Performance of an optical switch based on 3-D MEMS crossconnect

We demonstrate a fully functional microelectromechanical system-based optical crossconnect switch with advanced close-loop feedback control architecture for the mirrors. The system architecture was designed for handling multiple connections in parallel. The switch features rapid restoration of multiple connections at the switching element level opening up the path to synchronous optical network-like performance for mesh networks, and power equalization capability for each port.     

Design and implementation of wavelength-flexible network nodes

This paper analytically and experimentally examines node architectures for wavelength-routing networks, with emphasis on the degree of wavelength conversion provided. Wavelength flexibility simplifies network management and increases network capacity but requires large cross-connects and deployment of wavelength converters (WCs). A simple probabilistic model is used to upper-bound the number of WCs required at a network node, under dynamic traffic load. When provisioned in a shareable pool, with a fixed number of wavelength channels per fiber, the number of WCs required remains low as overall network capacity is scaled up. Motivated by this analysis, experiments demonstrate the feasibility of implementing wavelength-flexible network nodes using large microelectromechanical (MEMS)-based cross-connects and all-optical WCs. In one design, WCs were attached directly to cross-connect output ports, and in another, they were attached in a loop-back fashion to allow sharing. Error-free transmission at 10 Gb/s was demonstrated in both cases.     

Towards a First Vertical Prototyping of an Extremely Fine-Grained Parallel Programming Approach

Explicit multithreading (XMT) is a parallel programming approach for exploiting on-chip parallelism. XMT introduces a computational framework with (1) a simple programming style that relies on fine-grained PRAM-style algorithms; (2) hardware support for low-overhead parallel threads, scalable load balancing, and efficient synchronization. The missing link between the algorithmic-programming level and the architecture level is provided by the first prototype XMT compiler. This paper also takes this new opportunity to evaluate the overall effectiveness of the interaction between the programming model and the hardware, and enhance its performance where needed, incorporating new optimizations into the XMT compiler. We present a wide range of applications, which written in XMT obtain significant speedups relative to the best serial programs. We show that XMT is especially useful for more advanced applications with dynamic, irregular access patterns, where for regular computations we demonstrate performance gains that scale up to much higher levels than have been demonstrated before for on-chip systems.     

1100 /spl times/ 1100 port MEMS-based optical crossconnect with 4-dB maximum loss

We present a microelectromechanical systems-based beam steering optical crossconnect switch core with port count exceeding 1100, featuring mean fiber-to-fiber insertion loss of 2.1 dB and maximum insertion loss of 4.0 dB across all possible connections. The challenge of efficient measurement and optimization of all possible connections was met by an automated testing facility. The resulting connections feature optical loss stability of better than 0.2 dB over days, without any feedback control under normal laboratory conditions.     

ACOTES Project: Advanced Compiler Technologies for Embedded Streaming

Streaming applications are built of data-driven, computational components, consuming and producing unbounded data streams. Streaming oriented systems have become dominant in a wide range of domains, including embedded applications and DSPs. However, programming efficiently for streaming architectures is a challenging task, having to carefully partition the computation and map it to processes in a way that best matches the underlying streaming architecture, taking into account the distributed resources (memory, processing, real-time requirements) and communication overheads (processing and delay). These challenges have led to a number of suggested solutions, whose goal is to improve the programmer??s productivity in developing applications that process massive streams of data on programmable, parallel embedded architectures. StreamIt is one such example. Another more recent approach is that developed by the ACOTES project (Advanced Compiler Technologies for Embedded Streaming). The ACOTES approach for streaming applications consists of compiler-assisted mapping of streaming tasks to highly parallel systems in order to maximize cost-effectiveness, both in terms of energy and in terms of design effort. The analysis and transformation techniques automate large parts of the partitioning and mapping process, based on the properties of the application domain, on the quantitative information about the target systems, and on programmer directives. This paper presents the outcomes of the ACOTES project, a 3-year collaborative work of industrial (NXP, ST, IBM, Silicon Hive, NOKIA) and academic (UPC, INRIA, MINES ParisTech) partners, and advocates the use of Advanced Compiler Technologies that we developed to support Embedded Streaming.     

256/spl times/256 port optical cross-connect subsystem

This paper describes the subsystem design and performance of a 256/spl times/256-port micromechanical beam-steering optical cross-connect with 1.33-dB average loss, which can provide 238/spl times/238-port cross-connect with a maximum loss of less than 2dB. This paper describes the design chosen and analyzes the tolerance ranges required to produce low loss and simulate the expected loss distribution of the fabric. The method of establishing and testing the connections is also described. The simulation is compared with the measured system, and the expected and measured static and dynamic crosstalk are compared.