{"title":"An Efficient Self-Routing and Non-Blocking Interconnection Network on Chip","authors":"Tripti Jain, K. Schneider, Ankesh Jain","doi":"10.1145/3139540.3139546","DOIUrl":"https://doi.org/10.1145/3139540.3139546","url":null,"abstract":"In this paper, we present a new self-routing and non-blocking uni-cast interconnection network based on binary radix sorting that is more efficient than comparable other interconnection networks. To substantiate this claim, we first derive the asymptotic complexities of the size and depth of our network's circuit netlist. Moreover, we have implemented our network as well as other related radix-based sorting networks using 65nm CMOS chip technology. We compare the maximal frequency, the required chip area, and the power consumption of these circuits. Our evaluation shows that our network is best among the considered radix-based networks regardless whether the maximal frequency, the chip area or the power consumption is considered.","PeriodicalId":410968,"journal":{"name":"Proceedings of the 10th International Workshop on Network on Chip Architectures","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116642411","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Lightweight Emulation of Virtual Channels using Swaps","authors":"Mayank Parasar, T. Krishna","doi":"10.1145/3139540.3139541","DOIUrl":"https://doi.org/10.1145/3139540.3139541","url":null,"abstract":"Virtual Channels (VCs) are a fundamental design feature across networks, both on-chip and off-chip. They provide two key benefits - deadlock avoidance and head-of-line (HoL) blocking mitigation. However, VCs increase the router critical path, and add significant area and power overheads compared to simple wormhole routers. This is especially challenging in the era of energy-constrained many-core chips. The number of VCs required for deadlock avoidance is unavoidable, but those required for mitigating HoL depend on runtime factors such as the distribution and size of single and multi-flit packets, and their intended destinations. In some cases more VCs are beneficial, while in others they may actually harm performance, as we demonstrate. In this work, we provide a low-cost microarchitectural technique to emulate the HoL mitigation behavior of VCs inside routers, without requiring the expensive data path or control path (vc state and vc allocation) for VCs. We augment wormhole routers with the ability to do an in-place swap of blocked packets to the head of the queue. Our design (SwapNoC) can operate at low area and power specs like wormhole designs, without incurring their HoL challenges.","PeriodicalId":410968,"journal":{"name":"Proceedings of the 10th International Workshop on Network on Chip Architectures","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124340516","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jesus Gardea, Yuho Jin, Abdel-Hameed A. Badawy, J. Cook
{"title":"Performance Evaluation of Mesh-based 3D NoCs","authors":"Jesus Gardea, Yuho Jin, Abdel-Hameed A. Badawy, J. Cook","doi":"10.1145/3139540.3139545","DOIUrl":"https://doi.org/10.1145/3139540.3139545","url":null,"abstract":"The advances on 3D circuit integration have reignited the idea of processing-in-memory (PIM). In this paper, we evaluate 3D mesh-based NoC design for 3D-PIM systems. We study the stacked mesh (S-Mesh) which is a mesh-bus hybrid architecture for 3D NoCs that connects vertically stacked 2D meshes through buses. Previous S-Mesh studies have not addressed the problems and modifications needed at the building blocks of the network. We explain in details the internal structure of the S-Mesh, as well as, the problems and solutions of connecting 2D meshes using vertical buses. Also, we evaluate the performance of 3D NoC designs via two traffic patterns, one of which is a novel traffic pattern that better measures 3D-PIM systems performance. Our results show 15% performance improvement for the S-Mesh for zero-load packet latency while having a negligible decrease in saturation throughput.","PeriodicalId":410968,"journal":{"name":"Proceedings of the 10th International Workshop on Network on Chip Architectures","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123611198","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Thermal/Traffic Mutual-Coupling Co-simulation Platform for 3D Network-on-Chip (NoC) Designs","authors":"A. Wu, K. Chen, Chih-Hao Chao","doi":"10.1145/3139540.3139549","DOIUrl":"https://doi.org/10.1145/3139540.3139549","url":null,"abstract":"Three-dimensional Network-on-Chip (3D NoC), the combination of NoC and 3D IC technology, can achieve lower latency, lower power consumption, and higher data bandwidth for efficient intra/inter-chip data exchange of chip multiprocessors (CMPs). Due to die stacking in 3D IC, both heat conduction path and power density increase. Therefore, thermal issue becomes the major design challenges in the research field of three-dimensional (3D) IC. To facilitate such research, an accurate and non-proprietary environment for simulating the traffic and temperature behavior in 3D NoC is necessary. In this tutorial, one traffic-thermal mutual-coupling co-simulation platform for 3D NoC will be presented. The introduced platform can be used for 3D thermal-aware design, 3D dynamic thermal management technology, and other related researches in the future.","PeriodicalId":410968,"journal":{"name":"Proceedings of the 10th International Workshop on Network on Chip Architectures","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115921258","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Improving Scalability in Thermally Resilient Hybrid Photonic-Electronic NoCs","authors":"Keyvan Ramezanpour, Xingye Liu, P. Ampadu","doi":"10.1145/3139540.3146943","DOIUrl":"https://doi.org/10.1145/3139540.3146943","url":null,"abstract":"Hybrid photonic-electronic networks-on-chip (HPENoCs) harness the strengths of both photonic and electronic links to meet the stringent demands of bandwidth, power, and latency of many-core systems. Microring resonators (MRRs), fundamental components in on-chip photonic networks, are highly sensitive to thermal variations, which may lead to erroneous optical transmission. Previously, we proposed a thermal-aware fault-tolerant routing technique (TAFT) to address this problem. In this paper, we examine and evaluate the scalability of TAFT as the NoC size grows. Organizing the NoC into different size clusters is a crucial part of TAFT scalability. Given the same number of cores, different cluster sizes can have up to 45% latency difference. The latency, throughput and power consumption are all dependent on cluster size, under similar traffic patterns. Simulation results also show that as the traffic pattern degrades, revising cluster size can yield up to 56% latency improvement.","PeriodicalId":410968,"journal":{"name":"Proceedings of the 10th International Workshop on Network on Chip Architectures","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116914466","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Feed-Forward Routing for the Wormhole Switching Network-on-Chip of the Kalray MPPA2 Processor","authors":"B. Dinechin, Amaury Graillat","doi":"10.1145/3139540.3139542","DOIUrl":"https://doi.org/10.1145/3139540.3139542","url":null,"abstract":"The Kalray MPPA2-256 Bostan processor network-on-chip (NoC) implements wormhole switching without virtual channels and with source routing. As shown in earlier work, this NoC can be configured for guaranteed services by solving a set of linear inequalities based on deterministic network calculus (DNC). However, DNC assumes that a unique route is assigned to each flow and requires that the set of flows be feed-forward. We show that ensuring the feed-forward flows property is equivalent to deterministic deadlock-free routing on a wormhole switching NoC. While routing each flow between its given endpoints, minimal path diversity occurs and the choice of a particular unique path for each flow has an impact on the NoC bandwidth exploitation. We cast this choice as a max-min fairness with unsplittable paths problem, whose instances are solved by enumeration and by an efficient heuristic.","PeriodicalId":410968,"journal":{"name":"Proceedings of the 10th International Workshop on Network on Chip Architectures","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128096479","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Mourad Dridi, M. Lallali, S. Rubini, Frank Singhoff, J. Diguet
{"title":"Modeling and Validation of a Mixed-Criticality NoC Router Using the IF Language","authors":"Mourad Dridi, M. Lallali, S. Rubini, Frank Singhoff, J. Diguet","doi":"10.1145/3139540.3139543","DOIUrl":"https://doi.org/10.1145/3139540.3139543","url":null,"abstract":"In Mixed-Criticality Systems (MCS), high-critical real-time and low-critical real-time applications share the same hardware platform. Today MCS must also be implementable on NoC-based architectures. Those applications exchange messages with different timing requirements through the same network. Sharing resources between flows in a NoC can lead to unpredictable latencies and subsequently complicate the implementation of MCS in many-core architectures. A solution is that NoC routers provide guarantees for high-critical communications with a minimum impact on performances for low-critical communications. We propose a new router called DAS, which exhibits such properties to support MCS applications. Moreover we introduce the first formal verification of the MCS properties of a NoC-router. We detail a formal specification of the DAS router, with the IF language, in order to verify its ability to support MCS applications. We also describe the validation approach of this specification based on those properties and using the IF toolset.","PeriodicalId":410968,"journal":{"name":"Proceedings of the 10th International Workshop on Network on Chip Architectures","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131009265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A. Ganguly, N. Mansoor, Md Shahriar Shamim, M. Ahmed, Rounak Singh Narde, Abhishek Vashist, J. Venkataraman
{"title":"Intra-chip Wireless Interconnect: The Road Ahead","authors":"A. Ganguly, N. Mansoor, Md Shahriar Shamim, M. Ahmed, Rounak Singh Narde, Abhishek Vashist, J. Venkataraman","doi":"10.1145/3139540.3139548","DOIUrl":"https://doi.org/10.1145/3139540.3139548","url":null,"abstract":"On-chip wireless interconnects have been proposed to provide energy-efficient data communication paths between cores in System-on-Chips (SoCs) in the multi and many-core era. Networks-on-Chips (NoCs) when interconnecting hundreds of cores consume large amounts of energy and suffer from high and unpredictable latency due to congestion at intermediate routers. Wireless interconnects alleviate this problem by providing direct single-hop links between distant cores in the chip. While various wireless NoC (WiNoC) architectures have been proposed and evaluated in the in the past decade this technology is not yet adopted in the mainstream industry. In order to benefit from the past decade of research in WiNoC designs a few important myths regarding wireless interconnects need to be dispelled while propelling the research to tangible technology transfer. In this paper several vectors that define the design space of WiNoCs will be identified while highlighting the state-of-the-art accomplishments in those directions by leading research groups. This will be followed by identifying the future direction that needs to be pursued to make WiNoCs a mainstream reality. At the end a few potential high-impact use-cases for wireless interconnects are discussed.","PeriodicalId":410968,"journal":{"name":"Proceedings of the 10th International Workshop on Network on Chip Architectures","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132261002","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Game-based Congestion-aware Adaptive Routing (GCAR) for Proactive Thermal-aware 3D Network-on-Chip Systems","authors":"K. Chen","doi":"10.1145/3139540.3139547","DOIUrl":"https://doi.org/10.1145/3139540.3139547","url":null,"abstract":"Because of the stacking dies and heterogeneous thermal conduction, the three dimensional Network-on-Chip (3D NoC) suffers from more serious thermal problem. The thermal issue limits the performance gain of 3D integration and results in lower reliability of the system. To ensure the thermal safety, the Proactive Dynamic Thermal Management (PDTM) is proven as an efficient way to mitigate the performance impact during the temperature control period. The PDTM involves the different clock frequency assignment to each NoC node based on the information of temperature prediction results. Therefore, the PDTM can early control the system temperature before the system temperature achieves the thermal emergency, which helps to mitigate the performance impact. However, due to the different clock frequency assignment, the heterogeneous packet processing speed will lead to unbalanced traffic distribution and significant performance degradation. Although many congestion-aware adaptive routing algorithms can detour the packets away from the traffic congested regions, these approaches only adopt the information of buffer congestion status to deliver the packets, which makes the packet transmission become static and results in large thermal stress in the traffic non-congested routing regions. To increase the routing path diversity during the temperature control period, we apply the Game Theory to propose a Game-based Congestion-aware Adaptive Routing (GCAR) in this paper. The GCAR will distribute the packet delivery based on the Nash Equilibrium property in Game Theory. The experimental results show that the proposed GCAR will improve 35% -- 66% system performance compared with the previous related works.","PeriodicalId":410968,"journal":{"name":"Proceedings of the 10th International Workshop on Network on Chip Architectures","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132882111","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Sameh El-Ashry, Hala Ibrahim, M. A. Ibrahem, Mostafa Khamis, A. Shalaby, Mohamed Abdelsalam, M. El-Kharashi
{"title":"On Error Injection for NoC Platforms: A UVM-based Practical Case Study","authors":"Sameh El-Ashry, Hala Ibrahim, M. A. Ibrahem, Mostafa Khamis, A. Shalaby, Mohamed Abdelsalam, M. El-Kharashi","doi":"10.1145/3139540.3139544","DOIUrl":"https://doi.org/10.1145/3139540.3139544","url":null,"abstract":"Error injection has become critically important for testing the reliability of the hardware of any system. Measuring how a design under test reacts to different error injection methodologies is very essential for verification engineers to design dependable Universal Verification Methodology (UVM) scoreboards for error-detection purposes. The main target of this paper is to decide on the feasibility and compatibility of some error injection techniques when used with Networks-on-Chip (NoC) platforms. We target a UVM-based error injection and detection environment with its reusable components. Proposed techniques, introducing both positive and negative test scenarios, are applied to two example NoC components: a base router, which is a simple case study to prove proposed schemes and a configurable router, which is a complex open-source case study that provides the ability of changing the router's architecture with the change of some parameters and applied algorithms. The main novelty of our work is to integrate a full UVM environment with the various approaches of error injection and detection using reusable, generic UVM environment and components for NoC while inspecting network response according to error type and injection methodology.","PeriodicalId":410968,"journal":{"name":"Proceedings of the 10th International Workshop on Network on Chip Architectures","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-10-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115577151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}