Surila Guglani, K. Dimple, A. Dasgupta, Rohit Sharma, B. Kaushik, Sourajeet Roy
{"title":"A Transfer Learning Approach to Expedite Training of Artificial Neural Networks for Variability-Aware Signal Integrity Analysis of MWCNT Interconnects","authors":"Surila Guglani, K. Dimple, A. Dasgupta, Rohit Sharma, B. Kaushik, Sourajeet Roy","doi":"10.1109/EPEPS53828.2022.9947162","DOIUrl":"https://doi.org/10.1109/EPEPS53828.2022.9947162","url":null,"abstract":"In this paper, an artificial neural network (ANN) trained using a novel transfer learning approach is presented for the variability-aware signal integrity analysis of on-chip multi-walled carbon nanotube (MWCNT) interconnects. In the proposed transfer learning approach, initially a secondary ANN is trained to emulate the signal integrity quantities of interest of an approximate equivalent single conductor (ESC) model of the MWCNT interconnects. Thereafter, the values of the weights and bias terms of this secondary ANN are used to expedite the training of the primary ANN that will emulate the signal integrity quantities of the more rigorous multiconductor circuit (MCC) model of the MWCNT interconnects.","PeriodicalId":284818,"journal":{"name":"2022 IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131100055","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":"2D Spectral Transposed Convolutional Neural Network for S-Parameter Predictions","authors":"Yiliang Guo, Xingchen Li, Madhavan Swaminathan","doi":"10.1109/EPEPS53828.2022.9947109","DOIUrl":"https://doi.org/10.1109/EPEPS53828.2022.9947109","url":null,"abstract":"In packaging problems, S-parameter predictions are necessary. Machine learning methods lead to dimensionality related challenges which we address here through spectral trans-posed convolutional neural network using 2D kernels. Results show that Normalized Mean-squared Error (NMSE) dropped 0.002 by using 53.7% of the parameters.","PeriodicalId":284818,"journal":{"name":"2022 IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131699041","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}
Kyungjune Son, Keunwoo Kim, Gapyeol Park, Daehwan Lho, Hyunwook Park, Boogyo Sim, Taein Shin, Joonsang Park, Haeyeon Kim, Joungho Kim, Kyubong Gong
{"title":"Signal Integrity and Power Leakage Optimization for 3D X-Point Memory Operation using Reinforcement Learning","authors":"Kyungjune Son, Keunwoo Kim, Gapyeol Park, Daehwan Lho, Hyunwook Park, Boogyo Sim, Taein Shin, Joonsang Park, Haeyeon Kim, Joungho Kim, Kyubong Gong","doi":"10.1109/EPEPS53828.2022.9947197","DOIUrl":"https://doi.org/10.1109/EPEPS53828.2022.9947197","url":null,"abstract":"As the signal integrity (SI) issues become critical with high bandwidth and density applications, the SI analysis and optimization are necessary. The SI optimization loop including design, modeling, simulation, analysis and revision is repetitive and confined to specific applications. To overcome the recurrent issues, we proposed reinforcement learning (RL) model for SI and power leakage optimization in 3D X-Point memory operation. We defined the MDP components to reflect the optimization problem and the RL model shows learning convergence. The optimal design shows 6.2 % of crosstalk, 17.7 % of IR drop and 25.3 % of power leakage improvement than original design.","PeriodicalId":284818,"journal":{"name":"2022 IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122678712","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}
Simon Chun Kit See, Asmah Truky, Gaurav Hada, Sameer Shekhar, Chandru Raman
{"title":"Memory Speed Enhancement via SI/PI Optimization in Constrained Tablet Designs","authors":"Simon Chun Kit See, Asmah Truky, Gaurav Hada, Sameer Shekhar, Chandru Raman","doi":"10.1109/EPEPS53828.2022.9947110","DOIUrl":"https://doi.org/10.1109/EPEPS53828.2022.9947110","url":null,"abstract":"Achieving high speed memory in small form-factor and low PCB layer count is critical for tablets designs. This paper reports several practical SI/PI design improvements such as PTH patterning suited for common memory ball-maps, etc. Simulation data showing voltage noises and eye diagrams are presented. Finally, measurement data with speeds of 3200 MT/s are provided for successful demonstration.","PeriodicalId":284818,"journal":{"name":"2022 IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116454482","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}
Seungjin Lee, Jonghoon J. Kim, Jinseong Yun, Hee-Jea Cho, Youngho Lee, Kyoungsun Kim, Sungjoon Park, Jeonghyeon Cho, H. Song
{"title":"On-Dual In-line Memory Module (DIMM) Low-Pass Filter (LPF) using Via Stubs for Enhancing Signal Integrity","authors":"Seungjin Lee, Jonghoon J. Kim, Jinseong Yun, Hee-Jea Cho, Youngho Lee, Kyoungsun Kim, Sungjoon Park, Jeonghyeon Cho, H. Song","doi":"10.1109/EPEPS53828.2022.9947177","DOIUrl":"https://doi.org/10.1109/EPEPS53828.2022.9947177","url":null,"abstract":"A novel on-dual in-line memory module (on-DIMM) low-pass filter (LPF) using via stubs is proposed to enhance signal integrity. Proposed on-DIMM LPF implemented with existing via stubs not only eliminates the via stub effects, but also enhances the signal quality due to its low-pass characteristics without additional manufacturing processes and costs. For verification, both time- and frequency-domain simulation results of proposed DQ signal line with on-DIMM LPF are shown and compared with conventional DQ signal line. Proposed on-DIMM LPF exhibits 0.67 dB improvements at 2.8 GHz (nyquist frequency of 5.6 Gbps) shows relatively flat and improved insertion loss. Simulated eye height is improved for 29 mV and 20 mV and eye width is improved for 4.2 ps (0.02 UI) and 3.6 ps (0.02 UI) respectively at 4.8 Gbps and 5.6 Gbps. Finally, measurements verification with test board of on-DIMM LPF is also conducted and shows improvements in insertion loss and eye diagram","PeriodicalId":284818,"journal":{"name":"2022 IEEE 31st Conference on Electrical Performance of Electronic Packaging and Systems (EPEPS)","volume":"146 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124411101","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}