Related papers: TransPimLib: A Library for Efficient Transcendenta…
Transformers are the driving force behind today's Large Language Models (LLMs), serving as the foundation for their performance and versatility. Yet, their compute and memory costs grow with sequence length, posing scalability challenges…
Hashmaps are widely utilized data structures in many applications to perform a probe on key-value pairs. However, their performance tends to degrade with the increase in the dataset size, which leads to expensive off-chip memory accesses to…
Fully Homomorphic Encryption (FHE) is a technique that allows arbitrary computations to be performed on encrypted data without the need for decryption, making it ideal for securing many emerging applications. However, FHE computation is…
Processing-in-memory (PIM), as a novel computing paradigm, provides significant performance benefits from the aspect of effective data movement reduction. SRAM-based PIM has been demonstrated as one of the most promising candidates due to…
Nowadays, various memory-hungry applications like machine learning algorithms are knocking "the memory wall". Toward this, emerging memories featuring computational capacity are foreseen as a promising solution that performs data process…
The performance bottleneck of deep-learning-based recommender systems resides in their backbone Deep Neural Networks. By integrating Processing-In-Memory~(PIM) architectures, researchers can reduce data movement and enhance energy…
Large model inference is shifting from cloud to edge due to concerns about the privacy of user interaction data. However, edge devices often struggle with limited computing power, memory, and bandwidth, requiring collaboration across…
Processing in memory (PIM) has received significant attention due to its high efficiency, low latency, and parallelism. In optical computation, coherent memory is a crucial infrastructure for PIM frameworks. This study presents an…
The separation of the data capture and analysis in modern vision systems has led to a massive amount of data transfer between the end devices and cloud computers, resulting in long latency, slow response, and high power consumption.…
Our ISCA 2015 paper provides a new programmable processing-in-memory (PIM) architecture and system design that can accelerate key data-intensive applications, with a focus on graph processing workloads. Our major idea was to completely…
The rise of data-intensive applications exposed the limitations of conventional processor-centric von-Neumann architectures that struggle to meet the off-chip memory bandwidth demand. Therefore, recent innovations in computer architecture…
The emerging memristive Memory Processing Unit (mMPU) overcomes the memory wall through memristive devices that unite storage and logic for real processing-in-memory (PIM) systems. At the core of the mMPU is stateful logic, which is…
In this paper, we present madmom, an open-source audio processing and music information retrieval (MIR) library written in Python. madmom features a concise, NumPy-compatible, object oriented design with simple calling conventions and…
High-performance computing systems are moving towards 2.5D and 3D memory hierarchies, based on High Bandwidth Memory (HBM) and Hybrid Memory Cube (HMC) to mitigate the main memory bottlenecks. This trend is also creating new opportunities…
In this paper, we propose FusionCIM, an operator-fusion-driven compute-in-memory (CIM) accelerator architecture for efficient and scalable LLM inference, with three key innovations: (1) a hybrid CIM pipeline architecture that maps QKT…
Memory performance is often the main bottleneck in modern computing systems. In recent years, researchers have attempted to scale the memory wall by leveraging new technology such as CXL, HBM, and in- and near-memory processing. Developers…
Our RLibm project generates a single implementation for an elementary function that produces correctly rounded results for multiple rounding modes and representations with up to 32-bits. They are appealing for developing fast reference…
Compute in-memory (CIM) is a promising technique that minimizes data transport, the primary performance bottleneck and energy cost of most data intensive applications. This has found wide-spread adoption in accelerating neural networks for…
Due to reduced manufacturing yields, traditional monolithic chips cannot keep up with the compute, memory, and communication demands of data-intensive applications, such as rapidly growing deep neural network (DNN) models. Chiplet-based…
The computing wall and data movement challenges of deep neural networks (DNNs) have exposed the limitations of conventional CMOS-based DNN accelerators. Furthermore, the deep structure and large model size will make DNNs prohibitive to…