Research of Large Practical LAN Based on Interconnection Technology

In this paper we will introduce a large practical LAN using the technologies such as Netware bridge server, net structure segment, and TCP/IP etc. The net can provide a network develop circumstance with large communication bandwidth and strong function. The telecommunication interconnection among the over 350 heterogeneous machines and the heterogeneous operation svstem had benn realized.

The 8×10 GHz Receiver Optical Subassembly Based on Silica Hybrid Integration Technology for Data Center Interconnection

An 8×10 GHz receiver optical sub-assembly （ROSA） consisting of an 8-channel arrayed waveguide grating （AWG） and an 8-channel PIN photodetector （PD） array is designed and fabricated based on silica hybrid integration technology. Multimode output waveguides in the silica AWG with 2% refractive index difference are used to obtain fiat-top spectra. The output waveguide facet is polished to 45° bevel to change the light propagation direction into the mesa-type PIN PD, which simplifies the packaging process. The experimentM results show that the single channel I dB bandwidth of AWG ranges from 2.12nm to 3.06nm, the ROSA responsivity ranges from 0.097 A/W to 0.158A/W, and the 3dB bandwidth is up to 11 GHz. It is promising to be applied in the eight-lane WDM transmission system in data center interconnection.

A Single Mode Hybrid Ⅲ-Ⅴ/Silicon On-Chip Laser Based on Flip-Chip Bonding Technology for Optical Interconnection

A single mode hybrid Ⅲ-Ⅴ/silicon on-chip laser based on the flip-chip bonding technology for on-chip optical interconnection is demonstrated. A single mode Fabry-Perot laser structure with micro-structures on an InP ridge waveguide is designed and fabricated on an InP/AIGaInAs multiple quantum well epitaxial layer structure wafer by using i-line lithography. Then, a silicon waveguide platform including a laser mounting stage is designed and fabricated on a silicon-on-insulator substrate. The single mode laser is flip-chip bonded on the laser mounting stage. The lasing light is butt-coupling to the silicon waveguide. The laser power output from a silicon waveguide is 1.3roW, and the threshold is 37mA at room temperature and continuous wave operation.

High Performance MPI over the Slingshot Interconnect

The Slingshot interconnect designed by HPE/Cray is becoming more relevant in high-performance computing with its deployment on the upcoming exascale systems.In particular,it is the interconnect empowering the first exascale and highest-ranked supercomputer in the world,Frontier.It offers various features such as adaptive routing,congestion control,and isolated workloads.The deployment of newer interconnects sparks interest related to performance,scalability,and any potential bottlenecks as they are critical elements contributing to the scalability across nodes on these systems.In this paper,we delve into the challenges the Slingshot interconnect poses with current state-of-the-art MPI(message passing interface)libraries.In particular,we look at the scalability performance when using Slingshot across nodes.We present a comprehensive evaluation using various MPI and communication libraries including Cray MPICH,Open-MPI+UCX,RCCL,and MVAPICH2 on CPUs and GPUs on the Spock system,an early access cluster deployed with Slingshot-10,AMD MI100 GPUs and AMD Epyc Rome CPUs to emulate the Frontier system.We also evaluate preliminary CPU-based support of MPI libraries on the Slingshot-11 interconnect.