A Hyperconcentrator Switch for Routing Bit-Serial Messages

نویسندگان

  • Thomas H. Cormen
  • Charles E. Leiserson
چکیده

In highly parallel message routing networks, it is sometimes desirable to concentrate relatively few messages on many wires onto fewer wires. We have designed a VLSI chip for this purpose which is capable of concentrating bit-serial messages quickly. This hyperconcentrator switch has a regular layout using ratioed nMOS and takes advantage of the relatively fast performance of large fan-in NOR gates in this technology. A signal incurs exactly 2 lg n gate delays through the switch, where n is the number of inputs to the circuit. The architecture generalizes to domino CMOS and BiCMOS as well. The hyperconcentrator design has applications other than message concentration. It can be used in a superconcentrator switch to provide fault tolerance when interconnections are nonfunctional. Multiple hyperconcentrator switches can be conngured into a large partial concentrator switch. The hyperconcentrator design can also be used in a processor datapath to allow various manipulations on bits, including barrel shifting, APL-style compression and expansion, and bit interleaving. + = = log typeset in Roman _ appears in two diierent sizes within the text ^ A i line over A does not extend out over subscript O italic uppercase \oh" o italic lowercase \oh" uppercase Greek letter theta lowercase Greek letter phi uppercase Greek letter omega lowercase Greek letter alpha lowercase Greek letter beta lowercase Greek letter mu lowercase Greek letter epsilon

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Design Principles for Practical Self-Routing Nonblocking Switching Networks with O(N log N) Bit-Complexity

Principles for designing practical self-routing nonblocking N × N circuit-switched connection networks with optimal q(N ◊ log N) hardware at the bit-level of complexity are described. The overall principles behind the architecture can be described as “Expand-Route-Contract.” A self-routing nonblocking network with w-bit wide datapaths can be achieved by expanding the datapaths to w + z independ...

متن کامل

Fast Optical Circuit Switch for Intra-Datacenter Networking

This paper presents a fast and large-scale optical circuitswitch architecture for intra-datacenter applications that uses a combination of space switches and wavelength-routing switches are utilized. A 1,440 × 1,440 optical switch is designed with a fast-tunable laser, 8 × 8 deliveryand-coupling switch, and a 180 × 180 wavelength-routing switch. We test the bit-error-ratio characteristics of al...

متن کامل

Design of Arrayed Waveguide Grating based Optical Switch for High Speed Optical Networks

This paper demonstrates the design of an Arrayed Waveguide Gratings (AWG) based optical switch. In the design both physical and network layer analysis is performed. The physical layer power and noise analysis is done to obtain Bit Error Rate (BER). This has been found that at the higher bit rates, BER is not affected with number of buffer modules. Network layer analysis is done to obtain perfor...

متن کامل

HiPER: A Compact Narrow Channel Router with Hop-by-Hop Error Correction

Multiprocessor architectures demand efficient interprocessor communication to maximize system utilization and performance. To meet future demands, these interconnects must communicate at significantly higher speeds while operating more efficiently to meet system size, weight, power, and energy requirements. As high-performance parallel computing architectures make their way into portable system...

متن کامل

Design and Implementation of a High Speed Systolic Serial Multiplier and Squarer for Long Unsigned Integer Using VHDL

A systolic serial multiplier for unsigned numbers is presented which operates without zero words inserted between successive data words, outputs the full product and has only one clock cycle latency. &#10The multiplier is based on a modified serial/parallel scheme with two adjacent multiplier cells. Systolic concept is a well-known means of intensive computational task through replication of fu...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1986