It’s becoming clearer every day that the world is racing towards a state of constant, insatiable need for more and more computing power to make sense of the growing sea of data all around us – and we’ve barely scratched the surface. Just wait until IoT and machine learning kick into high gear. Not surprisingly, Linux clusters – in various evolving forms – continue to be the preferred approach for providing the computing horsepower to tackle these jobs, yet Linux clusters are notoriously complex and difficult to manage. For this reason, Bright Computing commissioned a market survey through Hyperion Research to understand how organizations are grappling with the challenges of Linux clusters in the face of growing demand.Read More >
I recently completed my third year as the CEO of Bright Computing, and it seems that a day doesn’t go by without me discovering some new (to me) capability within our product, Bright Cluster Manager. With more than a decade of development and customer implementations under its belt, coupled with a product team of 40 people working on the product every day, it’s obviously hard to keep up with everything this product can do. But while the product has grown in capability, it has remained true to its reputation for being easy to use.Read More >
At the 2019 GPU Technology Conference in March, NVIDIA Founder & CEO Jensen Huang positioned NVIDIA DGX servers at the intersection of scale-up and scale-out architectures, sitting squarely in the sweet spot of data science driven by the combination of increased concurrency of data science workloads and the massive compute requirements associated with those workloads. As a standalone server, the DGX delivers a solid scale-up architecture for data/compute-intensive workloads, and NVIDIA’s announced acquisition of Mellanox with its high-speed interconnects will only enhance that position and help enable a new realm of scale-out architectures as well.Read More >
Picking up from last week, I illustrated a common dialogue between IT administrators and executive leadership concerning the decision to build an HPC cluster management solution. Now that the green light has been given to build, all of that money you “saved” by not using commercial cluster management software allowed you to buy more hardware to support jobs from end users, right? You can see the extra servers on the floor, so you must be providing your users with more capacity for work, right? Maybe not. Does the do-it-yourself approach you developed tell you precisely which system resources are actually being used by end users, and for which jobs? Or, are users requesting more resources for their jobs than they really need and sitting on them (unused), preventing other users from gaining access to do real work? And one more thing … how much server/system resource is being inefficiently consumed by the processes of your do-it-yourself cluster management solution at the expense of real work for users? The point is, that cluster that appears to be 95% utilized is very likely to be far less productive than you think.Read More >
The historical thinking behind building and maintaining your own HPC cluster management solution using open source tools goes something like this: “We have smart people that can build this. We have limited capital budget. Commercial cluster management software costs money, but open source tools like xCAT, Rocks, OpenHPC and others are free. If we build a solution ourselves using open source tools, we can use the savings to buy more hardware.”Read More >
While the world eagerly awaits the rollout of 5G networks and the exciting new apps for both consumers and businesses that will be made possible via 5G services, enterprises, telcos, hosting providers and others are scrambling to architect and build the computing infrastructure necessary to support the new requirements of these apps. Two key challenges in defining the computing infrastructure for 5G apps are that they will be data/compute intensive and have little tolerance for network latency. The former means that significant computing capacity is needed to deliver the intended experience of the app and the latter means that the compute must be located in relative proximity to the user of the app. The result: A significant build-out of localized compute (predominately Linux servers and clusters) will be required to service the new generation of 5G apps speeding towards us. But where (specifically) will that compute infrastructure reside?Read More >
Read More >
We were very excited at SC16 to announce that Bright Cluster Manager provides infrastructure management technology for Dell’s Blueprints program. The program includes a group of end-to-end solutions optimized and validated to meet Dell customers’ biggest challenges: big data, high performance computing, and leveraging the power and capabilities the cloud brings to businesses.