[1] |
de Sensi D, di Girolamo S, McMahon K H, et al.An in-depth analysis of the slingshot interconnect[C]∥Proc of the International Conference for High Performance Computing Networking,2020:1-13.
|
[2] |
Kim J, Dally W J,Towles B,et al.Microarchitecture of a high-radix router[J].Computer Architecture News,2005,33(2):420-431.
|
[3] |
Scott S,Abts D,Kim J,et al.The BlackWidow high-radix clos network[C]∥Proc of the
|
33 |
rd International Symposium on Computer Architecture,2006:16-28.
|
[4] |
Dai Y,Lu K,Xiao L Q,et al.A cost-efficient router architecture for HPC interconnection networks:Design and implementation[J].IEEE Transactions on Parallel & Distributed Systems,
|
20 |
19,30(4):738-753.
|
[5] |
Moore G E.Cramming more components onto integrated circuits[J].IEEE Solid-State Circuits Society News Letter,2006,11(3):33-35.
|
[6] |
Dennard R H,Gaensslen F H,Yu H N,et al.Design of ion-implanted MOSFET’s with very small physical dimensions[J].IEEE Journal of Solid-State Circuits, 1974,9(5):256-268.
|
[7] |
Durant L, Giroux O, Harris M, et al.Inside Volta:The world’s most advanced data center GPU[EB/OL].[2021-01-16].https://devblogs.nvidia.com/parallelforall/inside-volta.
|
[8] |
Arunkumar A, Bolotin E, Cho B, et al.MCM-GPU:Multi-chip-module GPUs for continued performance scalability[C]∥Proc of
|
20 |
17 ACM/IEEE 44th Annual International Symposium on Computer Architecture,2017:320-332.
|
[9] |
Marvell Corporation.MoChi architecture[EB/OL].[2021-02-10].http://www.marvell.com/architecture/mochi/.
|
[10] |
Green D. Common heterogeneous integration and IP reuse strategies (CHIPS)[EB/OL].[2021-02-10].https://www.darpa.mil/program/common-heterogeneous-integration-and-ip-reuse-strategies.
|
[11] |
Li T, Hou J, Yan J L, et al. Chiplet heterogeneous integration technology—Status and challenges[J].Electronics,2020,9(4):670.
|
[12] |
The 50 Gbps si photonics link[EB/OL].[2010-06-08].http:∥www.intel.com/.
|
[13] |
Kim J.High-radix interconnection networks[D].Palo Alto:Stanford University,2008.
|
[14] |
Ahn J H,Choo S,Kim J D.Network within a network approach to create a scalable high-radix router microarchitecture[C]∥Proc of the 18th IEEE International Symposium on High Performance Computer Architecture,2012:455-466.
|
[15] |
Intel Tofino2 next-gen programmable switch detailed[EB/OL].[2010-10-10].https://www.servethehome.com/intel-tofino2-next-gen-programmable-switch-detailed/.
|
[16] |
Berkeley Architecture Research.Tilelink[EB/OL].[2010-10-10].https://bar.eecs.berkeley.edu/projects/tilelink.html.
|
[17] |
AMD.AMD previews EPYC rome processor:Up to 64 Zen 2 cores[EB/OL].[2010-10-10].https://www.anandtech.com/show/13561/amd-previews-epyc-rome-processor-up-to-64-zen-2-cores.
|
[18] |
Intel. Overview of heterogeneous integration[EB/OL].[2010-10-10].https://www.intel.com/content/www/us/en/architecture-and-technology/programmable/heterogeneous-integration/overview.html.
|
[19] |
Lin M S,Huang T C,Tsai C C,et al.A 7 nm 4 GHz Arm-core-based CoWoSR Chiplet design for high performance computing[C]∥Proc of the 2019 Symposium on VLSI Circuits,
|
20 |
19:C28-C29.
|