A new switch chip for IBM RS/6000 SP systems

Stunkel, Craig B.; Herring, Jay; Abali, Bülent; Sivaram, R.

doi:10.1145/331532.331548

Cited by 21 publications

(13 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The strict conditions enforced by CMP environments impose serious limitations for the direct adoption of some off-chip solutions for multicast support. Mechanisms based on the utilization of large centralized buffers [49] or high radix switches [9] are not suitable under CMP area and power conditions. However, ignoring multicast issues does not make the multidestination message problem disappear.…”

Section: On-chip Multicast Proposalsmentioning

confidence: 99%

Adaptive-Tree Multicast: Efficient Multidestination Support for CMP Communication Substrate

Abad

Puente

Menezo

et al. 2012

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

Multidestination communications are a highly necessary capability for many coherence protocols in order to minimize onchip hit latency. Although CMPs share this necessity, up to now few suitable proposals have been developed. The combination of resource scarcity and the common idea that multicast support requires a substantial amount of extra resources is responsible for this situation. In this work, we propose a new approach suitable for on-chip networks capable of managing multidestination traffic via hardware in an efficient way with negligible complexity. We introduce a novel multicast routing mechanism, able to circumvent many of the limitations of conventional multicast schemes. Adaptive-tree multicasting is able to maintain correctness for multiflit multicast messages without routing restrictions, while also coupling correctness and performance in a natural way. Replication restrictions not only guarantee the presence of enough resources to avoid deadlock, but also dynamically adapt tree shape to network conditions, routing multicast messages through noncongested paths. The performance results, using a state-of-the-art full system simulation framework, show that it improves the average full system performance of a CMP by 20 percent and network ED2P by 15 percent, when compared to a state-of-the-art router with conventional multicast support and similar implementation cost.

show abstract

Section: On-chip Multicast Proposalsmentioning

confidence: 99%

Adaptive-Tree Multicast: Efficient Multidestination Support for CMP Communication Substrate

Abad

Puente

Menezo

et al. 2012

IEEE Trans. Parallel Distrib. Syst.

View full text Add to dashboard Cite

show abstract

“…We rely on the Network Time Protocol, NTP (Mills 1995), which is satisfactory in most scenarios, but other solutions are possible. For example, Wu et al (2000) take advantage of the hardware globally synchronized clock of switch adapters (Stunkel et al 1999), while other implementations rely on specific hardware infrastructure (e.g., Blue Gene (Milano et al 2006)). …”

Section: Dalle and Mancinimentioning

confidence: 99%

Traces generation to simulate large-scale distributed applications

Dalle

Mancini

2011

Proceedings of the 2011 Winter Simulation Conference (WSC)

View full text Add to dashboard Cite

In order to study the performance of scheduling algorithms, simulators of parallel and distributed applications need accurate models of the application's behavior during execution. For this purpose, traces of low-level events collected during the actual execution of real applications are needed. Collecting such traces is a difficult task due to the timing, to the interference of instrumentation code, and to the storage and transfer of the collected data. To address this problem we propose a comprehensive software architecture, which instruments the application's executables, gather hierarchically the traces, and post-process them in order to feed simulation models. We designed it to be scalable, modular and extensible.

show abstract

“…Some of them [16], [17] rely on building virtual circuits, thus being latency sensitive at the circuit establishment. For off-chip multicast routers, please refer to [18], [19] (for multistage networks and/or high-radix switches). These techniques are not suitable for on-chip networks.…”

Section: Related Workmentioning

confidence: 99%

Efficient unicast and multicast support for CMPs

Rodrigo

Flich

Duato

et al. 2008

2008 41st IEEE/ACM International Symposium on Microarchitecture

View full text Add to dashboard Cite

Beyond a certain number of cores, multi-core processing chips will require a network-on-chip (NoC) to interconnect the cores and overcome the limitations of a bus. NoCs must be carefully designed to meet constraints like power consumption, area, and ultra low latencies. Although 2D meshes with DOR (Dimension-Order-Routing) meet these constraints, the need for partitioning (e.g. virtual machines, coherency domains) and traffic isolation may prevent the use of DOR routing. Also, core heterogeneity and manufacturing and run-time faults may lead to partially irregular topologies. Routing in these topologies is complex, and previously proposed solutions required routing tables, which drastically increase power consumption, area, and latency. The exception is LBDR (Logic-Based Distributed Routing), a flexible routing method for irregular topologies that removes the need for using routing tables (both at end-nodes and switches), thus achieving large savings in chip area and power consumption. But LBDR lacks support for multicast and broadcast, which are required to efficiently support cache coherence protocols both for single and multiple coherence domains.In this paper we propose bLBDR, an efficient multicast and broadcast mechanism built on top of LBDR. bLBDR performs multicast operations using a logic-based broadcast within a domain (a region with bounds). This allows us to isolate the traffic into different domains, thus enabling the concept of virtualization at the NoC level. Also, bLBDR extends the concept of routing regions in LBDR by providing a mechanism that allows the flexible definition of multiple domains, sets of network resources.bLBDR fulfills all the practical requirements, including not only low latency and power and area efficiency, but also support for virtualization, partitionability, fault-tolerance, traffic isolation and broadcast across the entire network as well as constrained to coherency domains or regions. All this is achieved by a small and power efficient routing logic (7x area savings and 17x power reduction when compared to a routing table in an 8 × 8 mesh network).

show abstract

A new switch chip for IBM RS/6000 SP systems

Cited by 21 publications

References 19 publications

Adaptive-Tree Multicast: Efficient Multidestination Support for CMP Communication Substrate

Adaptive-Tree Multicast: Efficient Multidestination Support for CMP Communication Substrate

Traces generation to simulate large-scale distributed applications

Efficient unicast and multicast support for CMPs

Contact Info

Product

Resources

About