Related papers: Transitive Array: An Efficient GEMM Accelerator wi…

Analytical framework for predicting General Matrix Multiplication (GEMM) performance on modern GPUs, focusing on runtime, power consumption, and energy efficiency. Our study employs two approaches: a custom-implemented tiled matrix…

Large Multimodal Models (LMMs) have achieved remarkable success in vision-language tasks, yet their vast parameter counts are often underutilized during both training and inference. In this work, we embrace the idea of looping back to move…

The inference and training stages of Graph Neural Networks (GNNs) are often dominated by the time required to compute a long sequence of matrix multiplications between the sparse graph adjacency matrix and its embedding. To accelerate these…

We present "GEMM-like Tensor-Tensor multiplication" (GETT), a novel approach to tensor contractions that mirrors the design of a high-performance general matrix-matrix multiplication (GEMM). The critical insight behind GETT is the…

Many convolutional neural network (CNN) accelerators face performance- and energy-efficiency challenges which are crucial for embedded implementations, due to high DRAM access latency and energy. Recently, some DRAM architectures have been…

Generic matrix multiplication (GEMM) and one-dimensional convolution/cross-correlation (CONV) kernels often constitute the bulk of the compute- and memory-intensive processing within image/audio recognition and matching systems. We propose…

Modern deep learning models have high memory and computation cost. To make them fast and memory-cost efficient, structured model pruning is commonly used. We find that pruning a model using a common training accelerator with large systolic…

The deployment of neural networks on heterogeneous SoCs coupled with custom accelerators is a challenging task because of the lack of end-to-end software tools provided for these systems. Moreover, the already available low level schedules…

We propose a novel acceleration technique for loops operating on arrays. The goal of acceleration is to characterize the transitive closure of loops in a logic which is suitable for automated reasoning. Using the new notion of inductive…

DL inference queries play an important role in diverse internet services and a large fraction of datacenter cycles are spent on processing DL inference queries. Specifically, the matrix-matrix multiplication (GEMM) operations of…

Graph neural networks (GNNs) emerge as a powerful approach to process non-euclidean data structures and have been proved powerful in various application domains such as social networks and e-commerce. While such graph data maintained in…

Recurrent Neural Network (RNN) applications form a major class of AI-powered, low-latency data center workloads. Most execution models for RNN acceleration break computation graphs into BLAS kernels, which lead to significant inter-kernel…

Deep neural network (DNN) inference relies increasingly on specialized hardware for high computational efficiency. This work introduces a field-programmable gate array (FPGA)-based dynamically configurable accelerator featuring systolic…

General-purpose processor vendors have integrated customized accelerator in their products due to the widespread use of General Matrix-Matrix Multiplication (GEMM) kernels. However, it remains a challenge to further improve the…

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to auto-regressive (AR) models, offering greater expressive capacity and potential for parallel generation and faster inference. However, open-source dLLMs…

It is appealing but challenging to achieve real-time deep neural network (DNN) inference on mobile devices because even the powerful modern mobile devices are considered as ``resource-constrained'' when executing large-scale DNNs. It…

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 growing adoption of domain-specific architectures in edge computing platforms for deep learning has highlighted the efficiency of hardware accelerators. However, integrating custom accelerators into modern machine learning (ML)…

Deep neural networks (DNN) have become significant applications in both cloud-server and edge devices. Meanwhile, the growing number of DNNs on those platforms raises the need to execute multiple DNNs on the same device. This paper proposes…

Modern machine learning accelerators are designed to efficiently execute deep neural networks (DNNs) by optimizing data movement, memory hierarchy, and compute throughput. However, emerging DNN models such as large language models, state…