Koi Computers announces integrations with AMD Instinct MI100 GPUs for AI, Deep Learning
Koi Computers, one of the leading turnkey HPC server and cluster providers, just announced technology integrated with AMD’s newest AMD Instinct MI100 accelerator. The accelerator is the world’s fastest HPC GPU.
Powered by the first AMD CDNA architecture, the MI100 accelerators deliver a giant leap in compute and interconnect performance, offering a nearly 3.5x boost for HPC (FP32 Matrix) performance and a nearly 7x boost for AI throughput (FP16) performance compared to AMD’s prior generation accelerators. Features and benefits include:
- All-new AMD CDNA architecture delivering as much as 74% higher FP64 performance to accelerate HPC workloads when compared with AMD prior gen
- All-new Matrix Core Technology delivering a giant leap in AI matrix performance with FP32 and FP16–introducing new bFloat16 operations
- 2nd Generation Infinity Architecture bringing advanced platform connectivity and scalability
- Enhanced HBM2 memory interface with about 20% more theoretical memory throughput and improved latencies vs. AMD’s prior gen accelerators
- Enhanced RAS and security capabilities
- AMD ROCm open software ecosystem
MI100 accelerators offer an open environment that does not lock users into a vendor-specific solution, enabling developers to enhance existing GPU codes to run everywhere. Combined with the powerful 2nd Gen AMD EPYC processors and AMD Infinity Fabric technology, MI100-powered systems provide scientists and researchers with extremely powerful platforms.
Koi Computers fully leverages the AMD MI100 with expertly engineered servers and clusters that are fully customized to accommodate current and projected client needs. The company’s Federal Business Development Manager Catherine Ho said, “This is the latest in AMD’s incredible run of powerful products that bring new capabilities to HPC. These products tend to fill gaps in the HPC market and create game-changing opportunities for our clients that no one could imagine before.” To learn more visit: https://koicomputers.com/amd-mi100/.
About Koi Computers
Headquartered in Greater Chicago since 1995, Koi Computers has been working with top technology manufacturers to deliver scalable high performance computing and technology solutions that improve efficiency, reliability and speed. The company’s world-class engineering team specializes in building custom IT solutions that accommodate today’s needs and tomorrow’s vision with services that include performance benchmarking and outstanding support. Koi Computers has a strong track record of developing, building and deploying HPC technology for the U.S. Federal Government with satisfactory ratings in CPARS and Past Performance. The company is a Prime Contract Holder of the GSA IT Schedule 70, NASA SEWP V, and NITAAC CIO-CS contracts.