Related papers: PIMCOMP: A Universal Compilation Framework for Cro…

Compiler optimization decisions are often based on hand-crafted heuristics centered around a few established benchmark suites. Alternatively, they can be learned from feature and performance data produced during compilation. However,…

Deep neural networks (DNNs) have revolutionized the field of artificial intelligence and have achieved unprecedented success in cognitive tasks such as image and speech recognition. Training of large DNNs, however, is computationally…

Text generation is a compelling sub-field of natural language processing, aiming to generate human-readable text from input words. In particular, the decoder-only generative models, such as generative pre-trained transformer (GPT), are…

Modern transformer-based Large Language Models (LLMs) are constructed with a series of decoder blocks. Each block comprises three key components: (1) QKV generation, (2) multi-head attention, and (3) feed-forward networks. In batched…

Analog Compute-in-Memory (CiM) accelerators are increasingly recognized for their efficiency in accelerating Deep Neural Networks (DNN). However, their dependence on Analog-to-Digital Converters (ADCs) for accumulating partial sums from…

Modular quantum processors require a compiler to reason about two resources at the same time: local device connectivity and communication across QPUs. A mapping that is acceptable on a single coupling graph may be unsuitable for a modular…

Mixed-precision neural networks (MPNNs) that enable the use of just enough data width for a deep learning task promise significant advantages of both inference accuracy and computing overhead. FPGAs with fine-grained reconfiguration…

Deploying mixed-precision neural networks on edge devices is friendly to hardware resources and power consumption. To support fully mixed-precision neural network inference, it is necessary to design flexible hardware accelerators for…

Genome sequence alignment is the core of many biological applications. The advancement of sequencing technologies produces a tremendous amount of data, making sequence alignment a critical bottleneck in bioinformatics analysis. The existing…

Transformers are gaining increasing attention across Natural Language Processing (NLP) application domains due to their outstanding accuracy. However, these data-intensive models add significant performance demands to the existing computing…

Several manufacturers have already started to commercialize near-bank Processing-In-Memory (PIM) architectures. Near-bank PIM architectures place simple cores close to DRAM banks and can yield significant performance and energy improvements…

Pipeline parallelism (PP) when training neural networks enables larger models to be partitioned spatially, leading to both lower network communication and overall higher hardware utilization. Unfortunately, to preserve the statistical…

The data transfer between a processor and memory has become a design bottleneck in data-intensive applications. Processing-In-Memory (PIM) is a practical approach to overcome the memory wall bottleneck. The 4:2 compressor is suitable for…

Compilers, while essential, are notoriously complex systems that demand prohibitively expensive human expertise to develop and maintain. The recent advancements in Large Language Models (LLMs) offer a compelling new paradigm: Neural…

The efficient deployment of large language models (LLMs) is hindered by memory architecture heterogeneity, where traditional compilers suffer from fragmented workflows and high adaptation costs. We present nncase, an open-source, end-to-end…

Quantum circuit simulations are essential for the verification of quantum algorithms on behalf of real quantum devices. However, the memory requirements for such simulations grow exponentially with the number of qubits involved in quantum…

The advent of Transformers has revolutionized computer vision, offering a powerful alternative to convolutional neural networks (CNNs), especially with the local attention mechanism that excels at capturing local structures within the input…

Compute-in-Memory (CIM) and weight sparsity are two effective techniques to reduce data movement during Neural Network (NN) inference. However, they can hardly be employed in the same accelerator simultaneously because CIM requires…

This paper discusses recent research that aims to enable computation close to data, an approach we broadly call processing-in-memory (PIM). PIM places computation mechanisms in or near where the data is stored (i.e., inside memory chips or…

Compute-Near-Memory (CNM) systems offer a promising approach to mitigate the von Neumann bottleneck by bringing computational units closer to data. However, optimizing for these architectures remains challenging due to their unique hardware…