arXiv subjects

Marcelo Daniel Berejuck

Publications and source records attributed to Marcelo Daniel Berejuck.

3 recordsLinked to original sources

arXiv2016

An overview about Networks-on-Chip with multicast suppor

Modern System-on-Chip (SoC) platforms typically consist of multiple processors and a communication interconnect between them. Network-on-Chip (NoC) arises as a solution to interconnect these systems, which provides a scalable, reusable, and an efficient interconnect. For these SoC platforms, multicast communication is significantly used for parallel applications. Cache coherency in distributed sharedmemory,clock synchronization, replication, or barrier synchronization are examples of these requests. This paper presents an overview of research on NoC with support for multicast communication and delineates the major issues addressed so far by the scientific community in this investigation area.

cs.AR↗

arXiv2015

Network-on-Chip with load balancing based on interleave of flits technique

This paper presents the evaluation of a Network-on-Chip (NoC) that offers load balancing for Systems-on-Chip (SoCs) dedicated for multimedia applications that require high traffic of variable bitrate communication. The NoC is based on a technique that allows the interleaving of flits from diferente flows in the same communication channel, and keep the load balancing without a centralized control in the network. For this purpose, all flits in the network received extra bits, such that every flit carries routing information. The routers use this extra information to perform arbitration and schedule the flits to the corresponding output ports. Analytic comparisons and experimental data show that the approach adopted in the network keeps average latency lower for variable bitrate flows than a network based on resource reservation when both networks are working over 80% of offered load.

cs.AR↗

arXiv2014

Evaluation of silicon consumption for a connectionless Network-on-Chip

We present the design and evaluation of a predictable Network-on-Chip (NoC) to interconnect processing units running multimedia applications with variable-bit-rate. The design is based on a connectionless strategy in which flits from different communication flows are interleaved in the same communication channel between routers. Each flit carries routing information used by routers to perform arbitration and scheduling of the corresponding output communication channel. Analytic comparisons show that our approach keeps average latency lower than a network based on resource reservation, when both networks are working over 80% of offered load. We also evaluate the proposed NoC on FPGA and ASIC technologies to understand the trade-off due to our approach, in terms of silicon consumption.

cs.AR↗