Related papers: CMOS+X: Stacking Persistent Embedded Memories base…
The growing demand for efficient, high-performance processing in machine learning (ML) and image processing has made hardware accelerators, such as GPUs and Data Streaming Accelerators (DSAs), increasingly essential. These accelerators…
Approximate computing (AC) leverages the inherent error resilience and is used in many big-data applications from various domains such as multimedia, computer vision, signal processing, and machine learning to improve systems performance…
Dynamic 3D Gaussian splatting (3DGS) extends static 3DGS to render dynamic scenes, enabling AR/VR applications with moving objects. However, implementing dynamic 3DGS on edge devices faces challenges: (1) Loading all Gaussian parameters…
Large persistent memories such as NVDIMM have been perceived as a disruptive memory technology, because they can maintain the state of a system even after a power failure and allow the system to recover quickly. However, overheads incurred…
In this paper, we propose a 'full-stack' solution to designing high capacity and low latency on-chip cache hierarchies by starting at the circuit level of the hardware design stack. First, we propose a novel Gain Cell (GC) design using…
Compute-in-memory (CiM) is a promising approach to improving the computing speed and energy efficiency in dataintensive applications. Beyond existing CiM techniques of bitwise logic-in-memory operations and dot product operations, this…
High-Performance Computing (HPC) and Artificial Intelligence (AI) workloads typically demand substantial memory bandwidth and, to a degree, memory capacity. CXL memory expansion modules, also known as CXL "type-3" devices, enable…
CMOS technology and its continuous scaling have made electronics and computers accessible and affordable for almost everyone on the globe; in addition, they have enabled the solutions of a wide range of societal problems and applications.…
Combinatorial optimization problems are funda- mental for various fields ranging from finance to wireless net- works. This work presents a simulated bifurcation (SB) Ising solver in CMOS for NP-hard optimization problems. Analog domain…
Modern day applications have grown in size and require more computational power. The rise of machine learning and AI increased the need for parallel computation, which has increased the need for GPGPUs. With the increasing demand for…
We propose overcoming the memory capacity limitation of GPUs with high-capacity Storage-Class Memory (SCM) and DRAM cache. By significantly increasing the memory capacity with SCM, the GPU can capture a larger fraction of the memory…
Current soft processor architectures for FPGAs do not utilize the potential of the massive parallelism available. FPGAs now support many thousands of embedded floating point operators, and have similar computational densities to GPGPUs.…
Stochastic computing (SC) offers hardware simplicity but suffers from low throughput, while high-throughput Digital Computing-in-Memory (DCIM) is bottlenecked by costly adder logic for matrix-vector multiplication (MVM). To address this…
Today's systems are overwhelmingly designed to move data to computation. This design choice goes directly against at least three key trends in systems that cause performance, scalability and energy bottlenecks: (1) data access from memory…
Byte-addressable persistent memory (B-APM) presents a new opportunity to bridge the performance gap between main memory and storage. In this paper, we present the usage scenarios for this new technology, based on the capabilities of Intel's…
Transformers have emerged as a powerful tool for natural language processing (NLP) and computer vision. Through the attention mechanism, these models have exhibited remarkable performance gains when compared to conventional approaches like…
Emerging technologies present opportunities for system designers to meet the challenges presented by competing trends of big data analytics and limitations on CMOS scaling. Specifically, memristors are an emerging high-density technology…
Recently, single-stage embedding based deep learning algorithms gain increasing attention in cell segmentation and tracking. Compared with the traditional "segment-then-associate" two-stage approach, a single-stage algorithm not only…
Stacked intelligent metasurfaces (SIMs) have emerged as a disruptive technology for future wireless networks. To investigate their capabilities, we study the sum rate maximization problem in an SIM-based multiuser (MU) multiple-input…
Software managed byte-addressable hybrid memory systems consisting of DRAMs and NVMMs offer a lot of flexibility to design efficient large scale data processing applications. Operating systems (OS) play an important role in enabling the…