“Intel provided a wealth of machine learning announcements following the Intel Xeon Phi processor (formerly known as Knights Landing) announcement at ISC’16. Building upon the various technologies in Intel Scalable System Framework, the machine learning community can expect up to 38% better scaling over GPU-accelerated machine learning and an up to 50x speedup when using 128 Intel Xeon Phi nodes compared to a single Intel Xeon Phi node. The company also announced an up to 30x improvement in inference performance (also known as scoring or prediction) on the Intel Xeon E5 product family due to an optimized Intel Caffe plus Intel Math Kernel Library (Intel® MKL) package.”
Organizations that implement high-performance computing technologies have a wide range of requirements. From small manufacturing suppliers to national research institutions, using significant computing technologies is critical to creating innovative products and leading-edge research. No two HPC installations are the same. “For maximum return, budget, software requirements, performance and customization all must be considered before installing and operating a successful environment.”
Organizations that implement high-performance computing (HPC) technologies have a wide range of requirements. From small manufacturing suppliers to national research institutions, using significant computing technologies is critical to creating innovative products and leading-edge research. No two HPC installations are the same. “For maximum return, budget, software requirements, performance and customization all must be considered before installing and operating a successful environment.”
While all users of HPC technology want the fastest performance available, price and power consumption always seem to come into play, whether in the initial planning or at a later time. Standard performance measures exist that may or may not relate to an end user’s application mix, but it is important to understand the various benchmark results that go into determining the performance of a CPU, a server or an overall cluster.
Today Univa announced the general availably of its Grid Engine 8.4.0 product. Enterprises can now automatically dispatch and run jobs in Docker containers, from a user specified Docker image, on a Univa Grid Engine cluster. This significant update simplifies running complex applications in a Grid Engine cluster and reduces configuration and OS issues. Grid Engine 8.4.0 isolates user applications into their own container, avoiding conflict with other jobs on the system and enables legacy applications in Docker containers and non-container applications to run in the same cluster.
Today Supermicro announced its extensive support for the new Intel Xeon processor E5-2600 v4 product family across SuperServer, SuperBlade, SuperStorage, SuperWorkstation and DP/UP motherboard product lines. Over 200+ Building Block Solutions take maximum advantage of the increased compute performance offered by Intel’s new processor technologies.
Total, one of the largest integrated oil and gas companies in the world, announced they are boosting the compute power of their SGI Pangea supercomputer with an additional 4.4 petaflops provided by a new SGI ICE X system and based on the Intel Xeon processor. Purchased last year, the new SGI system is now in production and will allow Total to determine the optimal extraction methods more quickly. The SGI supercomputer allows Total to improve complex modeling of the subsurface and to simulate the behavior of reservoirs, reducing the time and costs associated with discovering and extracting energy reserves.
Matrix multiplies can be decomposed into tiles and executed very fast on the latest generations of coprocessors. Intel has developed the hStreams library that supports task concurrency on heterogeneous platforms. The concurrency may be across nodes (Xeon, KNC, KNL-SB, KNL-LB); within a node for small matrix operations; and in the overlapping of computation and communication, particularly for tiled solutions. It relieves the user of complexity in dealing with thread affinitization, offloading, memory types, and memory affinitization.
“What we’re showcasing this year is – what we’re jokingly calling – face-melting performance. What we’re trying to do is make extreme performance available at a very aggressive price point, and at a very aggressive space point, for end users. So, what we’ve been doing and what we’ve been working on for the past couple of months has been, basically, building an NVMe-type unit. This NVMe unit connects flash devices through a PCIe interface to the processor complex.”
Bull Atos has installed the fastest supercomputer in Croatia at the University in Rijeka. With an expected debut on the TOP500 in November, the 239 Teraflop BURA supercomputer will be used by university researchers in areas including drug discovery and genomics.