Ioannis A. Papistas
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Ioannis A. Papistas has a total of 26 co-authors. Here are the top co-authors by number of shared publications:
Vasilis F. Pavlidis
Advanced Processor Technologies Group, School of Computer Science, University of Manchester, M13 9PL, Manchester, United Kingdom
6 shared publications- Peter Debacker
IMEC, Leuven, Belgium
2 shared publications A. Belmonte
IMEC, 3001 Leuven, Belgium
1 shared publicationA. Mallik
IMEC, 3001 Leuven, Belgium
1 shared publicationArindam Mallik
IMEC, Leuven, Belgium
1 shared publicationD. Verkest
IMEC, 3001 Leuven, Belgium
1 shared publication
Latest Publications
- Top Cited Papers
- 31 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 58 (1) , 203-215
DIANA: An End-to-End Hybrid DIgital and ANAlog Neural Network SoC for the Edge
DIgital-ANAlog (DIANA), a heterogeneous multi-core accelerator, combines a reduced instruction set computer -five (RISC-V) host processor with an analog in-memory computing (AIMC) artificial intelligence (AI) accelerator and a digital reconfigurable deep neural network (DNN) accelerator in a single system-on-chip (SoC) to support a wide variety of neural network (NN) workloads. AIMC cores can bring extreme computational parallelism and efficiency at the expense of accuracy and dataflow flexibility. Digital AI co-processors, on the other hand, guarantee accuracy through deterministic compute, but cannot achieve the same computational density and efficiency. DIANA exploits this fundamental tradeoff by integrating both types of cores in a shared and optimized memory system, to enable seamless execution of the workloads on the parallel cores. The system’s performance benefits further from pipelined parallel execution across both accelerator cores and enhanced AIMC spatial unrolling techniques, leading to drastically reduced execution latency and reduced memory footprints. The design has been implemented in a 22-nm technology and achieves peak efficiencies of 600 TOP/s/W for the AIMC core (I/W/O: 7/1.5/6 bit) and 14 TOP/s/W (I/W/O: 8/8/8 bit) for the digital accelerator, respectively. End-to-end performance evaluation of CIFAR-10 and ImageNet classification workloads is carried out on the chip, reporting 7.02 and 5.56 TOP/s/W, respectively, at the system level.
- 31 October 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Solid-State Circuits
- Vol. 58 (1) , 203-215
Top Cited PapersDIANA: An End-to-End Hybrid DIgital and ANAlog Neural Network SoC for the Edge
DIgital-ANAlog (DIANA), a heterogeneous multi-core accelerator, combines a reduced instruction set computer -five (RISC-V) host processor with an analog in-memory computing (AIMC) artificial intelligence (AI) accelerator and a digital reconfigurable deep neural network (DNN) accelerator in a single system-on-chip (SoC) to support a wide variety of neural network (NN) workloads. AIMC cores can bring extreme computational parallelism and efficiency at the expense of accuracy and dataflow flexibility. Digital AI co-processors, on the other hand, guarantee accuracy through deterministic compute, but cannot achieve the same computational density and efficiency. DIANA exploits this fundamental tradeoff by integrating both types of cores in a shared and optimized memory system, to enable seamless execution of the workloads on the parallel cores. The system’s performance benefits further from pipelined parallel execution across both accelerator cores and enhanced AIMC spatial unrolling techniques, leading to drastically reduced execution latency and reduced memory footprints. The design has been implemented in a 22-nm technology and achieves peak efficiencies of 600 TOP/s/W for the AIMC core (I/W/O: 7/1.5/6 bit) and 14 TOP/s/W (I/W/O: 8/8/8 bit) for the digital accelerator, respectively. End-to-end performance evaluation of CIFAR-10 and ImageNet classification workloads is carried out on the chip, reporting 7.02 and 5.56 TOP/s/W, respectively, at the system level.
- 5 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 67 (11) , 4616-4620
IGZO-Based Compute Cell for Analog In-Memory Computing—DTCO Analysis to Enable Ultralow-Power AI at Edge
We propose, for the first time, an indium gallium zinc oxide (IGZO)-based 2T1C compute cell (IGZO-cell) for analog in-memory computing. To assess the impact of an IGZO-cell-based array including the periphery on power and accuracy, a PyTorch framework was developed to analytically modeled analog components. The results are reported for a ResNet20 network on the Canadian Institute For Advanced Research-10 (CIFAR-10) benchmark. The state-of-the-art energy efficiency of 15 peta operations per second (POPS)/W including the periphery is achieved by using our proposed IGZO-cell with CMOS compatibility. Finally, it is shown that, with a properly trained neural network model, there is no degradation of test accuracy with 10% device to device variability for the IGZO devices.
- 5 October 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Electron Devices
- Vol. 67 (11) , 4616-4620
IGZO-Based Compute Cell for Analog In-Memory Computing—DTCO Analysis to Enable Ultralow-Power AI at Edge
We propose, for the first time, an indium gallium zinc oxide (IGZO)-based 2T1C compute cell (IGZO-cell) for analog in-memory computing. To assess the impact of an IGZO-cell-based array including the periphery on power and accuracy, a PyTorch framework was developed to analytically modeled analog components. The results are reported for a ResNet20 network on the Canadian Institute For Advanced Research-10 (CIFAR-10) benchmark. The state-of-the-art energy efficiency of 15 peta operations per second (POPS)/W including the periphery is achieved by using our proposed IGZO-cell with CMOS compatibility. Finally, it is shown that, with a properly trained neural network model, there is no degradation of test accuracy with 10% device to device variability for the IGZO devices.
- 9 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 66 (5) , 758-762
Fabrication Cost Analysis for Contactless 3-D ICs
The manufacturing cost of contactless 3-D circuits with inductive links is explored for the first time. The high-volume manufacturing (HVM) cost of contactless 3-D ICs is modeled by considering the on-chip inductor area and other important parameters, such as the coupling efficiency, which depend upon specific steps of the fabrication process. Inductive links based on current mode logic (CML) transceivers are simulated across a number of integration scenarios in a commercial 65-nm CMOS technology process, thereby evaluating the cost of these manufacturing options for performance and power objectives. Assuming a 10 Gb/s data rate, the power and area of the inductive link are determined for wafer-to-wafer and die-to-wafer integration and communication distances in the range of 5 $\mu \text{m}$ (face-to-face) to 120 $\mu \text{m}$ (face-to-back). An HVM cost estimation for each investigated inductive link scheme is provided for these integration approaches. Additional processing steps attributed to 3-D integration increase the aggregate cost by 2.5%–4.5% for a case study of a three-tier stack, compared to a conventional 2-D process. Moreover, the yield is explored for each integration approach considering the inductor area for contactless 3-D ICs.
- 9 April 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems II: Express Briefs
- Vol. 66 (5) , 758-762
Fabrication Cost Analysis for Contactless 3-D ICs
The manufacturing cost of contactless 3-D circuits with inductive links is explored for the first time. The high-volume manufacturing (HVM) cost of contactless 3-D ICs is modeled by considering the on-chip inductor area and other important parameters, such as the coupling efficiency, which depend upon specific steps of the fabrication process. Inductive links based on current mode logic (CML) transceivers are simulated across a number of integration scenarios in a commercial 65-nm CMOS technology process, thereby evaluating the cost of these manufacturing options for performance and power objectives. Assuming a 10 Gb/s data rate, the power and area of the inductive link are determined for wafer-to-wafer and die-to-wafer integration and communication distances in the range of 5 $\mu \text{m}$ (face-to-face) to 120 $\mu \text{m}$ (face-to-back). An HVM cost estimation for each investigated inductive link scheme is provided for these integration approaches. Additional processing steps attributed to 3-D integration increase the aggregate cost by 2.5%–4.5% for a case study of a three-tier stack, compared to a conventional 2-D process. Moreover, the yield is explored for each integration approach considering the inductor area for contactless 3-D ICs.
- 1 June 2018
- Published by Elsevier in Integration
- Vol. 62, 329-340
Contactless Heterogeneous 3-D ICs for Smart Sensing Systems
- 1 June 2018
- Published by Elsevier in Integration
- Vol. 62, 329-340
Contactless Heterogeneous 3-D ICs for Smart Sensing Systems
- 1 May 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Contactless inter-tier communication for heterogeneous 3-D ICs
A heterogeneous contactless transceiver circuit is designed to provide half duplex communication for a 3-D system considering specific bonding constraints. The system is composed of two tiers and is integrated face-to-back to support fluidic sensing. Communication between the tiers is achieved through inductive links. Each tier is considered to be fabricated in a different technology node to enable low manufacturing cost and benefit from the advantages each technology offers. Both the uplink and downlink transceivers achieve data rates that reach 1 Gbps with non-return-to-zero data encoding. Energy efficiency is the primary objective, with the uplink dissipating 4.93 mW and the downlink 10.53 mW. A 5.2 × power reduction is achieved when using heterogeneous technologies, compared to a state-of-the-art 0.35 βm transceiver, while the dissipated energy is decreased by 34% as compared to a state-of-the-art 65 nm transceiver.
- 1 May 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Contactless inter-tier communication for heterogeneous 3-D ICs
A heterogeneous contactless transceiver circuit is designed to provide half duplex communication for a 3-D system considering specific bonding constraints. The system is composed of two tiers and is integrated face-to-back to support fluidic sensing. Communication between the tiers is achieved through inductive links. Each tier is considered to be fabricated in a different technology node to enable low manufacturing cost and benefit from the advantages each technology offers. Both the uplink and downlink transceivers achieve data rates that reach 1 Gbps with non-return-to-zero data encoding. Energy efficiency is the primary objective, with the uplink dissipating 4.93 mW and the downlink 10.53 mW. A 5.2 × power reduction is achieved when using heterogeneous technologies, compared to a state-of-the-art 0.35 βm transceiver, while the dissipated energy is decreased by 34% as compared to a state-of-the-art 65 nm transceiver.
- 1 May 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 314-316
Comparative study of crosstalk noise due to inductive links on heterogeneous 3-D ICs
Inductive links have been proposed as an inter-tier interconnect solution for three-dimensional (3-D) integrated systems. Combined with signal multiplexing, inductive links achieve high communication bandwidth comparable to that of through silicon vias. However, being a wireless medium, electromagnetic coupling between the inductive link and nearby on-chip interconnects can cause voltage fluctuations affecting interconnect performance. Signal interference from adjacent interconnects on the operation of inductive links has empirically been investigated. Nevertheless, the reverse problem has yet to be fully explored. Consequently, this paper investigates the effect of electromagnetic coupling on the global interconnects of the power delivery network in the vicinity of on-chip inductors for disparate technologies in a heterogeneous 3-D SiP.
- 1 May 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 314-316
Comparative study of crosstalk noise due to inductive links on heterogeneous 3-D ICs
Inductive links have been proposed as an inter-tier interconnect solution for three-dimensional (3-D) integrated systems. Combined with signal multiplexing, inductive links achieve high communication bandwidth comparable to that of through silicon vias. However, being a wireless medium, electromagnetic coupling between the inductive link and nearby on-chip interconnects can cause voltage fluctuations affecting interconnect performance. Signal interference from adjacent interconnects on the operation of inductive links has empirically been investigated. Nevertheless, the reverse problem has yet to be fully explored. Consequently, this paper investigates the effect of electromagnetic coupling on the global interconnects of the power delivery network in the vicinity of on-chip inductors for disparate technologies in a heterogeneous 3-D SiP.
- 11 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1938-1941
Crosstalk noise effects of on-chip inductive links on power delivery networks
Inductive links have been proposed as an inter-tier interconnect solution for three-dimensional (3-D) integrated systems. Combined with signal multiplexing, inductive links achieve high communication bandwidth comparable to that of through silicon vias. However, being a wireless medium, electromagnetic coupling between the inductive link and nearby on-chip interconnects can cause voltage fluctuations affecting interconnect performance. The interference of interconnects on the operation of inductive links has been empirically investigated. Nevertheless, the reverse problem has yet to be explored. Consequently, this paper investigates the effect of electromagnetic coupling on global interconnects of the power delivery network in the vicinity of on-chip inductors. Analysis shows that operation at 6 GHz leads to an induced noise of 39.5 mV per link, which increases further if the interconnect length spans several inductors. As this noise adds to the existing power supply noise, this paper proposes amendments to the placement of the power/ground lines to maintain the power supply noise below a specified limit.
- 11 August 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1938-1941
Crosstalk noise effects of on-chip inductive links on power delivery networks
Inductive links have been proposed as an inter-tier interconnect solution for three-dimensional (3-D) integrated systems. Combined with signal multiplexing, inductive links achieve high communication bandwidth comparable to that of through silicon vias. However, being a wireless medium, electromagnetic coupling between the inductive link and nearby on-chip interconnects can cause voltage fluctuations affecting interconnect performance. The interference of interconnects on the operation of inductive links has been empirically investigated. Nevertheless, the reverse problem has yet to be explored. Consequently, this paper investigates the effect of electromagnetic coupling on global interconnects of the power delivery network in the vicinity of on-chip inductors. Analysis shows that operation at 6 GHz leads to an induced noise of 39.5 mV per link, which increases further if the interconnect length spans several inductors. As this noise adds to the existing power supply noise, this paper proposes amendments to the placement of the power/ground lines to maintain the power supply noise below a specified limit.
- Open Access
- 18 May 2016
- Published by Association for Computing Machinery (ACM)
- p. 257-262
Inter-Tier Crosstalk Noise On Power Delivery Networks For 3-D ICs With Inductively-Coupled Interconnects
Inductive links have been proposed as an inter-tier interconnect solution for three-dimensional (3-D) integrated systems. Combined with signal multiplexing, inductive links achieve high communication bandwidth comparable to that of through silicon vias. However, being a wireless medium, electromagnetic coupling between the inductive link and near-by on-chip interconnects can cause voltage fluctuations affecting interconnect performance. Although the interference of interconnects on the operation of inductive links has been investigated, the inverse problem has yet to be explored. Consequently, this paper performs an investigation on the effect of electromagnetic coupling on different topologies of power delivery networks (PDNs) in the vicinity of on-chip inductors. Results indicate that the interdigitated PDN topology suffers from the induced noise due to the inductive links of the neighbouring tiers exhibiting a minimum aggregate noise of 131.3 mV. Alternatively, the paired topologies exhibit a superior noise behaviour, achieving a 39.4% and 35.4% decrease in noise level for paired type I and paired type II topologies, respectively, compared to the interdigitated topology.
- 18 May 2016
- Published by Association for Computing Machinery (ACM)
- p. 257-262
Open AccessInter-Tier Crosstalk Noise On Power Delivery Networks For 3-D ICs With Inductively-Coupled Interconnects
Inductive links have been proposed as an inter-tier interconnect solution for three-dimensional (3-D) integrated systems. Combined with signal multiplexing, inductive links achieve high communication bandwidth comparable to that of through silicon vias. However, being a wireless medium, electromagnetic coupling between the inductive link and near-by on-chip interconnects can cause voltage fluctuations affecting interconnect performance. Although the interference of interconnects on the operation of inductive links has been investigated, the inverse problem has yet to be explored. Consequently, this paper performs an investigation on the effect of electromagnetic coupling on different topologies of power delivery networks (PDNs) in the vicinity of on-chip inductors. Results indicate that the interdigitated PDN topology suffers from the induced noise due to the inductive links of the neighbouring tiers exhibiting a minimum aggregate noise of 131.3 mV. Alternatively, the paired topologies exhibit a superior noise behaviour, achieving a 39.4% and 35.4% decrease in noise level for paired type I and paired type II topologies, respectively, compared to the interdigitated topology.
- 1 August 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Bandwidth-to-area comparison of through silicon vias and inductive links for 3-D ICs
Three-dimensional (3-D) integration is a promising technology that can mitigate the deleterious effects of the increased interconnect length in modern ICs by vertically stacking dies. Through silicon vias (TSVs) and AC coupling have been proposed as communication interfaces between multiple stacked dies. This paper investigates these communication schemes for 3-D systems where the link bandwidth is treated as a constraint rather than an objective. A frequency dependent RC model for the TSV and the redistribution layer (RDL) is employed. A first order delay analysis between the two schemes shows comparable performance, but a better area efficiency for the TSV. Considering, however, a multiplexing scheme shows that TSVs with a pitch lower than 20 μm exhibit better bandwidth-to-area efficiency without multiplexing, while the inductive link demonstrates higher efficiency in comparison to TSVs with a pitch larger than 20 μm for a 12:1 multiplexing ratio.
- 1 August 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Bandwidth-to-area comparison of through silicon vias and inductive links for 3-D ICs
Three-dimensional (3-D) integration is a promising technology that can mitigate the deleterious effects of the increased interconnect length in modern ICs by vertically stacking dies. Through silicon vias (TSVs) and AC coupling have been proposed as communication interfaces between multiple stacked dies. This paper investigates these communication schemes for 3-D systems where the link bandwidth is treated as a constraint rather than an objective. A frequency dependent RC model for the TSV and the redistribution layer (RDL) is employed. A first order delay analysis between the two schemes shows comparable performance, but a better area efficiency for the TSV. Considering, however, a multiplexing scheme shows that TSVs with a pitch lower than 20 μm exhibit better bandwidth-to-area efficiency without multiplexing, while the inductive link demonstrates higher efficiency in comparison to TSVs with a pitch larger than 20 μm for a 12:1 multiplexing ratio.