Keeping up with High Performance Computing’s ever-expanding horizon, with a chance of clouds. ☁️
engineering.com | How Can High Performance Computing Supercharge Manufacturing?
Using CFD to iterate rapidly on F1 designs, bringing greater R&D velocity and flexibility.
flant.com | Comparing Ceph, LINSTOR, Mayastor, and Vitastor storage performance in Kubernetes
Great mix of I/O patterns and client counts for benchmarking.
Thanks @Learnk8s for sharing!
Tesla has seventh largest GPU supercomputer in the world, employee claims
We [Tesla] have recently upgraded our GPU supercomputer to 7,360 A-100(80GB) GPUs, making it Top-7 by GPU-count. – Tim Zaman, AI and Autopilot lead. https://twitter.com/tim_zaman/status/1558201191342870528
CDK for Terraform Is Now Generally Available
Cloud Development Kit for Terraform enables infrastructure as code using programming languages rather than a configuration language.
Typescript, Python, Java, Go, C# can be used to describe your Cloud infrastructure
OpenCAPI to Be Folded into CXL
- CXL.io enhances PCIe5 for devices to better connect
- CXL.cache enables devices to cache main memory
- CXL.mem allows coherent memory access
That last one is juicy, should consolidate many coherent memory technologies: NVLink, AMD InfinityFabric, IBM OpenCAPI…
More by Joe Heaton at @Heaton_dev & LinkedIn