3D NoC Research Articles

Power consumption of 3D networks-on-chips: Modeling and optimization

Designing power-efficient Networks-on-Chips (NoCs) for 3D ICs has emerged as a promising solution for complex mobile and portable applications. The total power consumption of a 3D NoC design depends on the allocation of the Intellectual properties (IPs) to the different network routers and the number of Through Silicon Vias (TSVs) used in the design. In this paper, we introduce a new analytical model for the power consumption of 3D NoCs. This new model relies on graph-theoretic concepts and incorporates static and dynamic power in order to present a more accurate evaluation of 3D NoC power consumption. The proposed model utilizes Dijkstra’s algorithm to find shortest path routing. It also reflects the impact of using TSVs in 3D ICs. Using the proposed model, we develop a new methodology to select the 3D NoC topology and find the best IP-mapping. The proposed methodology utilizes a bio-inspired optimization technique. We compare particle swarm optimization (PSO) to genetic algorithms (GAs) in order to find the best 3D mesh network mapping that achieves minimum power consumption. The presented methodology is validated through two case studies to address symmetric and asymmetric multicore applications.

Exploration of Temperature Constraints for Thermal-Aware Mapping of 3D Networks-on-Chip

This paper proposes three ILP-based static thermal-aware mapping algorithms for 3D Networks-on-Chip (NoC). With these three mapping algorithms, the authors explore the thermal constraints and their effects on temperature and performance. Through complexity analysis, the authors show that the first algorithm, an optimal one, is not suitable for 3D NoCs. Therefore, the authors develop two approximation algorithms and analyze their algorithmic complexities to show their proficiency. According to simulation results, mapping algorithms that employ direct thermal calculation to minimize the temperature reduce the peak temperature by up to 24% and 22%, for the benchmarks that have the highest communication rate and largest number of tasks, respectively. This peak temperature reduction comes at the price of a higher power-delay product. The authors’ exploration shows that considering power balancing early in the mapping algorithm does not affect chip temperature. Moreover, the authors show that considering explicit performance constraints in the thermal mapping has no major effect on performance.

Partial Virtual Channel Sharing: A Generic Methodology to Enhance Resource Management and Fault Tolerance in Networks-on-Chip

We present a novel Partial Virtual channel Sharing (PVS) NoC architecture which reduces the impact of faults on performance and also tolerates faults within the routing logic. Without PVS, failure of a component impairs the fault-free connected components, which leads to considerable performance degradation. Improving resource utilization is key in enhancing or sustaining performance with minimal overhead when faults or overload occurs. In the proposed architecture, autonomic virtual-channel buffer sharing is implemented with a novel algorithm that determines the sharing of buffers among a set of ports. The runtime allocation of the buffers depends on incoming load and fault occurrence. In addition, we propose an efficient technique for maintaining the accessibility of a processing element (PE) to the network even if its router is faulty. Our techniques can be used in any NoC topology and for both, 2D and 3D NoCs. The synthesis results for an integrated video conference application demonstrate 22 % reduction in average packet latency compared to state-of-the-art virtual channel (VC) based NoC architecture. Extensive quantitative simulation has been carried out with synthetic benchmarks. Simulation results reveal that the PVS architecture improves the performance significantly in presence of faults, compared to other VC-based NoC architectures.

Efficient routing techniques in heterogeneous 3D Networks-on-Chip

Abstract Three-dimensional Networks-on-Chips (3D NoCs) have recently been proposed to address the on-chip communication demands of future highly dense 3D multi-core systems. Homogeneous 3D NoC topologies have many Through Silicon Vias (TSVs) which have a costly and complex manufacturing process. Also, 3D routers use more memory and are more power hungry than conventional 2D routers. Alternatively, heterogeneous 3D NoCs combine both the area and performance benefits of 2D and 3D static router architectures by using a limited number of TSVs. To improve the performance of heterogeneous 3D NoCs, we propose an adaptive router architecture which balances the traffic in such NoCs. Particularly, experimental results show that our proposed architecture significantly improves the performance up to 75% by replacing 2D static routers with adaptive 2D routers in heterogeneous 3D NoCs, while keeping the maximum clock frequency, power and energy consumption of the adaptive router nearly at the same level as the static router.

HETEROGENEOUS 3D NETWORK-ON-CHIP ARCHITECTURES: AREA AND POWER AWARE DESIGN TECHNIQUES

Three-dimensional Network-on-Chip (3D NoC) architectures have gained a lot of popularity to solve the on-chip communication delays of next generation System-on-Chip (SoC) systems. However, the vertical interconnects of 3D NoC are expensive and complex to manufacture. Also, 3D router architecture consumes more power and occupies more area per chip floorplan compared to a 2D router. Hence, more efficient architectures should be designed. In this paper, we propose area efficient and low power 3D heterogeneous NoC architectures, which combines both the power and performance benefits of 2D routers and 3D NoC-bus hybrid router architectures in 3D NoC architectures. Experimental results show a negligible penalty (less than 5%) in average packet latency of the proposed heterogeneous 3D NoC architectures compared to typical homogeneous 3D NoCs, while the heterogeneity provides power and area efficiency of up to 61% and 19.7%, respectively.

Deadlock-free generic routing algorithms for 3-dimensional Networks-on-Chip with reduced vertical link density topologies

3-Dimensional Networks-on-Chip (3D NoC) have emerged as the promising solution for scalability, power consumption and performance demands of next generation Systems-on-Chip (SoCs) interconnect. Due to the cost in terms of thermal, yield, chip area and design complexity, minimizing the number of Through-Silicon-Via (TSVs) in 3D ICs has become on the most important design issues. In this paper, we will present several stable, simple and deadlock-free generic routing algorithms for 3D NoCs with different reduced vertical link density topologies, which can maintain the 3D NoCs performance and save the system cost (TSV number, chip area, system power, etc.). The experimental results have been extracted from our cycle-accurate GSNOC simulator and have shown that our routing algorithms can maintain the system performance up to reducing 50% of TSVs number in comparison to the 100% TSVs number with ZXY routing algorithm configuration.

New heuristic algorithms for low-energy mapping and routing in 3D NoC

Three Dimensional Network on Chip 3D NoC, which reduces the average number of hops traversed by a packet, can achieve better performance than the traditional 2D NoC. However, when routers deliver packets in 3D NoC, more energy consumption is needed. High-energy consumption and small packaging density will cause excessive heat, which increases vulnerability of the system in performance and reliability. In this paper, we present a low-energy consumption mapping algorithm based on the symmetry of the architecture and construct a deadlock-free routing algorithm using mapping result information. Our proposed algorithms can reduce the total energy consumption of communication and achieve a good system performance under the bandwidth constraints. To evaluate the efficacy of the algorithms, we perform experiments on several benchmarks and compare the proposed algorithms with other existing algorithms. Experimental results show that, for complex benchmarks, our proposed algorithms get better results than others.

Shuttle: A Novel Topology Model for 3D NoC

Shuttle: A Novel Topology Model for 3D NoC

Developing a power-efficient and low-cost 3D NoC using smart GALS-based vertical channels

Shorter global interconnects enable 3D NoC structures to offer higher performance, improved packaging density, and lower interconnect power consumption to CMPs and SoCs compared to their 2D counterparts. However, substantial challenges such as high peak temperatures, power densities and area footprints of vertical interconnects in each layer cannot be ignored. In this paper, a power and area efficient 3D NoC architecture based on power-aware Bidirectional Bisynchronous Vertical Channels (BBVC) is proposed as a solution to mitigate these challenges. Instead of using a pair of unidirectional channels for inter-layer communication, utilizing a dynamically self-configurable BBVC enables a system to benefit from low-latency nature of the vertical interconnects. In addition, based on the GALS implementation approach of the proposed channels, a forecasting-based dynamic frequency scaling technique for reducing the power consumption of the inter-layer communication is introduced. Simulation results show that the proposed architecture can reduce up to 47% through-silicon via (TSV) area footprint and up to 18% NoC power consumption with a slight performance degradation compared to a typical Symmetric 3D NoC.

Optimized 3D Network-on-Chip Design Using Simulated Allocation

Three-dimensional (3D) silicon integration technologies have provided new opportunities for Network-on-Chip (NoC) architecture design in Systems-on-Chip (SoCs). In this article, we consider the application-specific NoC architecture design problem in a 3D environment. We present an efficient floorplan-aware 3D NoC synthesis algorithm based on simulated allocation (SAL), a stochastic method for traffic flow routing, and accurate power and delay models for NoC components. We demonstrate that this method finds greatly improved solutions compared to a baseline algorithm reflecting prior work. To evaluate the SAL method, we compare its performance with the widely used simulated annealing (SA) method and show that SAL is much faster than SA for this application, while providing solutions of very similar quality. We then extend the approach from a single-path routing to a multipath routing scheme and explore the trade-off between power consumption and runtime for these two schemes. Finally, we study the impact of various factors on the network performance in 3D NoCs, including the TSV count and the number of 3D tiers. Our studies show that link power and delay can be significantly improved when moving from a 2D to a 3D implementation, but the improvement flattens out as the number of 3D tiers goes beyond a certain point.

An asynchronous hierarchical router for networks‐on‐chip‐based three‐dimensional multi‐processor system‐on‐chip

SUMMARYThree‐dimensional networks‐on‐chip (3D NoC) are rising as a good approach to well managed complex interconnections in 3D multi‐processor system‐on‐chip (MPSoC). This paper introduces a new router in order to enhance throughput and latency compared to classic 3D mesh NoC. The proposed router is hierarchical as it is composed of two completely decoupled modules: one for inter‐layer communication and one for intra‐layer communication. It is fully implemented in asynchronous logic to allow low latency transfer.Synthesis and extrapolation results show that the hierarchical router is competitive with the classic 3D mesh in terms of area and power. Throughput and latency evaluation is performed using a SystemC‐TLM NoC simulator. Simulations' results show that the proposed hierarchical router can outperform the 3D mesh by more than 25% in terms of throughput and latency in the case of transpose traffic. Copyright © 2012 John Wiley & Sons, Ltd.

Adaptive Data Compression on 3D Network-on-Chips

The three-dimensional Network-on-Chip (3D NoC) is an emerging research topic exploring the network architecture of 3D ICs that stack several wafers or dies. As such topics being extensively studied, it is found negative impacts of 3D NoC's vertical interconnects are raising concerns considering their footprint sizes and routability degradation. In our evaluation, we found such vertical bandwidth limitation can dramatically degrade system performance by up to 2.3×. Since such limitations come from physical design constraints, to mitigate performance degradation, we have no other choice but to reduce the amount of communication data on-chip, especially for those data moving vertically. In this paper, therefore, we carry out a study of data compression on 3D NoC architectures with a comprehensive set of scientific workloads. Firstly, we propose an adaptive data compression scheme for 3D NoCs, taking account of the vertical bandwidth limitation and data compressibility. Secondly, we evaluate our proposal on a 3D NoC platform and we observe that the compressibility based adaptive compression is very useful against incompressible data while the location-based adaptive compression is more effective with more layers for the 3D NoC. Thirdly, we find that in a bandwidth limited situation like a CMP with 3D NoCs having multiple connected layers, adaptive data compression with location-based control or with both compressibility and location based control is very promising if the number of layers grows.

Design and management of high-performance, reliable and thermal-aware 3D networks-on-chip

Increasing the number of cores over a 2D plane is not efficient in hyper-core systems due to long interconnects. As a viable alternative over the 2D planar chip, 3D integrated technology offers greater device integration and shorter interlayer interconnects. 3D networks-on-chip (NoC)–bus hybrid mesh architecture, which is a hybrid between packet-switched network and a bus, was proposed to take advantage of the intrinsic attributes of 3D ICs. Even though this architecture was proposed as a feasible one to provide both performance and area benefits, the challenges of combining both media (NoC and bus) to design 3D NoCs have not been addressed. In this study, an efficient 3D NoC architecture is proposed to optimise performance, power consumption and reliability of 3D NoC–bus hybrid mesh system. The mechanism benefits from a congestion-aware and bus failure tolerant routing algorithm called ‘AdaptiveZ’ for vertical communication. In addition, the authors propose thermal-aware scheduling strategy in order to mitigate temperature by herding most of the switching activity closer to the heatsink. To estimate the efficiency of the proposed architecture, the system has been simulated using uniform, hotspot 10% and negative exponential distribution traffic patterns. In addition, a videoconference encoder has been used as a real application for system analysis. Compared with a typical stacked mesh 3D NoC, our extensive simulations demonstrate significant power, performance and peak temperature improvements.

A Stackable LTE Chip for Cost-effective 3D Systems

To address the problem of prohibitive cost of advanced fabrication technologies, one solution consists in reusing masks to address a wide range of ICs. This could be achieved by a modular circuit that can be stacked to build TSV-based 3D systems with processing performance adapted to several applications. This paper focuses on 4G wireless telecom applications. We propose a basic circuit that meets the SISO (Single Input Single Output) transmission mode. By stacking multiple instances of this same circuit, it will be possible to address several MIMO (Multiple Input Multiple Output) modes. The proposed circuit is composed of several processing units interconnected by a 3D NoC and controlled by a host processor. Compared to a 2D reference platform, the proposed circuit keeps at least the same performance and power consumption in the context of 4G telecom applications, while reducing total cost. More generally, our cost analysis shows that 3D integration efficiency depends on the size of the circuit and the stacking option (die-to-die, die-to-wafer and interposer-based stacking).

Power and area optimisation in heterogeneous 3D networks-on-chip architectures

Three dimensional Network-on-Chip (3D NoC) architectures have evolved with a lot of interest to address the on-chip communication delays of modern SoC systems. However, the vertical interconnections between layers is more power and area hungry compared to 2D interconnections. In this paper we propose area efficient and low power heterogeneous NoC architectures, which combines both the power and performance benefits of 2D routers and 3D NoC-bus hybrid router architectures in 3D mesh topologies. Experimental results show a negligible penalty of up to 5% in average packet latency of 3D homogeneous NoC with bus hybrid routers. The heterogeneity however provides superiority of up to 67% and 19.7% in power and area efficiency of the NoC resources, respectively.

CSL: Configurable Fault Tolerant Serial Links for Inter-die Communication in 3D Systems

Three dimensional (3D) integrated systems become a reality nowadays, as Thru-Silicon-Via (TSV) technologies mature. 3D integration promises significant performance and energy efficiency improvements by reducing the signal travel distances and integrating more capabilities on a single chip. High integration costs, thermal management, and poor reliability and yield are major challenges of TSV based 3D chips. High structural and parametric fault rates due to manufacturing defects makes it difficult to achieve high interconnect yield using only spare-based repair solutions. In this paper we address the TSV yield issue by implementing the inter-die links of 3D chips as Configurable fault-tolerant Serial Links (CSLs). When there are not enough available functional TSVs, faults are tolerated by performing data serialization. CSLs help reduce chip costs by improving the TSV yield with very few or no spares at all. For 3D Networks-on-Chip (3D NoCs) we show that the CSL yield improvement comes with moderate area overheads (~12---26%) and small performance penalties (less than 5% average latency overhead).

Exploring DRAM Last Level Cache for 3D Network-on-Chip Architecture

In this paper, we implement and analyze different Network-on-Chip (NoC) designs with Static Random Access Memory (SRAM) Last Level Cache (LLC) and Dynamic Random Access Memory (DRAM) LLC. Different 2D/3D NoCs with SRAM/DRAM are modeled based on state-of-the-art chips. The impact of integrating DRAM cache into a NoC platform is discussed. We explore the advantages and disadvantages of DRAM cache for NoC in terms of access latency, cache size, area and power consumption. We present benchmark results using a cycle accurate full system simulator based on realistic workloads. Experiments show that under different workloads, the average cache hit latencies in two DRAM based designs are increased by 12.53% (2D) and reduced by 27.97% (3D) respectively compared with the SRAM. It is also shown that the power consumption is a tradeoff consideration in improving the cache hit latency of DRAM LLC. Overall, the power consumption of 3D NoC design with DRAM LLC has reduced 25.78% compared with the SRAM design. Our analysis and experimental results provide a guideline to design efficient 3D NoCs with DRAM LLC.

3D NOC for many-core processors

With an increasing number of processors forming many-core chip multiprocessors (CMP), there exists a need for easily scalable, high-performance and low-power intra-chip communication infrastructure for emerging systems. In CMPs with hundreds of processing elements, 3D integration can be utilized to shorten long wires forming communication links. In this paper, we propose a Clos network-on-chip (CNOC) in conjunction with 3D integration as a viable network topology for many core CMPs. The primary benefit of 3D CNOC is scalability and a clear upper bound on power dissipation. We present the architectural and physical design of 3D CNOC and compare its performance with several other topologies. Comparisons are made among several topologies (fat tree, flattened butterfly, mesh and Clos) showing the power consumption of a 3D CNOC increases only minimally as the network size is scaled from 64 to 512 nodes relative to the other topologies. Furthermore, in a 512-node system, 3D CNOC consumes about 15% less average power than any other topology. We also compare 3D partitioning strategies for these topologies and discuss their effect on wire delay and the number of through-silicon vias.

A study of 3D Network-on-Chip design for data parallel H.264 coding

In this paper, we implement, analyze and compare different Network-on-Chip (NoC) architectures aiming at higher efficiencies for MPEG-4/H.264 coding. Two-dimensional (2D) and three-dimensional (3D) NoCs based on Non-Uniform Cache Access (NUCA) are analyzed. We present results using a full system simulator with realistic workloads. Experiments show the average network latencies in two 3D NoCs are reduced by 28% and 34% respectively, comparing with 2D design. It is also shown that heat dissipation is a trade-off in improving performance of 3D chips. Our analysis and experiment results provide a guideline to design efficient 3D NoCs for data parallel H.264 coding applications.

Adaptive inter-layer message routing in 3D networks-on-chip

Existing routing algorithms for 3D deal with regular mesh/torus 3D topologies. Today 3D NoCs are quite irregular, especially those with heterogeneous layers. In this paper, we present a routing algorithm targeting 3D networks-on-chip (NoCs) with incomplete sets of vertical links between adjacent layers. The routing algorithm tolerates multiple link and node failures, in the case of absence of NoC partitioning. In addition, it deals with congestion. The routing algorithm for 3D NoCs preserves the deadlock-free propriety of the chosen 2D routing algorithms. It is also scalable and supports a local reconfiguration that complements the reconfiguration of the 2D routing algorithms in case of failures of nodes or links. The algorithm incurs a small overhead in terms of exchanged messages for reconfiguration and does not introduce significant additional complexity in the routers. Theoretical analysis of the 3D routing algorithm is provided and validated by simulations for different traffic loads and failure rates.