SC20 Inspur Virtual Showcase
Welcome to Inspur's SC 2020 virtual showcase. See advanced high performance computing solutions for next-generation applications in AI, deep learning and scientific computing.
Cutting-Edge High Performance Solutions for Next-Gen Applications.
Supercomputing is the premier international conference for High Performance Computing, Storage, Networking, and Analysis. Inspur, a global leader in AI and HPC computing solutions, will be at the virtual conference to showcase innovations that advance key technology trends to empower major industries.
The virtual exhibit hall is free to attend.
The most powerful Delivering extreme AI performance with the industry's most powerful A100 GPUs
Dynamic AI resource pooling with optimized software framework AIStation3.0 and ClusterEngine
Cutting-Edge Hardware Design and Software Management for AI and HPC
NF5488A5: Versatile AI System for All AI Workloads
Record-Setting AI Performance
Best single sever performance in MLPerf v0.7 benchmark, delivers 5 petaFLOPS and high data throughput
Extreme Hardware Design
8x fully interconnected NVLink 3.0 NVIDIA A100 GPUs, 2x AMD Rome processors enabling PCIe4.0 in 4U
Empowering AI Applications
Suitable for intelligent image, video and voice processing, financial analysis, virtual assistant
NF5488A5 AI Training & Inference Server
NF5488M5-D: Extreme Performance AI Server
Leading AI Performance
8x fully interconnected NVLink 3.0 NVIDIA A100 GPUs, 2x second-generation Intel® Xeon® scalable processors, HBM2e memory in 4U
Comprehensive Ecosystem Support
NVIDIA CUDA Delta system and Intel platform development ecosystems minimize business migration costs, enabling fast deployment
NF5488M5-D AI Server
AI Management Software
Unified management and scheduling of computing resources and a complete development software stack to accelerate AI application development.
Greater GPU Power
Supports the latest NVIDIA Ampere architecture and multi-instance GPU
AI Model Training
Speeds up model training tasks with autoscaling mechanism
Dynamic Resource Allocation
Flexible computing resources (CPU & GPU) management and allocation based on specific applications
Manages and optimizes the resource allocation and maintenance of large-scale clusters, supporting unified management of multiple HPC/AI workloads simultaneously.
Sharing and reproductivity of applications simplifies development and management cost savings
Cluster Performance Monitoring
Application performance analysis reveals runtime features, hotspots, and bottlenecks
Heterogeneous Resource Management
Compatibility with mainstream servers to accelerate multi-node parallel computing
WORKSHOPS & SESSIONS
Attend a virtual forum with leading international researchers and HPC experts.
The HPC Connection Workshop is an international High Performance Computing event organized by the Asia Supercomputer Community and Inspur Group, taking place three times a year: during ASC in China, ISC in Germany, and SC in the USA. Top researchers and leading professionals from around the world gather at the workshops to discuss the latest developments and disruptive technologies in AI and supercomputing.