ExaNoDe: combined integration of chiplets on active interposer with bare dice in a multi-chip-module for heterogeneous and scalable high performance compute nodes
Pierre-Yves Martinez, Y. Beilliard, M. Godard, D. Danovitch, D. Drouin, J. Charbonnier, P. Coudrain, A. Garnier, D. Lattard, P. Vivet, S. Chéramy, E. Guthmuller, C. F. Tortolero, V. Mengue, J. Durupt, A. Philippe, D. Dutoit
{"title":"ExaNoDe: combined integration of chiplets on active interposer with bare dice in a multi-chip-module for heterogeneous and scalable high performance compute nodes","authors":"Pierre-Yves Martinez, Y. Beilliard, M. Godard, D. Danovitch, D. Drouin, J. Charbonnier, P. Coudrain, A. Garnier, D. Lattard, P. Vivet, S. Chéramy, E. Guthmuller, C. F. Tortolero, V. Mengue, J. Durupt, A. Philippe, D. Dutoit","doi":"10.1109/VLSITechnology18217.2020.9265100","DOIUrl":null,"url":null,"abstract":"In the context of high performance computing (HPC), energy efficiency and computing density are key for targeting exascale architectures. Close integration of chiplets, active interposer and field programmable gate arrays (FPGA) paves the way for dense, efficient and modular compute nodes. In this paper, we detail the ExaNoDe multi-chip-module (MCM) combining the integration of a substrate, an active interposer, some chiplets and bare dice. The reported MCM demonstrates that the multi-level integration flow enables tight integration of hardware accelerators in a heterogeneous HPC compute node.","PeriodicalId":6850,"journal":{"name":"2020 IEEE Symposium on VLSI Technology","volume":"44 1","pages":"1-2"},"PeriodicalIF":0.0000,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2020 IEEE Symposium on VLSI Technology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/VLSITechnology18217.2020.9265100","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7
Abstract
In the context of high performance computing (HPC), energy efficiency and computing density are key for targeting exascale architectures. Close integration of chiplets, active interposer and field programmable gate arrays (FPGA) paves the way for dense, efficient and modular compute nodes. In this paper, we detail the ExaNoDe multi-chip-module (MCM) combining the integration of a substrate, an active interposer, some chiplets and bare dice. The reported MCM demonstrates that the multi-level integration flow enables tight integration of hardware accelerators in a heterogeneous HPC compute node.