Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 30
Encontrada(s) 1 página(s)

UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

System-level exploration of in-package wireless communication for multi-chiplet platforms

  • Medina Morillas, Rafael
  • Kein, Joshua
  • Ansaloni, Giovanni
  • Zapater Sancho, Marina
  • Abadal Cavallé, Sergi|||0000-0003-0941-0260
  • Alarcón Cot, Eduardo José|||0000-0001-7663-7153
  • Atienza Alonso, David
Multi-Chiplet architectures are being increasingly adopted to support the design of very large systems in a single package, facilitating the integration of heterogeneous components and improving manufacturing yield. However, chiplet-based solutions have to cope with limited inter-chiplet routing resources, which complicate the design of the data interconnect and the power delivery network. Emerging in-package wireless technology is a promising strategy to address these challenges, as it allows to implement flexible chiplet interconnects while freeing package resources for power supply connections. To assess the capabilities of such an approach and its impact from a full-system perspective, herein we present an exploration of the performance of in-package wireless communication, based on dedicated extensions to the gem5-X simulator. We consider different Medium Access Control (MAC) protocols, as well as applications with different runtime profiles, showcasing that current in-package wireless solutions are competitive with wired chiplet interconnects. Our results show how in-package wireless solutions can outperform wired alternatives when running artificial intelligence workloads, achieving up to a 2.64× speed-up when running deep neural networks (DNNs) on a chiplet-based system with 16 cores distributed in four clusters., This work has been partially supported by the EC H2020 WiPLASH project (GA No. 863337) and the EC H2020 FVLLMONTI project (GA No. 101016776), Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Integrated graphene patch antenna for communications at THz frequencies

  • de Santana, Elana Pereira
  • Wigger, Anna K.
  • Wang, Zhenxing
  • Wang, Kun Ta
  • Lemme, Max
  • Abadal Cavallé, Sergi|||0000-0003-0941-0260
  • Haring Bolívar, Peter
Graphene is an attractive material for communications in the THz range due to its ability to support surface plasmon polaritons. This enables a graphene antenna to be smaller in size than its metallic counterpart. In addition, the possibility to control the graphene conductivity during operation by an applied bias leads to the tunability of the resonant frequency of graphene antennas. Graphene-based antennas integrated into transceivers working at THz frequencies may lead to faster and more efficient devices. In this work, we design and simulate a graphene patch antenna that can be integrated into transceivers by through-substrate vias. The tuning of the resonant frequency is also studied by simulations., This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement N° 863337., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

One protocol to rule them all: Wireless network-on-chip using deep reinforcement learning

  • Jog, Suraj
  • Liu, Zikun
  • Franques, Antonio
  • Fernando, Vimuth
  • Abadal Cavallé, Sergi|||0000-0003-0941-0260
  • Torrellas, Josep
  • Hassanieh, Haitham
Wireless Network-on-Chip (NoC) has emerged as a promising solution to scale chip multi-core processors to hundreds and thousands of cores. The broadcast nature of a wireless network allows it to significantly reduce the latency and overhead of many-to-many multicast and broadcast communication on NoC processors. Unfortunately, the traffic patterns on wireless NoCs tend to be very dynamic and can change drastically across different cores, different time intervals and different applications. New medium access protocols that can learn and adapt to the highly dynamic traffic in wireless NoCs are needed to ensure low latency and efficient network utilization. Towards this goal, we present NeuMAC, a unified approach that combines networking, architecture and deep learning to generate highly adaptive medium access protocols for wireless NoC architectures. NeuMAC leverages a deep reinforcement learning framework to create new policies that can learn the structure, correlations, and statistics of the traffic patterns and adapt quickly to optimize performance. Our results show that NeuMAC can quickly adapt to NoC traffic to provide significant gains in terms of latency, throughput, and overall execution time. In particular, for applications with highly dynamic traffic patterns, NeuMAC can speed up the execution time by 1.37× -3.74× as compared to 6 baselines., The work is funded in part by NSF Award 1750725., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Tunable plasmonic graphene antenna array for communications at THz frequencies

  • de Santana, Elana Pereira
  • Stock, Daniel
  • Wang, Zhenxing
  • Wang, Kun Ta
  • Abadal Cavallé, Sergi|||0000-0003-0941-0260
  • Lemme, Max
  • Bolívar, Peter Haring
The existence of plasmonic waves at a graphene/dielectric interface at THz frequencies enables the use of graphene as the radiative element of antennas working at this frequency range, but with a smaller lateral dimension compared to a standard metallic antenna. Due to the low carrier mobility in large-area graphene, result of its manufacturing process, the emitted radiation of graphene antennas is still smaller than its metallic counterpart. In this work, we show that the low emission of a graphene antenna can be compensated by antenna arrays. The proposed 1x4 graphene antenna array presents a far-field radiated gain of 9.3 dBi with a resonance frequency at 269 GHz. The resonating frequency of the graphene antenna array can also be tuned by an electrostatic bias., This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement N° 863337., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Collective communication patterns using time-reversal terahertz links at the chip scale

  • Rodríguez Galán, Fátima Yolanda
  • Ama Bandara, Paveena
  • de Santana, Elana Pereira
  • Bolívar, Peter Haring
  • Alarcón Cot, Eduardo José|||0000-0001-7663-7153
  • Abadal Cavallé, Sergi|||0000-0003-0941-0260
Wireless communications in the terahertz band have been recently proposed as complement to conventional wired interconnects within computing packages. Such environments are typically highly reverberant, hence showing long channel impulse responses and severely limiting the achievable rates. Fortunately, this communications scenario is static and can be pre-characterized, which opens the door to techniques such as time reversal. Time reversal acts a spatial matched filter and has a spatiotemporal focusing effect, which allows not only to increase the achievable symbol rates, but also to create multiple spatial channels. In this paper, the multi-user capability of time reversal is explored in the context of wireless communications in the terahertz band within a computing package. Full-wave simulations are carried out to validate the approach, whereas modulation streams are simulated to evaluate the error rate as a function of the transmitted power, symbol rate, and number of simultaneous transmissions., Authors acknowledge support from the European Union’s Horizon 2020 research and innovation program, grant agreement 863337 (WiPLASH), the European Research Council (ERC) under grant agreement 101042080 (WINC) as well as the European Innovation Council (EIC) PATHFINDER scheme, grant agreement No 101099697 (QUADRATURE)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Dataflow-architecture co-design for 2.5D DNN accelerators using wireless network-on-package

  • Guirado Liñan, Robert
  • Kwon, Hyoukjun
  • Abadal Cavallé, Sergi|||0000-0003-0941-0260
  • Alarcón Cot, Eduardo José|||0000-0001-7663-7153
  • Krishna, Tushar
Deep neural network (DNN) models continue to grow in size and complexity, demanding higher computational power to enable real-time inference. To efficiently deliver such computational demands, hardware accelerators are being developed and deployed across scales. This naturally requires an efficient scale-out mechanism for increasing compute density as required by the application. 2.5D integration over interposer has emerged as a promising solution, but as we show in this work, the limited interposer bandwidth and multiple hops in the Network-on-Package (NoP) can diminish the benefits of the approach. To cope with this challenge, we propose WIENNA, a wireless NoP-based 2.5D DNN accelerator. In WIENNA, the wireless NoP connects an array of DNN accelerator chiplets to the global buffer chiplet, providing high-bandwidth multicasting capabilities. Here, we also identify the dataflow style that most efficienty exploits the wireless NoP's high-bandwidth multicasting capability on each layer. With modest area and power overheads, WIENNA achieves 2.2X-5.1X higher throughput and 38.2% lower energy than an interposer-based NoP design., This work was supported by the European Commission under grant 863337 and NSF under Award OAC-1909900., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Multi-channel medium access control protocols for wireless networks within computing packages

  • Ollé Ferrayuoli, Bernat
  • Talarn Bell-lloch, Pau
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
  • Lemic, Filip
  • Alarcón Cot, Eduardo José|||0000-0001-7663-7153
  • Abadal Cavallé, Sergi|||0000-0003-0941-0260
Wireless communications at the chip scale emerge as a interesting complement to traditional wire-based approaches thanks to their low latency, inherent broadcast nature, and capacity to bypass pin constraints. However, as current trends push towards massive and bandwidth-hungry processor architectures, there is a need for wireless chip-scale networks that exploit and share as many channels as possible. In this context, this work addresses the issue of channel sharing by exploring the design space of multi-channel Medium Access Control (MAC) protocols for chip-scale networks. Distinct channel assignment strategies for both random access and token passing are presented and evaluated under realistic traffic patterns. It is shown that, even with the improvements enabled by the multiple channels, both protocols maintain their intrinsic advantages and disadvantages., This work is supported by the European Commission under H2020 grant WiPLASH (GA 863337) and HE grant WINC (GA 101042080)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Characterizing the communication requirements of GNN accelerators: A model-based approach

  • Guirado Liñan, Robert
  • Jain, Akshay|||0000-0002-6986-2720
  • Abadal Cavallé, Sergi|||0000-0003-0941-0260
  • Alarcón Cot, Eduardo José|||0000-0001-7663-7153
Relational data present in real world graph representations demands for tools capable to study it accurately. In this regard Graph Neural Network (GNN) is a powerful tool, wherein various models for it have also been developed over the past decade. Recently, there has been a significant push towards creating accelerators that speed up the inference and training process of GNNs. These accelerators, however, do not delve into the impact of their dataflows on the overall data movement and, hence, on the communication requirements. In this paper, we formulate analytical models that capture the amount of data movement in the most recent GNN accelerator frameworks. Specifically, the proposed models capture the dataflows and hardware setup of these accelerator designs and expose their scalability characteristics for a set of hardware, GNN model and input graph parameters. Additionally, the proposed approach provides means for the comparative analysis of the vastly different GNN accelerators., The authors gratefully acknowledge support from the Spanish Ministry of Science and Innovation (MICINN) under grant EIN2019-103461 and from the European Comission under grant H2020-863337-WIPLASH., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Architecting more than Moore: wireless plasticity for massive heterogeneous computer architectures (WiPLASH)

  • Klein, Joshua
  • Levisse, Alexandre
  • Ansaloni, Giovanni
  • Atienza Alonso, David
  • Zapater Sancho, Marina
  • Dazzi, Martino
  • Karunaratne, Geethan
  • Boybat, Irem
  • Sebastian, Abu
  • Rossi, Davide
  • Jain, Akshay|||0000-0002-6986-2720
  • Guirado Liñan, Robert
  • Taghvaee, Hamidreza|||0000-0001-8732-6086
  • Abadal Cavallé, Sergi|||0000-0003-0941-0260
This paper presents the research directions pursued by the WiPLASH European project, pioneering on-chip wireless communications as a disruptive enabler towards next-generation computing systems for artificial intelligence (AI). We illustrate the holistic approach driving our research efforts, which encompass expertises and abstraction levels ranging from physical design of embedded graphene antennas to system-level evaluation of wirelessly-communicating heterogeneous systems., This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 863337 (WiPLASH)., Peer Reviewed, Article signat per 22 autors/es: - Joshua Klein, Alexandre Levisse, Giovanni Ansaloni, David Atienza (EPFL, Lausanne, Switzerland) - Marina Zapater (HEIG-VD/HES-SO Yverdon-les-Bains, Switzerland / EPFL, Lausanne, Switzerland) - Martino Dazzi, Geethan Karunaratne, Irem Boybat, Abu Sebastian (IBM Research Europe, Zurich, Switzerland) - Davide Rossi, Francesco Conti (Università di Bologna, Bologna, Italy) - Elana Pereira de Santana, Peter Haring Bolívar (University of Siegen, Siegen, Germany) - Mohamed Saeed, Renato Negra (RWTH, Aachen, Germany) - Zhenxing Wang, Kun-Ta Wang (AMO GmbH, Aachen, Germany) - Max C. Lemme (RWTH, Aachen, Germany / AMO GmbH, Aachen, Germany) - Akshay Jain, Robert Guirado, Hamidreza Taghvaee, Sergi Abadal (Universitat Politècnica de Catalunya, Barcelona, Spain)
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Towards spatial multiplexing in wireless networks within computing packages

  • Rodríguez Galán, Fátima Yolanda
  • de Santana, Elana Pereira
  • Bolívar, Peter Haring
  • Abadal Cavallé, Sergi|||0000-0003-0941-0260
  • Alarcón Cot, Eduardo José|||0000-0001-7663-7153
Wireless Networks-on-Chip (WNoCs) are regarded as a disruptive alternative to conventional interconnection networks at the chip scale, yet limited by the relatively low aggregate bandwidth of such wireless networks. Hence, any method to increase the amount of concurrent channels in this scenario is of high value. In this direction, and since WNoC implies close integration of multiple antennas on a chip anyway, in this paper we present a feasibility study of compact monopole antenna arrays in a flip-chip environment at millimeter-wave and sub-terahertz frequencies. By means of a full-wave solver, we evaluate the feasibility to create, at will, concentrations of field in different spots of the chip. This way, we set the steps towards spatial multiplexing that enables concurrent multicast communications and also increases the aggregate bandwidth of the wireless network. Our results at 60 GHz show two clearly separable parallel channels that radiate simultaneously from two opposite corners of the chip, achieving a Signal-to-Interference Ratio (SIR) of around 40 dB, which proves that the channels are independent of each other even in such an enclosed environment. Further, we see potential to expand our approach to three or more concurrent channels, and to frequencies beyond 100 GHz., Authors acknowledge support from the European Union’s Horizon 2020 research and innovation program, grant agreement 863337., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Scale up your In-Memory Accelerator: leveraging wireless-on-chip communication for AIMC-based CNN inference

  • Bruschi, Nazareno
  • Tagliavini, Giuseppe
  • Conti, Francesco
  • Abadal Cavallé, Sergi|||0000-0003-0941-0260
  • Cabellos Aparicio, Alberto|||0000-0001-9329-7584
  • Alarcón Cot, Eduardo José|||0000-0001-7663-7153
  • Karunaratne, Geethan
  • Boybat, Irem
  • Benini, Luca
  • Rossi, Davide
Analog In-Memory Computing (AIMC) is emerging as a disruptive paradigm for heterogeneous computing, potentially delivering orders of magnitude better peak performance and efficiency over traditional digital signal processing architectures on Matrix-Vector multiplication. However, to sustain this throughput in real-world applications, AIMC tiles must be supplied with data at very high bandwidth and low latency; this poses an unprecedented pressure on the on-chip communication infrastructure, which becomes the system's performance and efficiency bottleneck. In this context, the performance and plasticity of emerging on-chip wireless communication paradigms provide the required breakthrough to up-scale on-chip communication in large AIMC devices. This work presents a many-tile AIMC architecture with inter-tile wireless communication that integrates multiple heterogeneous computing clusters, embedding a mix of parallel RISC-V cores and AIMC tiles. We perform an extensive design space exploration of the proposed architecture and discuss the benefits of exploiting emerging on-chip communication technologies such as wireless transceivers in the millimeter-wave and terahertz bands., This work was supported by the WiPLASH project (g.a. 863337), founded from the European Union’s Horizon 2020 research and innovation program., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

WiDir: A Wireless-Enabled Directory cache coherence protocol

  • Franques, Antonio
  • Kokolis, Apostolos
  • Abadal Cavallé, Sergi|||0000-0003-0941-0260
  • Fernando, Vimuth
  • Misailovic, Sasa
  • Torrellas, Josep
As the core count in shared-memory manycores keeps increasing, it is becoming increasingly harder to design cache-coherence protocols that deliver high performance without an inordinate increase in complexity and cost. In particular, sharing patterns where a group of cores frequently reads and writes a shared variable are hard to support efficiently. Hence, programmers end up tuning their applications to avoid these patterns, hurting the programmability of shared memory. To address this problem, this paper uses the recently-proposed on-chip wireless network technology to augment a conventional invalidation-based directory cache coherence protocol. We call the resulting protocol WiDir. WiDir seamlessly transitions between wired and wireless coherence transactions for a given line based on the access patterns in a programmer-transparent manner. In this paper, we describe the protocol transitions in detail. Further, an evaluation using SPLASH and PARSEC applications shows that WiDir substantially reduces the memory stall time of applications. As a result, for 64-core runs, WiDir reduces the execution time of applications by an average of 22% compared to a conventional directory protocol. Moreover, WiDir is more scalable. These benefits are obtained with a very modest power cost., This work was funded in part by NSF Grant No. CCF1629431 and by EU’s Horizon 2020 Research and Innovation Programme Grant No. 863337 (WiPLASH)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Millimeter wave wireless network on chip using deep reinforcement learning

  • Jog, Suraj
  • Liu, Zikun
  • Franques, Antonio
  • Fernando, Vimuth
  • Hassanieh, Haitham
  • Abadal Cavallé, Sergi|||0000-0003-0941-0260
  • Torrellas, Josep
Wireless Network-on-Chip (NoC) has emerged as a promising solution to scale chip multi-core processors to hundreds of cores. However, traditional medium access protocols fall short here since the traffic patterns on wireless NoCs tend to be very dynamic and can change drastically across different cores, different time intervals and different applications. In this work, we present NeuMAC, a unified approach that combines networking, architecture and AI to generate highly adaptive medium access protocols that can learn and optimize for the structure, correlations and statistics of the traffic patterns on the NoC. Our results show that NeuMAC can quickly adapt to NoC traffic to provide significant gains in terms of latency and overall execution time, improving the execution time by up to 1.69× - 3.74×., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Fuzzy-Token: An adaptive MAC protocol for wireless-enabled manycores

  • Franques, Antonio
  • Abadal Cavallé, Sergi|||0000-0003-0941-0260
  • Hassanieh, Haitham
  • Torrellas, Josep
Recent computer architecture trends herald the arrival of manycores with over one hundred cores on a single chip. In this context, traditional on-chip networks do not scale well in latency or energy consumption, leading to bottlenecks in the execution. The Wireless Network-on-Chip (WNoC) paradigm holds considerable promise for the implementation of on-chip networks that will enable such highly-parallel manycores. However, one of the main challenges in WNoCs is the design of mechanisms that provide fast and efficient access to the wireless channel, while adapting to the changing traffic patterns within and across applications. Existing approaches are either slow or complicated, and do not provide the required adaptivity. In this paper, we propose FUZZY TOKEN, a simple WNoC protocol that leverages the unique properties of the on-chip scenario to deliver efficient and low-latency access to the wireless channel irrespective of the application characteristics. We substantiate our claim via simulations with a synthetic traffic suite and with real application traces. FUZZY TOKEN consistently provides one of the lowest packet latencies among the evaluated WNoC MAC protocols. On average, the packet latency in FUZZY TOKEN is 4.4× and 2.6× lower than in a state-of-the art contention-based WNoC MAC protocol and in a token-passing protocol, respectively., This work was funded in part by NSF Grant No. CCF-1629431 and by EU’s Horizon 2020 research and innovation programme Grant No. 863337 (WiPLASH)., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publicación Contribución de congreso (ConferenceOutput)

Toward dynamically adapting wireless intra-chip channels to traffic needs with a programmable metasurface

  • Imani, Mohammadreza
  • Abadal Cavallé, Sergi|||0000-0003-0941-0260
  • Del Hougne, Philipp
We introduce the idea of endowing on-chip wireless propagation environments with in-situ programmability by equipping the chip package with a programmable metasurface. The limitations of current wired chip interconnect fabrics present a serious performance bottleneck for multi-core chips. Wireless links between far-apart cores are a promising complementary link technique but struggle with the complex on-chip propagation environment presenting strong multipath effects. We expect that these challenges can be addressed with the ability to shape wireless channels between far-apart cores and to dynamically adapt them to traffic needs; for instance, by tailoring the impulse response between two wireless nodes, it may be feasible to prevent inter-symbol interference. Here, we present our recent progress toward this goal, including an analysis of the on-chip propagation environment, an efficient design of programmable meta-atoms suitable for the on-chip environment and operating in the 60 GHz regime, and a detailed discussion of different single-channel and multi-channel use-case scenarios., S.A. acknowledges support from the European Commission throughthe H2020 FET-OPEN program under grants No. 736876 and No. 863337, Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

System-level exploration of in-package wireless communication for multi-chiplet platforms

  • Medina Morillas, Rafael
  • Kein, Joshua
  • Ansaloni, Giovanni
  • Zapater Sancho, Marina
  • Abadal Cavallé, Sergi
  • Alarcón Cot, Eduardo José
  • Atienza Alonso, David
Multi-Chiplet architectures are being increasingly adopted to support the design of very large systems in a single package, facilitating the integration of heterogeneous components and improving manufacturing yield. However, chiplet-based solutions have to cope with limited inter-chiplet routing resources, which complicate the design of the data interconnect and the power delivery network. Emerging in-package wireless technology is a promising strategy to address these challenges, as it allows to implement flexible chiplet interconnects while freeing package resources for power supply connections. To assess the capabilities of such an approach and its impact from a full-system perspective, herein we present an exploration of the performance of in-package wireless communication, based on dedicated extensions to the gem5-X simulator. We consider different Medium Access Control (MAC) protocols, as well as applications with different runtime profiles, showcasing that current in-package wireless solutions are competitive with wired chiplet interconnects. Our results show how in-package wireless solutions can outperform wired alternatives when running artificial intelligence workloads, achieving up to a 2.64× speed-up when running deep neural networks (DNNs) on a chiplet-based system with 16 cores distributed in four clusters., This work has been partially supported by the EC H2020 WiPLASH project (GA No. 863337) and the EC H2020 FVLLMONTI project (GA No. 101016776), Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

WiDir: A Wireless-Enabled Directory cache coherence protocol

  • Franques, Antonio
  • Kokolis, Apostolos
  • Abadal Cavallé, Sergi
  • Fernando, Vimuth
  • Misailovic, Sasa
  • Torrellas, Josep
As the core count in shared-memory manycores keeps increasing, it is becoming increasingly harder to design cache-coherence protocols that deliver high performance without an inordinate increase in complexity and cost. In particular, sharing patterns where a group of cores frequently reads and writes a shared variable are hard to support efficiently. Hence, programmers end up tuning their applications to avoid these patterns, hurting the programmability of shared memory. To address this problem, this paper uses the recently-proposed on-chip wireless network technology to augment a conventional invalidation-based directory cache coherence protocol. We call the resulting protocol WiDir. WiDir seamlessly transitions between wired and wireless coherence transactions for a given line based on the access patterns in a programmer-transparent manner. In this paper, we describe the protocol transitions in detail. Further, an evaluation using SPLASH and PARSEC applications shows that WiDir substantially reduces the memory stall time of applications. As a result, for 64-core runs, WiDir reduces the execution time of applications by an average of 22% compared to a conventional directory protocol. Moreover, WiDir is more scalable. These benefits are obtained with a very modest power cost., This work was funded in part by NSF Grant No. CCF1629431 and by EU’s Horizon 2020 Research and Innovation Programme Grant No. 863337 (WiPLASH)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Fuzzy-Token: An adaptive MAC protocol for wireless-enabled manycores

  • Franques, Antonio
  • Abadal Cavallé, Sergi
  • Hassanieh, Haitham
  • Torrellas, Josep
Recent computer architecture trends herald the arrival of manycores with over one hundred cores on a single chip. In this context, traditional on-chip networks do not scale well in latency or energy consumption, leading to bottlenecks in the execution. The Wireless Network-on-Chip (WNoC) paradigm holds considerable promise for the implementation of on-chip networks that will enable such highly-parallel manycores. However, one of the main challenges in WNoCs is the design of mechanisms that provide fast and efficient access to the wireless channel, while adapting to the changing traffic patterns within and across applications. Existing approaches are either slow or complicated, and do not provide the required adaptivity. In this paper, we propose FUZZY TOKEN, a simple WNoC protocol that leverages the unique properties of the on-chip scenario to deliver efficient and low-latency access to the wireless channel irrespective of the application characteristics. We substantiate our claim via simulations with a synthetic traffic suite and with real application traces. FUZZY TOKEN consistently provides one of the lowest packet latencies among the evaluated WNoC MAC protocols. On average, the packet latency in FUZZY TOKEN is 4.4× and 2.6× lower than in a state-of-the art contention-based WNoC MAC protocol and in a token-passing protocol, respectively., This work was funded in part by NSF Grant No. CCF-1629431 and by EU’s Horizon 2020 research and innovation programme Grant No. 863337 (WiPLASH)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Architecting more than Moore: wireless plasticity for massive heterogeneous computer architectures (WiPLASH)

  • Klein, Joshua
  • Levisse, Alexandre
  • Ansaloni, Giovanni
  • Atienza Alonso, David
  • Zapater Sancho, Marina
  • Dazzi, Martino
  • Karunaratne, Geethan
  • Boybat, Irem
  • Sebastian, Abu
  • Rossi, Davide
  • Jain, Akshay
  • Guirado Liñan, Robert
  • Taghvaee, Hamidreza
  • Abadal Cavallé, Sergi
This paper presents the research directions pursued by the WiPLASH European project, pioneering on-chip wireless communications as a disruptive enabler towards next-generation computing systems for artificial intelligence (AI). We illustrate the holistic approach driving our research efforts, which encompass expertises and abstraction levels ranging from physical design of embedded graphene antennas to system-level evaluation of wirelessly-communicating heterogeneous systems., This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 863337 (WiPLASH)., Peer Reviewed, Article signat per 22 autors/es: - Joshua Klein, Alexandre Levisse, Giovanni Ansaloni, David Atienza (EPFL, Lausanne, Switzerland) - Marina Zapater (HEIG-VD/HES-SO Yverdon-les-Bains, Switzerland / EPFL, Lausanne, Switzerland) - Martino Dazzi, Geethan Karunaratne, Irem Boybat, Abu Sebastian (IBM Research Europe, Zurich, Switzerland) - Davide Rossi, Francesco Conti (Università di Bologna, Bologna, Italy) - Elana Pereira de Santana, Peter Haring Bolívar (University of Siegen, Siegen, Germany) - Mohamed Saeed, Renato Negra (RWTH, Aachen, Germany) - Zhenxing Wang, Kun-Ta Wang (AMO GmbH, Aachen, Germany) - Max C. Lemme (RWTH, Aachen, Germany / AMO GmbH, Aachen, Germany) - Akshay Jain, Robert Guirado, Hamidreza Taghvaee, Sergi Abadal (Universitat Politècnica de Catalunya, Barcelona, Spain), Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Integrated graphene patch antenna for communications at THz frequencies

  • de Santana, Elana Pereira
  • Wigger, Anna K.
  • Wang, Zhenxing
  • Wang, Kun Ta
  • Lemme, Max
  • Abadal Cavallé, Sergi
  • Haring Bolívar, Peter
Graphene is an attractive material for communications in the THz range due to its ability to support surface plasmon polaritons. This enables a graphene antenna to be smaller in size than its metallic counterpart. In addition, the possibility to control the graphene conductivity during operation by an applied bias leads to the tunability of the resonant frequency of graphene antennas. Graphene-based antennas integrated into transceivers working at THz frequencies may lead to faster and more efficient devices. In this work, we design and simulate a graphene patch antenna that can be integrated into transceivers by through-substrate vias. The tuning of the resonant frequency is also studied by simulations., This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement N° 863337., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

One protocol to rule them all: Wireless network-on-chip using deep reinforcement learning

  • Jog, Suraj
  • Liu, Zikun
  • Franques, Antonio
  • Fernando, Vimuth
  • Abadal Cavallé, Sergi
  • Torrellas, Josep
  • Hassanieh, Haitham
Wireless Network-on-Chip (NoC) has emerged as a promising solution to scale chip multi-core processors to hundreds and thousands of cores. The broadcast nature of a wireless network allows it to significantly reduce the latency and overhead of many-to-many multicast and broadcast communication on NoC processors. Unfortunately, the traffic patterns on wireless NoCs tend to be very dynamic and can change drastically across different cores, different time intervals and different applications. New medium access protocols that can learn and adapt to the highly dynamic traffic in wireless NoCs are needed to ensure low latency and efficient network utilization. Towards this goal, we present NeuMAC, a unified approach that combines networking, architecture and deep learning to generate highly adaptive medium access protocols for wireless NoC architectures. NeuMAC leverages a deep reinforcement learning framework to create new policies that can learn the structure, correlations, and statistics of the traffic patterns and adapt quickly to optimize performance. Our results show that NeuMAC can quickly adapt to NoC traffic to provide significant gains in terms of latency, throughput, and overall execution time. In particular, for applications with highly dynamic traffic patterns, NeuMAC can speed up the execution time by 1.37× -3.74× as compared to 6 baselines., The work is funded in part by NSF Award 1750725., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Collective communication patterns using time-reversal terahertz links at the chip scale

  • Rodríguez Galán, Fátima Yolanda
  • Ama Bandara, Paveena
  • de Santana, Elana Pereira
  • Bolívar, Peter Haring
  • Alarcón Cot, Eduardo José
  • Abadal Cavallé, Sergi
Wireless communications in the terahertz band have been recently proposed as complement to conventional wired interconnects within computing packages. Such environments are typically highly reverberant, hence showing long channel impulse responses and severely limiting the achievable rates. Fortunately, this communications scenario is static and can be pre-characterized, which opens the door to techniques such as time reversal. Time reversal acts a spatial matched filter and has a spatiotemporal focusing effect, which allows not only to increase the achievable symbol rates, but also to create multiple spatial channels. In this paper, the multi-user capability of time reversal is explored in the context of wireless communications in the terahertz band within a computing package. Full-wave simulations are carried out to validate the approach, whereas modulation streams are simulated to evaluate the error rate as a function of the transmitted power, symbol rate, and number of simultaneous transmissions., Authors acknowledge support from the European Union’s Horizon 2020 research and innovation program, grant agreement 863337 (WiPLASH), the European Research Council (ERC) under grant agreement 101042080 (WINC) as well as the European Innovation Council (EIC) PATHFINDER scheme, grant agreement No 101099697 (QUADRATURE)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Multi-channel medium access control protocols for wireless networks within computing packages

  • Ollé Ferrayuoli, Bernat
  • Talarn Bell-lloch, Pau
  • Cabellos Aparicio, Alberto
  • Lemic, Filip
  • Alarcón Cot, Eduardo José
  • Abadal Cavallé, Sergi
Wireless communications at the chip scale emerge as a interesting complement to traditional wire-based approaches thanks to their low latency, inherent broadcast nature, and capacity to bypass pin constraints. However, as current trends push towards massive and bandwidth-hungry processor architectures, there is a need for wireless chip-scale networks that exploit and share as many channels as possible. In this context, this work addresses the issue of channel sharing by exploring the design space of multi-channel Medium Access Control (MAC) protocols for chip-scale networks. Distinct channel assignment strategies for both random access and token passing are presented and evaluated under realistic traffic patterns. It is shown that, even with the improvements enabled by the multiple channels, both protocols maintain their intrinsic advantages and disadvantages., This work is supported by the European Commission under H2020 grant WiPLASH (GA 863337) and HE grant WINC (GA 101042080)., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Toward dynamically adapting wireless intra-chip channels to traffic needs with a programmable metasurface

  • Imani, Mohammadreza
  • Abadal Cavallé, Sergi
  • Del Hougne, Philipp
We introduce the idea of endowing on-chip wireless propagation environments with in-situ programmability by equipping the chip package with a programmable metasurface. The limitations of current wired chip interconnect fabrics present a serious performance bottleneck for multi-core chips. Wireless links between far-apart cores are a promising complementary link technique but struggle with the complex on-chip propagation environment presenting strong multipath effects. We expect that these challenges can be addressed with the ability to shape wireless channels between far-apart cores and to dynamically adapt them to traffic needs; for instance, by tailoring the impulse response between two wireless nodes, it may be feasible to prevent inter-symbol interference. Here, we present our recent progress toward this goal, including an analysis of the on-chip propagation environment, an efficient design of programmable meta-atoms suitable for the on-chip environment and operating in the 60 GHz regime, and a detailed discussion of different single-channel and multi-channel use-case scenarios., S.A. acknowledges support from the European Commission throughthe H2020 FET-OPEN program under grants No. 736876 and No. 863337, Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Towards spatial multiplexing in wireless networks within computing packages

  • Rodríguez Galán, Fátima Yolanda
  • de Santana, Elana Pereira
  • Bolívar, Peter Haring
  • Abadal Cavallé, Sergi
  • Alarcón Cot, Eduardo José
Wireless Networks-on-Chip (WNoCs) are regarded as a disruptive alternative to conventional interconnection networks at the chip scale, yet limited by the relatively low aggregate bandwidth of such wireless networks. Hence, any method to increase the amount of concurrent channels in this scenario is of high value. In this direction, and since WNoC implies close integration of multiple antennas on a chip anyway, in this paper we present a feasibility study of compact monopole antenna arrays in a flip-chip environment at millimeter-wave and sub-terahertz frequencies. By means of a full-wave solver, we evaluate the feasibility to create, at will, concentrations of field in different spots of the chip. This way, we set the steps towards spatial multiplexing that enables concurrent multicast communications and also increases the aggregate bandwidth of the wireless network. Our results at 60 GHz show two clearly separable parallel channels that radiate simultaneously from two opposite corners of the chip, achieving a Signal-to-Interference Ratio (SIR) of around 40 dB, which proves that the channels are independent of each other even in such an enclosed environment. Further, we see potential to expand our approach to three or more concurrent channels, and to frequencies beyond 100 GHz., Authors acknowledge support from the European Union’s Horizon 2020 research and innovation program, grant agreement 863337., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Scale up your In-Memory Accelerator: leveraging wireless-on-chip communication for AIMC-based CNN inference

  • Bruschi, Nazareno
  • Tagliavini, Giuseppe
  • Conti, Francesco
  • Abadal Cavallé, Sergi
  • Cabellos Aparicio, Alberto
  • Alarcón Cot, Eduardo José
  • Karunaratne, Geethan
  • Boybat, Irem
  • Benini, Luca
  • Rossi, Davide
Analog In-Memory Computing (AIMC) is emerging as a disruptive paradigm for heterogeneous computing, potentially delivering orders of magnitude better peak performance and efficiency over traditional digital signal processing architectures on Matrix-Vector multiplication. However, to sustain this throughput in real-world applications, AIMC tiles must be supplied with data at very high bandwidth and low latency; this poses an unprecedented pressure on the on-chip communication infrastructure, which becomes the system's performance and efficiency bottleneck. In this context, the performance and plasticity of emerging on-chip wireless communication paradigms provide the required breakthrough to up-scale on-chip communication in large AIMC devices. This work presents a many-tile AIMC architecture with inter-tile wireless communication that integrates multiple heterogeneous computing clusters, embedding a mix of parallel RISC-V cores and AIMC tiles. We perform an extensive design space exploration of the proposed architecture and discuss the benefits of exploiting emerging on-chip communication technologies such as wireless transceivers in the millimeter-wave and terahertz bands., This work was supported by the WiPLASH project (g.a. 863337), founded from the European Union’s Horizon 2020 research and innovation program., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Tunable plasmonic graphene antenna array for communications at THz frequencies

  • de Santana, Elana Pereira
  • Stock, Daniel
  • Wang, Zhenxing
  • Wang, Kun Ta
  • Abadal Cavallé, Sergi
  • Lemme, Max
  • Bolívar, Peter Haring
The existence of plasmonic waves at a graphene/dielectric interface at THz frequencies enables the use of graphene as the radiative element of antennas working at this frequency range, but with a smaller lateral dimension compared to a standard metallic antenna. Due to the low carrier mobility in large-area graphene, result of its manufacturing process, the emitted radiation of graphene antennas is still smaller than its metallic counterpart. In this work, we show that the low emission of a graphene antenna can be compensated by antenna arrays. The proposed 1x4 graphene antenna array presents a far-field radiated gain of 9.3 dBi with a resonance frequency at 269 GHz. The resonating frequency of the graphene antenna array can also be tuned by an electrostatic bias., This project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement N° 863337., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Dataflow-architecture co-design for 2.5D DNN accelerators using wireless network-on-package

  • Guirado Liñan, Robert
  • Kwon, Hyoukjun
  • Abadal Cavallé, Sergi
  • Alarcón Cot, Eduardo José
  • Krishna, Tushar
Deep neural network (DNN) models continue to grow in size and complexity, demanding higher computational power to enable real-time inference. To efficiently deliver such computational demands, hardware accelerators are being developed and deployed across scales. This naturally requires an efficient scale-out mechanism for increasing compute density as required by the application. 2.5D integration over interposer has emerged as a promising solution, but as we show in this work, the limited interposer bandwidth and multiple hops in the Network-on-Package (NoP) can diminish the benefits of the approach. To cope with this challenge, we propose WIENNA, a wireless NoP-based 2.5D DNN accelerator. In WIENNA, the wireless NoP connects an array of DNN accelerator chiplets to the global buffer chiplet, providing high-bandwidth multicasting capabilities. Here, we also identify the dataflow style that most efficienty exploits the wireless NoP's high-bandwidth multicasting capability on each layer. With modest area and power overheads, WIENNA achieves 2.2X-5.1X higher throughput and 38.2% lower energy than an interposer-based NoP design., This work was supported by the European Commission under grant 863337 and NSF under Award OAC-1909900., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Millimeter wave wireless network on chip using deep reinforcement learning

  • Jog, Suraj
  • Liu, Zikun
  • Franques, Antonio
  • Fernando, Vimuth
  • Hassanieh, Haitham
  • Abadal Cavallé, Sergi
  • Torrellas, Josep
Wireless Network-on-Chip (NoC) has emerged as a promising solution to scale chip multi-core processors to hundreds of cores. However, traditional medium access protocols fall short here since the traffic patterns on wireless NoCs tend to be very dynamic and can change drastically across different cores, different time intervals and different applications. In this work, we present NeuMAC, a unified approach that combines networking, architecture and AI to generate highly adaptive medium access protocols that can learn and optimize for the structure, correlations and statistics of the traffic patterns on the NoC. Our results show that NeuMAC can quickly adapt to NoC traffic to provide significant gains in terms of latency and overall execution time, improving the execution time by up to 1.69× - 3.74×., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publicación Contribución de congreso (ConferenceOutput)

Characterizing the communication requirements of GNN accelerators: A model-based approach

  • Guirado Liñan, Robert
  • Jain, Akshay
  • Abadal Cavallé, Sergi
  • Alarcón Cot, Eduardo José
Relational data present in real world graph representations demands for tools capable to study it accurately. In this regard Graph Neural Network (GNN) is a powerful tool, wherein various models for it have also been developed over the past decade. Recently, there has been a significant push towards creating accelerators that speed up the inference and training process of GNNs. These accelerators, however, do not delve into the impact of their dataflows on the overall data movement and, hence, on the communication requirements. In this paper, we formulate analytical models that capture the amount of data movement in the most recent GNN accelerator frameworks. Specifically, the proposed models capture the dataflows and hardware setup of these accelerator designs and expose their scalability characteristics for a set of hardware, GNN model and input graph parameters. Additionally, the proposed approach provides means for the comparative analysis of the vastly different GNN accelerators., The authors gratefully acknowledge support from the Spanish Ministry of Science and Innovation (MICINN) under grant EIN2019-103461 and from the European Comission under grant H2020-863337-WIPLASH., Peer Reviewed, Postprint (author's final draft)