Related papers: AutoMM: Energy-Efficient Multi-Data-Type Matrix Mu…
Traditional von Neumann architecture based processors become inefficient in terms of energy and throughput as they involve separate processing and memory units, also known as~\textit{memory wall}. The memory wall problem is further…
General Matrix Multiplication (GEMM) has a wide range of applications in scientific simulation and artificial intelligence. Although traditional libraries can achieve high performance on large regular-shaped GEMMs, they often behave not…
The energy efficiency of analog computing-in-memory (ACIM) accelerator for recurrent neural networks, particularly long short-term memory (LSTM) network, is limited by the high proportion of nonlinear (NL) operations typically executed…
Transformer-based Large Language Models (LLMs) have made a significant impact on various domains. However, LLMs' efficiency suffers from both heavy computation and memory overheads. Compression techniques like sparsification and…
Power efficiency is a critical design objective in modern CPU design. Architects need a fast yet accurate architecture-level power evaluation tool to perform early-stage power estimation. However, traditional analytical architecture-level…
Recently, large language models (LLMs) have achieved huge success in the natural language processing (NLP) field, driving a growing demand to extend their deployment from the cloud to edge devices. However, deploying LLMs on…
Many of today's deep neural network accelerators, e.g., Google's TPU and NVIDIA's tensor core, are built around accelerating the general matrix multiplication (i.e., GEMM). However, supporting convolution on GEMM-based accelerators is not…
The exponential growth of artificial intelligence (AI) applications has exposed the inefficiency of conventional von Neumann architectures, where frequent data transfers between compute units and memory create significant energy and latency…
General matrix multiplication (GeMM) is a core operation in virtually all AI applications. Systolic array (SA) based architectures have shown great promise as GeMM hardware accelerators thanks to their speed and energy efficiency.…
Chiplet-based integration enables large-scale systems that combine diverse technologies, enabling higher yield, lower costs, and scalability, making them well-suited to AI workloads. Processing-in-Memory (PIM) has emerged as a promising…
Large Language Models (LLMs) show promise for automated code optimization but struggle without performance context. This work introduces Opal, a modular framework that connects performance analytics insights with the vast body of published…
SRAM-based compute-in-memory (CIM) offers high computational density and energy efficiency for deep neural network (DNN) accelerators, but its limited capacity causes on/off-chip data movement overhead for large DNN models. Existing CIM…
In recent years, HPC systems and CPU architectures as their central components, have become increasingly complex, making application development and optimization quite challenging. In this respect, intuitive performance models like the…
Decoder-only Transformer models such as GPT have demonstrated exceptional performance in text generation, by autoregressively predicting the next token. However, the efficacy of running GPT on current hardware systems is bounded by low…
In this study, we propose a novel machine learning based algorithm to improve the performance of beyond 5 generation (B5G) wireless communication system that is assisted by Orthogonal Frequency Division Multiplexing (OFDM) and…
Processing-in-memory (PIM) architectures have demonstrated great potential in accelerating numerous deep learning tasks. Particularly, resistive random-access memory (RRAM) devices provide a promising hardware substrate to build PIM…
Symbolic accelerators are increasingly used for symbolic data processing in domains such as genomics, NLP, and cybersecurity. However, these accelerators face scalability issues due to excessive memory use and routing complexity, especially…
Large matrix multiplication is a cornerstone of modern machine learning workloads, yet traditional approaches suffer from cubic computational complexity (e.g., $\mathcal{O}(n^3)$ for a matrix of size $n\times n$). We present Low-Rank GEMM,…
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…
Modern Neural Network (NN) architectures heavily rely on vast numbers of multiply-accumulate arithmetic operations, constituting the predominant computational cost. Therefore, this paper proposes a high-throughput, scalable and energy…