Providing throughput guarantees in mixed-criticality networks-on-chip

Tobuschat, Sebastian; Ernst, Rolf

doi:10.1109/socc.2017.8226064

Cited by 3 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Accordingly, adaptive routing algorithms are able to use alternative paths instead of waiting for busy channels. In adaptive routing algorithms, most selection functions are based on monitoring the buffer fill level in its neighboring nodes, such as Contention-look-ahead on-chip routing scheme [16], Dynamic Adaptive Deterministic (DyAD) switching [17], Neighbors-on-Path (NoP) selection [18], Local Congestion Avoidance [7], Mixed-criticality NoC [19], and Destination Intensity and Congestion-Aware (DICA) [9], all of which allow for each router to monitor the buffers of its nearest or two-hop neighboring routers in order to detect potential congestion earlier.…”

Section: Congestion Control Without Resource Reservationmentioning

confidence: 99%

“…Conventional congestion control schemes depend on some forms of buffer fill level information to dynamically select routing paths [7,9,[16][17][18][19]. Differently, we applied the proposed concept of buffer fluidity level in [11].…”

Section: Buffer Fluidity Conceptmentioning

confidence: 99%

“…For congestion control, adaptive routing schemes [14,15], can be used to forward packets around the contentious regions. In NoCs, most congestion control schemes select profitable routing paths by monitoring some forms of buffer fill level [7,9,10,[16][17][18][19][20]. NoC link-layer (node-to-node) flow control schemes [6,8,[20][21][22], are developed to prevent buffers overfill between neighboring nodes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Network-Cognitive Traffic Control: A Fluidity-Aware On-Chip Communication

Tsai

Chen

et al. 2020

Electronics

View full text Add to dashboard Cite

A novel network-on-chip (NoC) integrated congestion control and flow control scheme, called Network-Cognitive Traffic Control (NCogn.TC), is proposed. This scheme is cognizant of the fluidity levels in on-chip router buffers and it uses this measurement to prioritize the forwarding of flits in the buffers. This preferential forwarding policy is based on the observation that flits with higher levels of fluidity are likely to arrive at their destinations faster, because they may require fewer routing steps. By giving higher priority to forward flits in high-fluidity buffers, scarce buffer resources may be freed-up sooner in order to relieve on-going traffic congestion. In this work, a buffer cognition monitor is developed to rapidly estimate the buffer fluidity level. An integrated congestion control and flow control algorithm is proposed based on the estimated buffer fluidity level. Tested with both synthetic traffic patterns as well as industry benchmark traffic patterns, significant performance enhancement has been observed when the proposed Network-Cognitive Traffic Control is compared against conventional traffic control algorithms that only monitor the buffer fill level.

show abstract