Related papers: PlaceIT: Placement-based Inter-Chiplet Interconnec…
For its advantage in GPU acceleration and less dependency on human experts, machine learning has been an emerging tool for solving the placement and routing problems, as two critical steps in modern chip design flow. Being still in its…
Trapped-ion qubits are a leading technology for practical quantum computing. In this work, we present an architectural analysis of a linear-tape architecture for trapped ions. In order to realize our study, we develop and evaluate mapping…
The 6TiSCH protocol stack plays a vital role in enabling reliable and energy-efficient communications for the Industrial Internet of Things (IIoT). However, it faces challenges, including prolonged network formation, inefficient parent…
The increase in design cost and complexity have motivated designers to adopt modular design of System on Chip (SoC) by integrating independently designed small chiplets. However, it introduces new challenges for correctness validation,…
Modern machine learning (ML) applications are becoming increasingly complex and monolithic (single chip) accelerator architectures cannot keep up with their energy efficiency and throughput demands. Even though modern digital electronic…
Transformers have revolutionized deep learning and generative modeling, enabling advancements in natural language processing tasks. However, the size of transformer models is increasing continuously, driven by enhanced capabilities across…
We present Placeto, a reinforcement learning (RL) approach to efficiently find device placements for distributed neural network training. Unlike prior approaches that only find a device placement for a specific computation graph, Placeto…
Dedicated, after acceptance and publication, in memory of the late Vassos Soteriou. For the first time, we leverage the 2.5D interposer technology to establish system-level security in the face of hardware- and software-centric adversaries.…
In recent years, deep learning models have become ubiquitous in industry and academia alike. Deep neural networks can solve some of the most complex pattern-recognition problems today, but come with the price of massive compute and memory…
Multi-die FPGAs are crucial components in modern computing systems, particularly for high-performance applications such as artificial intelligence and data centers. Super long lines (SLLs) provide interconnections between super logic…
In implant prosthesis treatment, the design of the surgical guide heavily relies on the manual location of the implant position, which is subjective and prone to doctor's experiences. When deep learning based methods has started to be…
Automated placement of components on printed circuit boards (PCBs) is a critical stage in placement layout design. While reinforcement learning (RL) has been successfully applied to system-on-chip IP block placement and chiplet arrangement…
Interface localization-delocalization transitions (ILDT) occur in two-phase fluids confined in a slit with competing preferences of the walls for the two fluid phases. At low temperatures the interface between the two phases is localized at…
Ion trap technologies have earned significant attention as potential candidates for quantum information processing due to their long decoherence times and precise manipulation of individual qubits, distinguishing them from other candidates…
Cloud-based computing technology is one of the most significant technical advents of the last decade and extension of this facility towards access networks by aggregation of cloudlets is a step further. To fulfill the ravenous demand for…
Rapidly evolving artificial intelligence and machine learning applications require ever-increasing computational capabilities, while monolithic 2D design technologies approach their limits. Heterogeneous integration of smaller chiplets…
In this work, we present a learning-based approach to chip placement, one of the most complex and time-consuming stages of the chip design process. Unlike prior methods, our approach has the ability to learn from past experience and improve…
Pre-trained language models are increasingly important components across multiple information retrieval (IR) paradigms. Late interaction, introduced with the ColBERT model and recently refined in ColBERTv2, is a popular paradigm that holds…
Parallel programming is emerging fast and intensive applications need more resources, so there is a huge demand for on-chip multiprocessors. Accessing L1 caches beside the cores are the fastest after registers but the size of private caches…
Network switches and routers need to serve packet writes and reads at rates that challenge the most advanced memory technologies. As a result, scaling the switching rates is commonly done by parallelizing the packet I/Os using multiple…