اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدMorphoNoC: Exploring the Design Space of a Configurable Hybrid NoC using Nanophotonics
81
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
As diminishing feature sizes drive down the energy for computations, the power budget for on-chip communication is steadily rising. Furthermore, the increasing number of cores is placing a huge performance burden on the network-on-chip (NoC) infrastructure. While NoCs are designed as regular architectures that allow scaling to hundreds of cores, the lack of a flexible topology gives rise to higher latencies, lower throughput, and increased energy costs. In this paper, we explore MorphoNoCs - scalable, configurable, hybrid NoCs obtained by extending regular electrical networks with configurable nanophotonic links. In order to design MorphoNoCs, we first carry out a detailed study of the design space for Multi-Write Multi-Read (MWMR) nanophotonics links. After identifying optimum design points, we then discuss the router architecture for deploying them in hybrid electronic-photonic NoCs. We then study explore the design space at the network level, by varying the waveguide lengths and the number of hybrid routers. This affords us to carry out energy-latency trade-offs. For our evaluations, we adopt traces from synthetic benchmarks as well as the NAS Parallel Benchmark suite. Our results indicate that MorphoNoCs can achieve latency improvements of up to 3.0x or energy improvements of up to 1.37x over the base electronic network.
قيم البحث
اقرأ أيضاً
Advances in the field of plasmonics, that is, nanophotonics based on optical properties of metal nanostructures, paved the way for the development of ultrasensitive biological sensors and other devices whose operating principles are based on localiza
tion of an electromagnetic field at the nanometer scale. However, high dissipative losses of metal nanostructures limit their performance in many modern areas, including metasurfaces, metamaterials, and optical interconnections, which required the development of new devices that combine them with high refractive index dielectric nanoparticles. Resulting metal-dielectric (hybrid) nanostructures demonstrated many superior properties from the point of view of practical application, including moderate dissipative losses, resonant optical magnetic response, strong nonlinear optical properties, which made the development in this field the vanguard of the modern light science. This review is devoted to the current state of theoretical and experimental studies of hybrid metal-dielectric nanoantennas and nanostructures based on them, capable of selective scattering light waves, amplifying and transmitting optical signals in the desired direction, controlling the propagation of such signals, and generating optical harmonics.
A major hurdle to the deployment of quantum linear systems algorithms and recent quantum simulation algorithms lies in the difficulty to find inexpensive reversible circuits for arithmetic using existing hand coded methods. Motivated by recent advanc
es in reversible logic synthesis, we synthesize arithmetic circuits using classical design automation flows and tools. The combination of classical and reversible logic synthesis enables the automatic design of large components in reversible logic starting from well-known hardware description languages such as Verilog. As a prototype example for our approach we automatically generate high quality networks for the reciprocal $1/x$, which is necessary for quantum linear systems algorithms.
In this paper, we presented the design and development of a new integrated device for measuring heart rate using fingertip to improve estimating the heart rate. As heart related diseases are increasing day by day, the need for an accurate and afforda
ble heart rate measuring device or heart monitor is essential to ensure quality of health. However, most heart rate measuring tools and environments are expensive and do not follow ergonomics. Our proposed Heart Rate Measuring (HRM) device is economical and user friendly and uses optical technology to detect the flow of blood through index finger. Three phases are used to detect pulses on the fingertip that include pulse detection, signal extraction, and pulse amplification. Qualitative and quantitative performance evaluation of the device on real signals shows accuracy in heart rate estimation, even under intense of physical activity. We compared the performance of HRM device with Electrocardiogram reports and manual pulse measurement of heartbeat of 90 human subjects of different ages. The results showed that the error rate of the device is negligible.
Graph Neural Network (GNN) is a variant of Deep Neural Networks (DNNs) operating on graphs. However, GNNs are more complex compared to traditional DNNs as they simultaneously exhibit features of both DNN and graph applications. As a result, architect
ures specifically optimized for either DNNs or graph applications are not suited for GNN training. In this work, we propose a 3D heterogeneous manycore architecture for on-chip GNN training to address this problem. The proposed architecture, ReGraphX, involves heterogeneous ReRAM crossbars to fulfill the disparate requirements of both DNN and graph computations simultaneously. The ReRAM-based architecture is complemented with a multicast-enabled 3D NoC to improve the overall achievable performance. We demonstrate that ReGraphX outperforms conventional GPUs by up to 3.5X (on an average 3X) in terms of execution time, while reducing energy consumption by as much as 11X.
Photons have been identified early on as a very good candidate for quantum technologies applications, as carriers of quantum information, either by polarization encoding, time encoding or spatial encoding. Quantum cryptography, quantum communications
, quantum networks and quantum computing are some of the applications targeted by the so called quantum photonics. Nevertheless, it was also clear at an early stage that bulk optics for handling quantum states of light would not be the best option for these technologies. More recently, single photons, entangled photons and quantum light in general have been coupled to integrated approaches coming from classical optics in order to meet the requirements of scalability, reliability and efficiency for quantum technologies. In this article, we describe our recent advances using elongated optical nano-fibers. We also present our latest results on nanocrystals made of perovskites and discuss some of their quantum properties. Finally, we will discuss the general steps necessary in order to couple these nanoemitters efficiently with our photonic platform, based on tapered optical nanofibers.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
