User:Approinc/sandbox

Appro was a leading developer of supercomputing solutions supporting High Performance Computing (HPC) markets focused on medium to large-scale deployments where lower total cost of ownership is essential. Appro accelerated technical applications and business results through outstanding price/performance, power efficient and fast time-to-market solutions based on the latest open standards, technologies, innovative cluster tools and management software packaged with HPC professional services and support. Appro was based in Milpitas, California with an advanced computing center in Houston, Texas, and a manufacturing and support subsidiary in Korea and Japan.

Company History
Appro was founded in 1991 by President and CEO Daniel Kim. Mr. Kim expanded the company in the US market as OEM high performance rackmount computer systems manufacturer. Appro quickly became one of the fastest growing rackmount computer companies. For the first time in 2002, Appro produced and marketed its own line of branded high-density servers for the high-performance and Internet computing markets in a transition from OEM to Appro branded products. In 2005, Appro expanded manufacturing, engineering and product development teams in South Korea and introduced its first blade cluster, the Appro HyperBlade Server Cluster Solution and the Appro 1142H, the first 1U 4-processor server available to the HPC market.

In 2006, Appro launched its first flagship product, the Xtreme-X™ Supercomputer based on x86 processors. The system combines high performance and high availability in a balanced architecture ideal for scaling out data centers from medium to large-sized systems. The supercomputer features the Appro Cluster Engine™ (ACE) Management Software, a complete lights-out remote management system. Appro wins several prominent awards with the new supercomputer including the TLCC07 Project for the NNSA and The Peloton project for Lawrence Livermore National Laboratories.

In 2008 and 2009, Appro announced the Appro HyperPower™ Cluster Solution, a hybrid CPU/GPU computing based on NVIDIA Tesla™ and NVIDIA® Cuda software technology and including professional services and cluster management options. Appro also launched the Appro GreenBlade™ System, a solution building block with a modular and energy-efficient architecture to respond to the growth of small and medium HPC deployments as well as addressing challenges with performance-optimized and power-efficient solutions.

Appro revealed the next generation Xtreme-X™ Supercomputer in 2011. The system featured the latest processing and accelerator technologies, increased performance/watt, multiple high performance network connectivity, I/O and disk options along with specialized professional services. The system addressed four critical HPC workloads: capacity, hybrid, data intensive, and capability computing. The reinvented system won several major supercomputing contracts for customers such as San Diego Supercomputer Center, Lockheed Martin, US Department of Energy, University of Tsukuba, and Lawrence Livermore, Sandia, Los Alamos National Laboratories.

On November 9, 2012, Cray Inc. announced plans to acquire Appro for $21.8 million to strengthen the company's HPC cluster system offerings. On November 21, 2012 Cray announced it had completed the acquisition of Appro International, Inc.

Customers and Supercomputing Projects

 * National Oceanic and Atmospheric Administration (NOAA) - 113TF supercomputer for NOAA's Hurricane Forecast Improvement Project (HFIP) (2012)
 * Virginia Tech, Advanced Research Computing (ARC) - Blue-Ridge Supercomputer (2011) featuring Intel Xeon Phi coprocessors
 * Kyoto University - 210TF supercomputer (2011) for the Academic Center for Computing and Media Studies (ACCMS) at Kyoto University
 * San Diego Supercomputer Center (SDSC) - 35M IOPS Gordon Supercomputer (2011), 100TF Trestles (2010), and DASH (2009).
 * TLCC Projects for the NNSA - Tri-lab Linux Capacity Cluster: TLCC2 (2011) and TLCC07 (2007) at Lawrence Livermore, Sandia, and Los Alamos National Laboratories
 * Los Alamos National Laboratory - 353TF Mustang supercomputer (2011)
 * University of Tsukuba - 802TF HA-PACS supercomputer (2011) and 95TF supercomputer (2009) at the Center for Computational Sciences
 * Lockheed Martin - 147.5TF Supercomputer in support of the DoD High Performance Computing Modernization Program (HPCMP)
 * Sandia National Laboratory - First of a Kind Intel MIC Testbed Experimental Cluster (2011)
 * Idaho National Laboratory - Fission supercomputer (2011)
 * Lawrence Livermore National Laboratory - Hyperion Project (2010), 110TF Graph supercomputer (2009) and 222TF Peloton Project consisting of Rhea, Zeus, Minos and Atlas Clusters (2007)
 * Renault Formula 1 Team - 38TF supercomputer delivered to the Computational Fluid Dynamics Center in the UK (2009)

Product Portfolio
Xtreme-X Supercomputer - The Appro Xtreme-X™ was an energy efficient, air-cooled architecture for high performance and high availability computing. It features optional 480V power distribution and a choice of 208V or 277V 3-phase power supplies to significantly reduce energy costs. It offers flexible configuration options for a wide range of data center cooling architecture requirements through the use of chilled cooling rear door heat exchangers. The Appro Xtreme-X™ is tightly integrated with the Appro HPC Software Stack providing supported and necessary software tools that is compatible with most open source and commercial compilers, tools, schedules, and libraries to run complex applications. The system is integrated with the Appro Cluster Engine™ (ACE), essential management software suite designed to eliminate the complexity of managing HPC clusters offering server, cluster, storage, and network management features combined with node provisioning, failover, load-balancing, job scheduling and revision control capabilities with multi-Linux OS support.

Xtreme-Cool Supercomputer - The Appro Xtreme-Cool™ delivered superior energy savings, lower TCO and faster ROI by requiring fewer or no air conditioning units in the data center. It uses warm water liquid-cooling heat exchangers with no chillers reducing typical energy consumption used to cool the data center by 50% while dropping PUE lower than 1.1. The Appro Xtreme-Cool offers high performance and three times more energy efficiency per rack versus traditional air-cooled designs. It also produces 80% heat capture to the warm water for possible heat reuse.

Appro Cluster Engine (ACE) Management Software - Appro Cluster Engine™ (ACE) management software provided a complete Network, Server, Cluster, and Storage Management software suite featuring node provisioning, power and temperature monitoring with rollback, failover and revision control capabilities. It also provides robust network boot, diskless nodes, multi-OS support for heterogeneous nodes and logical clusters. ACE is built on industry leading management software including job schedulers such as Grid Engine, SLURM and PBS Pro and is compatible with most open source and commercial compilers, tools, schedulers, and libraries.

GreenBlade System - The Appro GreenBlade™ system was an energy efficient, air-cooled, modular, component building block platform designed for HPC environments that consolidates server, storage, power and simplified management capabilities while providing performance, reliability, density and upgradeability. The GreenBlade™ Subrack SR5110 model features hot-swappable and redundant cooling fans, power supplies, and blade nodes and is integrated with four high-efficient power supplies with an option for 480V power distribution based on 208V or 277V 3-phase for further energy savings. It features new mixed-flow fans providing noise reduction. The system houses up to 10 blade servers offering a total of 20 processors in a 5U form factor. The system configurations can be coupled with the NVIDIA® Tesla GPU computing accelerator or Intel® Xeon Phi™ coprocessor expansion blades.

Awards and Honors

 * HPCwire Editors' Choice Award 2012 - Appro Xtreme-X Supercomputer was awarded "Best HPC Cluster Solution" and "Best HPC Storage Product or Technology" for the collaborative project with SDSC for its Data Oasis Storage System running on the Gordon Supercomputer.
 * Appro Ranked #1 on the November 2012 Green500 List - Beacon Supercomputer for the National Institute for Computational Sciences at the University of Tennessee
 * Top500 November 2012 - Appro was ranked #4 vendor on the Top500 list with 24 supercomputers making the list, with the highest ranking system, the Zin supercomputer at Lawrence Livermore National Laboratory, at #29.
 * 2012 Intel Solution Summit - Datacenter Solution Innovation Award Winner for Appro GreenBlade and Xtreme-X Supercomputer
 * HPCwire Reader and Editor Choice 2011 - Editor's Choice for "Top 5 Vendors to Watch" and "Best HPC Server Product or Technology" for Appro Xtreme-X Supercomputer.