category: Technical Papers

category: Auto, Security & Edge AI

Multistep staircase avalanche photodiodes with extremely low noise & deterministic amplification (lidar)
By Technical Paper Link - 27 Jul, 2021 - Comments: 0

Engineers at University of Texas at Austin and University of Virginia developed a light detector that can amplify weak light signals and reduce noise to improve the accuracy of lidar. Find technical paper here. Abstract "In 1982, Capasso and co-workers proposed the solid-state analogue of the photomultiplier tube, termed the staircase avalanche photodiode. Through a combination of co... » read more

Emergent magnetic monopoles isolated using quantum-annealing computer
By Technical Paper Link - 27 Jul, 2021 - Comments: 0

Using D-Wave’s quantum-annealing computer, Los Alamos National Laboratory has shown that it’s possible to isolate magnetic monopoles. This research could one day enable future nanomagnets.   Abstract: "Artificial spin ices are frustrated spin systems that can be engineered, wherein fine tuning of geometry and topology has allowed the design and characterization of exotic eme... » read more

Underlayer Optimization Method For EUV Lithography
By Brewer Science - 21 Jul, 2021 - Comments: 0

Photoresist and underlayer combine to serve a central role in EUVL for patterning. Layers will be very thin in future, because high numerical aperture (NA) and tight pitches will require very thin layers in the lithography stack. This thinness will make chemical interactions at the photoresist-underlayer interface more common. Adhesion between these layers will be critical to overcome pattern c... » read more

Efficient Multi-GPU Shared Memory via Automatic Optimization of Fine-Grained Transfers
By Technical Paper Link - 02 Jul, 2021 - Comments: 0

Harini Muthukrishnan (U of Michigan); David Nellans, Daniel Lustig (NVIDIA); Jeffrey A. Fessler, Thomas Wenisch (U of Michigan). Abstract—"Despite continuing research into inter-GPU communication mechanisms, extracting performance from multiGPU systems remains a significant challenge. Inter-GPU communication via bulk DMA-based transfers exposes data transfer latency on the GPU’s critical... » read more

SARA: Scaling a Reconfigurable Dataflow Accelerator
By Technical Paper Link - 02 Jul, 2021 - Comments: 0

Yaqi Zhang, Nathan Zhang, Tian Zhao, Matt Vilim, Muhammad Shahbaz, Kunle Olukotun (Stanford) Abstract—"The need for speed in modern data-intensive workloads and the rise of “dark silicon” in the semiconductor industry are pushing for larger, faster, and more energy and areaefficient architectures, such as Reconfigurable Dataflow Accelerators (RDAs). Nevertheless, challenges remain in d... » read more

REDUCT: Keep It Close, Keep It Cool – Scaling DNN Inference on Multi-Core CPUs with Near-Cache Compute
By Technical Paper Link - 02 Jul, 2021 - Comments: 0

Abstract—"Deep Neural Networks (DNN) are used in a variety of applications and services. With the evolving nature of DNNs, the race to build optimal hardware (both in datacenter and edge) continues. General purpose multi-core CPUs offer unique attractive advantages for DNN inference at both datacenter [60] and edge [71]. Most of the CPU pipeline design complexity is targeted towards optimizin... » read more

RaPiD: AI Accelerator for Ultra-low Precision Training and Inference
By Technical Paper Link - 02 Jul, 2021 - Comments: 0

Abstract—"The growing prevalence and computational demands of Artificial Intelligence (AI) workloads has led to widespread use of hardware accelerators in their execution. Scaling the performance of AI accelerators across generations is pivotal to their success in commercial deployments. The intrinsic error-resilient nature of AI workloads present a unique opportunity for performance/energy i... » read more

PF-DRAM: A Precharge-Free DRAM Structure
By Technical Paper Link - 02 Jul, 2021 - Comments: 0

Authors: Nezam Rohbani † (IPM); Sina Darabii § (Sharif); Hamid Sarbazi-Azad † i §(Sharif / IPM): † School of Computer Science, Institute for Research in Fundamental Sciences (IPM), Tehran, Iran § Department of Computer Engineering, Sharif University of Technology, Tehran, Iran Abstract: "Although DRAM capacity and bandwidth have increased sharply by the advances in technology ... » read more

High-Temperature-Stable, Spin-On Carbon Materials For High-Aspect-Ratio Gap-Fill Applications
By Brewer Science - 16 Jun, 2021 - Comments: 0

Brewer Science, Inc. has developed a class of novel, high-temperature-stable spin-on carbon (SOC)-based materials with excellent processability. These SOCs are cured under mild conditions and have flow properties that enable the fill of high-aspect-ratio vias in a void-free manner. Moreover, this new class of SOCs has remarkable thermal stability and can survive temperatures of up to 550°C wit... » read more

NN-Baton: DNN Workload Orchestration & Chiplet Granularity Exploration for Multichip Accelerators
By Technical Paper Link - 14 Jun, 2021 - Comments: 0

"Abstract—The revolution of machine learning poses an unprecedented demand for computation resources, urging more transistors on a single monolithic chip, which is not sustainable in the Post-Moore era. The multichip integration with small functional dies, called chiplets, can reduce the manufacturing cost, improve the fabrication yield, and achieve die-level reuse for different system scales... » read more

← Older posts Newer posts →

  • Sponsors

About

Navigation

Connect With Us

Copyright ©2013-2026 SMG   |  Terms of Service  |  Privacy Policy