Related papers: StreamDCIM: A Tile-based Streaming Digital CIM Acc…
Diffusion Transformers (DiTs) have gained increasing adoption in high-quality image and video generation. As demand for higher-resolution images and longer videos increases, single-GPU inference becomes inefficient due to increased latency…
Intelligent metasurfaces may be harnessed for realizing efficient holographic multiple-input and multiple-output (MIMO) systems, at a low hardware-cost and high energy-efficiency. As part of this family, we propose a hybrid beamforming…
Expanding Deep Learning applications toward edge computing demands architectures capable of delivering high computational performance and efficiency while adhering to tight power and memory constraints. Digital In-Memory Computing (DIMC)…
Multiple-input multiple-output (MIMO) orthogonal frequency-division multiplexing (OFDM) systems rely on digital or hybrid digital and analog designs for beamforming against frequency-selective fading, which suffer from high hardware…
Deep learning (DL) models are piquing high interest and scaling at an unprecedented rate. To this end, a handful of tiled accelerators have been proposed to support such large-scale training tasks. However, these accelerators often…
In contrast to traditional videos, the imaging in virtual reality (VR) is 360{\deg}, and it consumes larger bandwidth to transmit video contents. To reduce bandwidth consumption, tile-based streaming has been proposed to deliver the focused…
Transformers are central to advances in artificial intelligence (AI), excelling in fields ranging from computer vision to natural language processing. Despite their success, their large parameter count and computational demands challenge…
Tydi is an open specification for streaming dataflow designs in digital circuits, allowing designers to express how composite and variable-length data structures are transferred over streams using clear, data-centric types. These data types…
As an emerging type of AI computing accelerator, SRAM Computing-In-Memory (CIM) accelerators feature high energy efficiency and throughput. However, various CIM designs and under-explored mapping strategies impede the full exploration of…
Various processing-in-memory (PIM) accelerators based on various devices, micro-architectures, and interfaces have been proposed to accelerate deep neural networks (DNNs). How to deploy DNNs onto PIM-based accelerators is the key to explore…
Tile-based many-Processing Element (PE) accelerators can achieve competitive performance on General Matrix Multiplication (GEMM), but they are extremely hard to program, as their optimal software mapping is deeply coupled with hardware…
Real-time processing of data streams emanating from sensors is becoming a common task in Internet of Things scenarios. The key implementation goal consists in efficiently handling massive incoming data streams and supporting advanced data…
Analog In-Memory Computing (AIMC) is emerging as a disruptive paradigm for heterogeneous computing, potentially delivering orders of magnitude better peak performance and efficiency over traditional digital signal processing architectures…
Stream computing is the use of multiple autonomic and parallel modules together with integrative processors at a higher level of abstraction to embody "intelligent" processing. The biological basis of this computing is sketched and the…
Analog Computing-in-Memory (ACIM) is an emerging architecture to perform efficient AI edge computing. However, current ACIM designs usually have unscalable topology and still heavily rely on manual efforts. These drawbacks limit the ACIM…
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…
The enhanced efficiency of hardware accelerators, including Single Instruction Multiple Data (SIMD) architectures and Coarse-Grained Reconfigurable Architectures (CGRAs), is driving significant advancements in Artificial Intelligence and…
Compute-in-memory (CIM) accelerators for spiking neural networks (SNNs) are promising solutions to enable $\mu$s-level inference latency and ultra-low energy in edge vision applications. Yet, their current lack of flexibility at both the…
Stacked intelligent metasurface (SIM) is an emerging design that consists of multiple layers of metasurfaces. A SIM enables holographic multiple-input multiple-output (HMIMO) precoding in the wave domain, which results in the reduction of…
Processing-in-memory (PIM) has emerged as a promising solution for accelerating memory-intensive workloads as they provide high memory bandwidth to the processing units. This approach has drawn attention not only from the academic community…