Google just announced the general availability of Preemptible VMs for Compute Engine and that Cycle Computing's full suite of products now work on it (including the use of Preemptible VMs).
Google launched Preemptible VMs in beta back in May. Since then, Google says many big and small customers in areas as diverse as genomics and pharmaceuticals, financial modeling and simulation, rendering, media transcoding, manufacturing design, big data, and web crawling used them to save money.
"Cycle Computing has deep, industry-leading expertise in managing and scaling large compute workloads; we’re thrilled to welcome them to the Google Cloud Platform ecosystem," says Google Compute Engine Senior Product Manager Paul Nash.
"Cycle Computing recently ran a 50,000+ core workload for the Broad Institute using CycleCloud with Preemptible VMs, performing three decades of cancer research computations in an afternoon," he adds. "Over the past decade, the Broad Institute has collected and either sequenced or genotyped the equivalent of more than 1.4 million biological samples. They’re a pioneer in genomics research to benefit human health, and we’re very happy that our products are furthering this important mission. This new data suite is designed to be affordably re-run as new experimental data becomes available, and Preemptible VMs enable that affordability and flexibility."
You can find the documentation for Preemptible VMs here.
Last week, Google made Compute Engine Autoscaler generally available in addition to 32-core VMs. More on that here.
Image via Google