Select a topic or year
ARMONK, N.Y. - 12 Aug 2011: IBM (NYSE: IBM) today announced that it has achieved the highest TPC-C benchmark performance score ever achieved for an x86 server.
The single rack non-clustered IBM System x® running DB2® achieved more than three million transactions per minute, which breaks the industry record set by the same IBM x86 system just eight months ago, and extends the performance advantage over a comparable HP® system by as much as 66 percent.
"Leveraging significant investments in x86 technology, IBM continues to push the envelop in terms of innovation, scalability and performance," said Alex Yost, vice president, IBM System x and BladeCenter systems. "At the end of the day, it's about the customer, about delivering highly scalable, cost-effective, energy-efficient solutions that help clients differentiate themselves in their chosen markets."
This achievement demonstrates the leadership performance possible with the combined power of IBM's exclusive 5th generation Enterprise X-Architecture®, DB2 9.7, IBM MAX5® on System x, and the lastest Intel® Xeon® E7 processors running SUSE Linux Enterprise Server 11 (SP1). IBM MAX5 on System x is an industry-first technology that decouples memory from the processor, enabling a 50 percent increase in memory capacity for a single server, which increases productivity and allows the system to process more transactions per minute.
The IBM System x3850 X5 server performed a record 3,014,684 transactions per minute (tpmC) at $.59 USD/tpmC, ranking it 5th overall on TPC-C Top 10 results for all non-clustered systems. The benchmark simulates the order-entry environment of a wholesale supplier entering and delivering orders, recording payments, checking the status of orders, and monitoring the level of stock at the warehouses. Current results show that clients who deploy IBM technology can expect to see more orders entered, as well as faster monitoring, distribution and delivery.
The record-breaking IBM x3850 X5 system was housed in a single, space-saving 42U rack. It was configured with four Intel Xeon E7-8870 processors running at 2.40GHz with 30MB of shared L3 cache per processor (4 processors/40 cores/80 threads), a total of 3TB of memory (2TB in server and 1TB in the IBM MAX5 for System x). The system was also configured with eXFlash enterprise multi-level cell solid state drive (SSD) storage which enables faster database access. IBM eXFlash drives are capable of providing up to a 20 times improvement over traditional disk drives.
For more information on IBM System x, visit http://www.ibm.com/systems/x/
IBM System x®3850 X5 (Intel Xeon E7-8870 processors 2.40GHz, 4 processors/40 cores/80 threads) TPC-C result of 3,014,684 tpmC, $.59 USD/tpmC, available 9/22/11, DB2 9.7, SUSE Linux® Enterprise Server 11 (SP1) vs. IBM System x®3850 X5 ( Intel Xeon X7560 processors 2.26GHz, 4 processors/32 cores/64 threads) TPC-C result of 2,308,099 tpmC, $.60 USD/tpmC, available 5/20/11, DB2 9.7, SUSE Linux® Enterprise Server 11 (SP1) vs. HP ProLiant DL580 G7 (Intel Xeon X7560 2.26GHz, 4 processors/32 cores/64 threads) result of 1,807,347 tpmC, $.49/tpmC, 2.46 Watts per KtpmC, available 10/15/10, Microsoft SQL Server 2005 Enterprise x64 Edition SP3, Microsoft Windows Server 2008 R2 Enterprise Edition. Source: www.tpc.org. Results current as of 8/11/11. TPC-C is a trademark of the Transaction Performance Processing Council (TPPC).
IBM and IBM logo are trademarks of International Business Machines Corporation, registered in many jurisdictions worldwide. For a current list of IBM trademarks, please see www.ibm.com/legal/copytrade.shtml. Other company, product or service names may be trademarks, or service marks of others. All statements regarding IBM future direction and intent are subject to change or withdrawal without notice, and represents goals and objectives only. All examples cited or described as presented as illustrations of the manner in which some clients and IBM Business Partners have used IBM products and the results they may have achieved. Actual environmental costs and performance characteristics will vary depending on individual client configurations and conditions. Generally expected results cannot be provided as each clients results will depend entirely on the client's systems and services ordered.