…

Approximate computing is a promising approach to reduce the power, delay, and area in hardware design for many error-resilient applications such as machine learning (ML) and digital signal processing (DSP) systems, in which multipliers…

Processing-in-DRAM (DRAM-PIM) has emerged as a promising technology for accelerating memory-intensive operations in modern applications, such as Large Language Models (LLMs). Despite its potential, current software stacks for DRAM-PIM face…

We propose Atomic Active Messages (AAM), a mechanism that accelerates irregular graph computations on both shared- and distributed-memory machines. The key idea behind AAM is that hardware transactional memory (HTM) can be used for simple…

Over the years, accelerating neural networks with quantization has been widely studied. Unfortunately, prior efforts with diverse precisions (e.g., 1-bit weights and 2-bit activations) are usually restricted by limited precision support on…

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).…

Efficient AI inference on AMD's Versal AI Engine (AIE) is challenging due to tightly coupled VLIW execution, explicit datapaths, and local memory management. Prior work focused on first-generation AIE kernel optimizations, without tackling…

Energy system optimization models are increasing in scope and resolution, yielding large and challenging linear programs. For a long time, the standard way to address such problems has relied on shared-memory interior-point methods (IPM),…

The substantial memory bandwidth and computational demands of large language models (LLMs) present critical challenges for efficient inference. To tackle this, the literature has explored heterogeneous systems that combine neural processing…

Developing accurate and reliable Compute-In-Memory (CIM) architectures is becoming a key research focus to accelerate Artificial Intelligence (AI) tasks on hardware, particularly Deep Neural Networks (DNNs). In that regard, there has been…