Sharif Digital Repository

In recent years, GPUs are becoming an ideal candidate for processing a variety of high performance applications. By relying on thousands concurrent threads in applications and the computational power of large numbers of computing units; GPGPUs have provided high performance and throughput. To achieve the potential computational power of GPGPUs in broader kinds of applications, we need to apply some modifications in their architecture. In the baseline architecture, the maximum part of chip area is devoted to SIMT cores which their communication is handled through an interconnection network and a slow off-chip memory. Recent research shows that out of many types of miss events the last level... 

Integrated silicon photonic networks have attracted a lot of attention in the recent decade due to their potential for low-power and high-bandwidth communications. However, despite high bandwidth and low-loss data communication capability, optical NoCs are susceptible to on-chip temperature variations. In these promising networks, packets’ erroneous routing due to thermally-induced resonant wavelength shift of microring resonators are common temporary faults unless heat control mechanism is adopted. In other words, thermal drifts may paralyze wavelength-based operation of these networks. On the other hand, employing a heat control mechanism in an ONoC necessitates developing thermal fault... 

In recent years, flash-based Solid State Drives (SSDs), because of their lower power consumption, higher throughput, and resistance against physical damages compared to Hard Disk Drives (HDDs) have confronted ever increasing usage in data center, cloud applications, and enterprise servers. Recently, advantages of using interconnection networks between SSD controller and NAND Flash chips for transferring data and commands have been shown. Interconnection network intrinsically provides many advantages such as maintaining the signal integrity at high frequencies, pipelining support, sharing the communication resources, eliminating communication bottlenecks, and reducing power consumption. The... 

By scaling the technology node, leakage power and process variations emerge as the two important factors to design a chip. Static power becomes more important when the number of portable devices which spend most of the time in the idle mode is increasing.Process variations lessen performance, reliability and lead to more leakage power. To mitigate these limitations multiple devices have been proposed to displace Bulk MOSFET.Among these devices we can name FinFET and CNTFET transistors. FinFET transistors due to their superior gate control in compare to Bulk MOSFETs transistor have shown lesser short channel effects, more scalability, more I_on to I_off ratio and lesser process variations.... 

The advancement of technology in the semiconductor industry and the resulting increase in the number of transistors on a chip has led to an increase in the number of processing cores an increase in the number of processing cores in a system on chip (SoC). A surge in the number of processing cores, makes their communication more and more noteworthy. This communication is established through the network on chip (NoC). One of the main challenges in NoC design is power management, as it constitutes a high percentage of the overall power consumption of the chip. One of the most power-hungry components of NoC is the router. According to our observation, some of the components of the routers are... 

The fast development of semiconductor industry has moved the design methodology to SoC (System on Chip) design. Due to the increasing number of processing elements, In SoC, buses become the bottleneck of the system and lead to non-efficient designs. NoC (Network onChip) is an efficient solution that eliminates bus bottleneck and it had been introduced as a suitable substructure for interconnecting processing elements. The NoCs were originally built based on Interconnection Networks.They have been proposed as an efficient, scalable, modular and reliable solution to provide on chip communication in any large SoC design. The trend of market to mobile digital systems and battery-powered devices,... 

In the upward trend of advancing technologies in chips manufacturing, utilizing Network on Chip (NOC) solutions is a sensible approach towards overcoming challenges in System on Chip (SOC). The most common form of NOC is the Wired NOC. The continuous physical size reduction of electronic circuits has led to bandwidth deficiency as well as increased temperature in various parts of these circuits. The vast advancement in chips manufacturing industry has made it possible to embed and adapt telecommunication equipment into chips, giving rise to Wireless NOC (WNOC) manufacturing. However, wireless communication increases fault rate; thereby, the system becomes more vulnerable against transient... 

With progress in integrated circuits technology, on chip systems have become operational, and after that, onchip network are as solutions to improve onchip connections and also its scalability. With improving technology, the number of cores on chips can be more, that it causes increasing importance of produced problems by parallel links. Serial links are one of the methods to decrease these problems. Serial links have some advantages in compare with parallel links in some aspects like: clock pulse skew, cross talk, area cost, difficulties in wiring and synchronizing clock pulse signals. But any way, problems such as high operational frequency and complicated serializer and deserializer... 

Recent advances in VLSI technology have led to integrate a few billion transistors on a chip. Systems on Chip provide solutions to the design problems of these systems. As technology scales down to deep sub-micron dimensions, the delay and power consumption of global interconnects become the major bottleneck in SoC design. Networks on Chip (NoCs) have been proposed as an efficient, scalable, modular and reliable solution to provide on chip communication in large VLSI design. The market trend to mobile digital systems and battery-powered devices add power as a new dimension to VLSI design space in addition to speed and area. Interconnect wires dissipate a significant fraction of power... 

Kardar-Parisi-Zhang (KPZ) equation was first proposed as a model to explain surface growth. This equation is very similar to Edwards-Wilkinson (EW) equation that is used to study scaling phenomena in non-equilibrium systems and phase transition. Although EW’s universality classes have been known well, it still remains a problem for KPZ. In the present thesis, in addition to a general review on surface growth models and a study on properties of rough surfaces, we study the physics of the KPZ model and the other related physical models. Also, using numerical results (like SLE method), renormalization group results and simulation, we study the dynamic and roughness exponents (α, z), and the... 

Recently, a new tool in the study of two-dimensional continuous phase transition was provided by Schramm-Loewner evolution. The main part of SLE is a conformal map which relates growth process of a two-dimensional simple curve to one-dimensional motion on the real axis (so-called Loewner driving function). Time evolution of this map and Loewner driving function is connected via the Loewner differential equation. It turns out that for a certain class of stochastic and conformally invariant curves in two dimensions, the driving function shows Brownian motion in one dimension. Strength point of SLE comes from this fact that all the geometrical properties of such curves is described through a... 

Brown and Henneaux showed that asymptotic symmetries of asymptotically form a conformal group in two dimensions [1]. Also they could derive classical central charge of theory. Fourteen years later, Maldacena, conjectured that this Holographic correspondence could be true for a specific theory a simplified chromodynamics in the boundary of ), this holographic theory attracted physicist communitee's attention. Many physicists tried to make this conjecture more precise. It is worth to say that, no example of holographic correspondence has been completely proven, till now, Because of the difficulty of the calculation. However these days we consider Madacena conjectrure in any arbitrary... 

XY Model due to topological defects (or vortex) has topological phase transition. According Kosterlitz-Thouless (KT) theory, phase transition is from low-temperature bounded vortices to high-temperature free vortices. XY model is appropriate choice for description of superfluidity in 2d thin films of . KT theory predicts universal jump in mass density of 2d superfluid in phase transition point. It is confirmed experimentally by Bishop and Reppy. All critical behavior of XY model is described with 2d coulomb gas, vortices are topological charges of the gas. KT predict variance of topological charge should obey of the “surface law vs perimeter law”, similar to behavior of Wilson loop in ... 

Deep learning, as a subdivision of machine learning, attempts to model high-level concepts by using a deep graph, consisting of several layers of linear and nonlinear transformations. Implementing these algorithms on hardware is a big challenge.¬This project offers a system in which various hardware methodologies can be used to implement deep learning algorithms side by side. The overall structure of the system consists of high-level programming interfaces for implementation and expression of machine learning algorithms by the user, which will be available as libraries in a high-level programming language such as Python, Ruby, and Julia. These interfaces allow the user to evaluate their... 

We propose a model for friction between two rough surfaces based on extreme value statistics (EVS). Different models for single-asperity contact, including adhesive and elasto-plastic contacts, were combined with EVS. The Hertzian model for contacts and Gumbel distribution for summit heights show the closest conformity with Amonton’s law. The range over which Gumbel distribution mimics Amonton’s law is wider than that of the Greenwood–Williamson (GW) model. In comparison with other EVS distribution, Gumbel distribution seems the proper choice for summit‘ s height. Interestingly, here again, elasto-plastic contact and Gumbel distribution for summits achieve the best conformity with Amontons... 

Nowadays by increasing the number of processing cores in system-on-chip, using networks-on-chip, as an optimized interconnection foundation for transferring data between processing cores is inevitable .Based on this, the necessity of designing and implementing an optimized structure for testing network-on-chip, considering various overheads such as power consumption, latency, bandwidth and area, becomes an important issue in designing network-on-chip. The purpose of this project is to design an optimized structure for testing routers and connecting links in network, which considers power consumption overhead, latency and area overhead on one hand, and fault coverage on the other hand.... 

In this thesis, a hardware is designed and implemented for testing the perfoemance of MIMO communication systems in LTE standard using SCM channel model. This hardware can be used for measuring the BER of 2x2 wireless systems. This hardware is the first channel emulator, with hardware implementation which is using SCM channel model and implementation of a similar one has not been reported.In addition to the implementation of the mentioned channel emulator, a new approach is used for implementing a Gaussian variate generator (GVG) which is implemented on both FPGA and ASIC and shows better characteristics in comparison with the works done in the past. ASIC implementation of this part is done... 

Schramm Loewner evolution (SLE) is a one-parameter family of random simple curves in the complex plane introduced by Schramm in 1999 which is believed to describe the scaling limit of a variety of domain interfaces at criticality. This thesis is concerned with statistical properties of watersheds dividing drainage basins. The fractal dimension of this model is 1.22 which is consistent with the known fractal dimension for several important models such as Invasion percolation and minimum spanning trees (MST). We present numerical evidences that in the scaling limit this model are SLE curves with =1.73, being the only known physical example of an
SLE with <2. This lies outside the... 

In the last two decades, Convolutional Neural Networks (CNN) have shown significant capabilities in artificial intelligence. These networks are able to provide comprehensive conclusions about the overall behavior a system by analyzing the relationship between the components of that system; Clearly, these networks have been successful in performing categorization tasks. However, there are no coherent theories as to why they work, and how to optimize them. On the other hand, according to recent research on the relationship between deep networks (in computer science) and Renormalization Group (in physics), convolutional networks seem to use a method similar to the Density Matrix Renormalization...