Open source licensing for Altair’s market-leading HPC workload manager, PBS Professional, is now available. PBS Pro development communities are now forming and the full-core open source version of PBS Pro can be downloaded at www.pbspro.org. “Our intent is to continuously push the boundaries of HPC to pursue exascale computing through active participation with the HPC community,” says James R. Scapa, Altair’s Founder, Chairman, and CEO. “Working together toward common goals will allow for resources to be applied more efficiently. Our dual-licensing platform will encourage public and private sector collaboration to advance globally relevant topics including Big Data, cloud computing, advanced manufacturing, energy, life sciences, and the inexorable move toward a connected world through the Internet of Things.”
“The SUSE and Intel collaboration on Intel HPC Orchestrator and OpenHPC puts this power within reach of a whole new range of industries and enterprises that need data-driven insights to compete and advance. This is an industry-changing approach that will rapidly accelerate HPC innovation and advance the state of the art in a way that creates real-world benefits for our customers and partners.”
In this video from the PASC16 conference, Andrew Lumsdaine from Indiana University presents: Context Matters: Distributed Graph Algorithms and Runtime Systems. “The increasing complexity of the software/hardware stack of modern supercomputers makes understanding the performance of the modern massive-scale codes difficult. Distributed graph algorithms (DGAs) are at the forefront of that complexity, pushing the envelope with their massive irregularity and data dependency. We analyze the existing body of research on DGAs to assess how technical contributions are linked to experimental performance results in the field. We distinguish algorithm-level contributions related to graph problems from “runtime-level” concerns related to communication, scheduling, and other low-level features necessary to make distributed algorithms work. We show that the runtime is an integral part of DGAs’ experimental results, but it is often ignored by the authors in favor of algorithm-level contributions.”
“Tasks keep the CPUs busy. When a core is working, rather than waiting for work to be sent to it, the application progresses towards it conclusion. A caveat to all of this is to remember that tasking and threading models remain on the system it was created on. Tasks that use a shared memory space only work within the shared memory segment that the processing cores can get to. Shared memory on the CPU side of the system is separate from the shared memory on the coprocessor. The threads created will remain on the part of the system where it started.”
In this video from ISC 2016, Barry Davis from Intel describes the company’s brand new Intel Xeon Phi Processor and how it fits into the Intel Scalable System Framework. “Eliminate node bottlenecks, simplify your code modernization and build on a power-efficient architecture with the Intel Xeon Phi™ processor, a foundational element of Intel Scalable System Framework. The bootable host processor offers an integrated architecture for powerful, highly parallel performance that will pave your path to deeper insight, innovation and impact for today’s most-demanding High Performance Computing applications, including Machine Learning. Supported by a comprehensive technology roadmap and robust ecosystem, the Intel Xeon Phi processor is a future-ready solution that maximizes your return on investment by using open standards code that are flexible, portable and reusable.”
The SGI Management Suite’s system health monitoring and management capability collects health status information on fundamental system’s functions such as memory, CPU and power. It identifies changes that require action, automatically alerts the system administrator, and provides proactive solutions to correct the problem.
In this video from ISC 2016, Figen Ulgen from Intel describes the new Intel HPC Orchestrator. “Intel HPC Orchestrator simplifies the installation, management and ongoing maintenance of a high-performance computing system by reducing the amount of integration and validation effort required for the HPC system software stack. Intel HPC Orchestrator can help accelerate your time to results and value in your HPC initiatives. With Intel HPC Orchestrator, based on the OpenHPC system software stack, you can take advantage of the innovation driven by the open source community – while also getting peace of mind from Intel support across the stack.”
Today Allinea Software announced that the Joint Center for Advanced High Performance Computing (JCAHPC) in Japan will use the Allinea DDT debugger for its new supercomputer. Coming online in December 2016, the new supercomputer, known as Oakforest-PACS, will be the fastest supercomputer system in Japan with 25 PFLOPS on Intel’s Xeon Phi (Knights Landing) manycore processors and the Omni-Path architecture.
In this video from ISC 2016, Dr. Eng Lim Goh from SGI discusses the latest trends in high performance data analytics and machine learning. “Dr. Eng Lim Goh joined SGI in 1989, becoming a chief engineer in 1998 and then chief technology officer in 2000. He oversees technical computing programs with the goal to develop the next generation computer architecture for the new many-core era. His current research interest is in the progression from data intensive computing to analytics, machine learning, artificial specific to general intelligence and autonomous systems. Since joining SGI, he has continued his studies in human perception for user interfaces and virtual and augmented reality.”
FrostByte is a complete solution that integrates Penguin Computing’s new Scyld FrostByte software with an optimized high-performance storage platform. FrostByte will support multiple open software storage technologies including Lustre, Ceph, GlusterFS and Swift, and will first be available with Intel Enterprise Edition for Lustre. The entry-level FrostByte is a single rack with 500TB of highly available storage that can deliver up to 18GB/s and 500K/s metadata ops/s over Intel Omni-Path, Mellanox EDR InfiniBand or Penguin Arctica 100GbE network solutions. A single FrostByte “Scalable Unit” can deliver up to 15PB and greater than 500GB/s in 5 racks. Multiple Scalable Units can be combined to scale up to 100s of petabytes and 10s of terabytes/sec of aggregate storage bandwidth.