December 09, 2005
Sun Microsystems claims that it has achieved a record-breaking data warehousing performance TPC-H SF10000 benchmark result with the Sun Fire E25K UltraSPARC IV+ system and the Oracle Database 10g Release 2, outperforming recent benchmark results from HP and IBM. Sun also claimed a record-breaking performance SPECjbb2005 benchmark result with the Sun Fire E6900 UltraSPARC IV+ system which eclipsed newly announced SPECjbb2005 result from IBM based on a comparably priced Power5 system. Sun achieved a SPECjbb2005 result of 248,075 business operations per second (bops), which beats the performance of the POWER5 IBM eServer p5 570 16-way SPECjbb2005 result of 244,361 bops.
The Sun Fire E25K system's record surpassed a HP Integrity Superdome cluster by 25 percent, and an IBM POWER5-based cluster by over 4 percent on the TPC-H 10 terabyte benchmark. The 72-way 1.5 Ghz UltraSPARC IV+ processor-based Sun Fire E25K system with 108 Sun StorEdge SE3510 arrays running the industry-leading Solaris 10 Operating System (OS) and Oracle Database 10g Release 2 resulted in 108,099.7 QphH@10000GB, at a price-performance ratio of $53.80/QphH@10000GB (OK - mbp), with the TPC-H SF10000 benchmark.
With Solaris 10, Sun's multi-platform, open source OS, and new Sun Studio 11 software compilers, the E25K is optimized for performance and throughput maximization. The system was able to deliver 20 GB/sec of I/O bandwidth.
The Transaction Processing Performance Council's (TPC) TPC-H benchmark measures systems' capability to examine large volumes of data, execute queries with a high degree of complexity, and give answers to critical business questions. TPC-H evaluates a composite performance metric (QphH@size) and a price/performance metric ($/QphH@size) that measure the performance of various decision support systems by the execution of sets of queries against a standard database under controlled conditions.
SPECjbb2005 (Java Business Benchmark) measures the performance of a Java implemented application tier (server-side Java) based on the order processing in a wholesale supplier application. It also measures the performance of CPUs, caches, memory hierarchy and the scalability of shared memory processors (SMPs). The metrics given are number of bops (business operations per second) and bops/Java Virtual Machine.
10/30/2013 | Cray, DDN, Mellanox, NetApp, ScaleMP, Supermicro, Xyratex | Creating data is easy… the challenge is getting it to the right place to make use of it. This paper discusses fresh solutions that can directly increase I/O efficiency, and the applications of these solutions to current, and new technology infrastructures.
10/01/2013 | IBM | A new trend is developing in the HPC space that is also affecting enterprise computing productivity with the arrival of “ultra-dense” hyper-scale servers.
Ken Claffey, SVP and General Manager at Xyratex, presents ClusterStor at the Vendor Showdown at ISC13 in Leipzig, Germany.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?