Related papers: Neurostream: Scalable and Energy Efficient Deep Le…

This research work proposes a design of an analog ReRAM-based PIM (processing-in-memory) architecture for fast and efficient CNN (convolutional neural network) inference. For the overall architecture, we use the basic hardware hierarchy…

This paper introduces NeuroBlend, a novel neural network architecture featuring a unique building block known as the Blend module. This module incorporates binary and fixed-point convolutions in its main and skip paths, respectively. There…

In modern computer architectures, the performance of many memory-bound workloads (e.g., machine learning, graph processing, databases) is limited by the data movement bottleneck that emerges when transferring large amounts of data between…

Edge deployment of low-batch large language models (LLMs) faces critical memory bandwidth bottlenecks when executing memory-intensive general matrix-vector multiplications (GEMV) operations. While digital processing-in-memory (PIM)…

Binary neural networks (BNNs) that use 1-bit weights and activations have garnered interest as extreme quantization provides low power dissipation. By implementing BNNs as computing-in-memory (CIM), which computes multiplication and…

Emerging nano-scale programmable Resistive-RAM (RRAM) has been identified as a promising technology for implementing brain-inspired computing hardware. Several neural network architectures, that essentially involve computation of scalar…

Neuromorphic Systems-on-Chip (NSoCs) are becoming heterogeneous by integrating general-purpose processors (GPPs) and neural processing units (NPUs) on the same SoC. For embedded systems, an NSoC may need to execute user applications built…

AI data centers are increasingly becoming tightly coupled compute--energy systems, where workload placement, cooling demand, electricity procurement, storage operation, and carbon emissions interact over time. This paper studies…

Deep convolution Neural Network (DCNN) has been widely used in computer vision tasks. However, for edge devices even inference has too large computational complexity and data access amount. The inference latency of state-of-the-art models…

Vision Transformers (ViTs) have established new performance benchmarks in vision tasks such as image recognition and object detection. However, these advancements come with significant demands for memory and computational resources,…

Compute-in-memory (CIM) techniques are widely employed in energy-efficient artificial intelligent (AI) processors. They alleviate power and latency bottlenecks caused by extensive data movements between compute and storage units. To extend…

The AI problem has no solution in the environment of existing hardware stack and OS architecture. CPU-centric model of computation has a huge number of drawbacks that originate from memory hierarchy and obsolete architecture of the…

Demand for data-intensive workloads and confidential computing are the prominent research directions shaping the future of cloud computing. Computer architectures are evolving to accommodate the computing of large data better. Protecting…

Analog compute-in-memory (CIM) in static random-access memory (SRAM) is promising for accelerating deep learning inference by circumventing the memory wall and exploiting ultra-efficient analog low-precision arithmetic. Latest analog CIM…

We address the challenges associated with deploying neural networks on CPUs, with a particular focus on minimizing inference time while maintaining accuracy. Our novel approach is to use the dataflow (i.e., computation order) of a neural…

Cryogenic neuromorphic systems, inspired by the brains unparalleled efficiency, present a promising paradigm for next generation computing architectures.This work introduces a fully integrated neuromorphic framework that combines…

Processing-using-DRAM (PUD) is a processing-in-memory (PIM) approach that uses a DRAM array's massive internal parallelism to execute very-wide data-parallel operations, in a single-instruction multiple-data (SIMD) fashion. However, DRAM…

Recently, crossbar array based in-memory accelerators have been gaining interest due to their high throughput and energy efficiency. While software and compiler support for the in-memory accelerators has also been introduced, they are…

Computing-in-Memory (CIM) macros have gained popularity for deep learning acceleration due to their highly parallel computation and low power consumption. However, limited macro size and ADC precision introduce throughput and accuracy…

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…