The HPC industry is ever facing more and more challenges on various topics and especially a significant increase in cooling requirements. To meet those requirements, liquid cooling looks like the solution. But there is an alternative cooling solution that works without a pump and without water.
Getting started with HPC can be a challenge for SMEs, but managing a cluster doesn’t have to be a struggle. IBM’s Platform Computing group has been helping users to stand up and run clusters efficiently for years. Now, with the recently announced IBM Platform LSF Suites for Workgroups and HPC, the company has made it easier than ever to get kick the tires on High Performance Computing. “So basically, we would give you all the tools that would allow you to easily migrate from a loose collection of work stations to a small cluster environment. And we would handle the bare metal provisioning and then installing the software that you need really to manage your workload.”
The OpenPOWER Foundation is pleased to announce the first OpenPOWER Europe Summit taking place on June 16-17 in Frankfurt.
In this video from the 2016 GPU Technology Conference, Jaan Mannik from One Stop Systems describes the GPUltima system. Delivering up to 1 Petaflop in a rack, the GPUltima is a single 19″ rack comprised of 8 OSS High Density Compute Accelerators (HDCA) each with 16 NIVIDA Dual GPUs (128 total), 16 dual-socket servers, an Infiniband Switch and an Ethernet Switch.”
Through the microarchitecture improvements, increased core counts, and faster memory speeds of the new Intel Xeon processor E5-2600 v4 product family based on the “Broadwell” microarchitecture, you can increase your HPC application performance. You will see significantly improved per-core performance with these just announced Intel® Xeon® processors that can then be multiplied by parallel programs that utilize the number of cores available inside these processors. Improvements to the memory and virtual memory capabilities – including the ability to utilize faster DDR4-2400 memory – means that these processors can speed all aspects of your application from IO DMA operations, to processing serial sections of code, as well as delivering increased performance on both task- and data-parallel applications.
Expected later in 2016, Intel will be releasing production versions of its Knights Landing (KNL) 72-core coprocessor. These next generation coprocessors are impacting the physical design of the supercomputers now coming down the pike in a number of ways. One of the most dramatic changes is the significant increase in cooling requirements – these are high wattage chips that run very hot and present some interesting engineering challenges for systems designers.
Even though it’s a new generation fabric, Intel OPA is still backwards compatible with the many applications in the HPC community that were written using the OpenFabrics Alliance* software stack for InfiniBand. So, existing InfiniBand users will be able to run their codes that are based on the OpenFabrics Enterprise Distribution (OFED) software on Intel OPA. Additionally, Intel has open sourced the key software elements of their fabric to allow integration of Intel OPA into the OFED stack, which several Linux* distributions include in their packages.
In this week’s Sponsored Post, Katie Garrison of One Stop Systems explains how Flash storage arrays are becoming more accessible as the economics of Flash becomes more attractive. “Comprised of a unique combination of a Haswell-based engine and 200TB Flash arrays, the FSA-SAN can be increased to a petabyte of storage with additional Flash arrays. Each 200TB array delivers 16 million IOPS, making it the ideal platform for high-speed data recording and processing with lightning fast data response time, high-availability and flexibility in the cloud.”
In this video, Bill Wagner of Bright Computing describes what attracted him to join the company as CEO and what’s ahead for system management software. “Bright addresses the exploding demand to manage increasingly complex IT infrastructures with a simple yet powerful ‘single pane of glass’ management platform that can extend across the datacenter and the cloud. I am excited to join Bright’s talented team and eager to build on the company’s upward growth trajectory.”
The Integrative Model for Parallelism at TACC is a new development in parallel programming. It allows for high level expression of parallel algorithms, giving efficient execution in multiple parallelism modes. We caught up with its creator, Victor Eijkhout, to learn more. “If you realize that both task dependencies and messages are really the dependency arcs in a dataflow formulation, you now have an intermediate representation, automatically derived, that can be interpreted in multiple parallelism modes.”