Blog de Red Hat
Not long ago, Intel introduced a new Xeon processor platform to enable faster computing for the enterprise world. Codenamed Broadwell, this architecture brought additional cores to the chip and many improvements, from faster memory support to various security enhancements. As with three generations of Intel Xeon processors before this one, these benefits span beyond simple increases in transistor counts or the number of cores within each processor.
Today, Intel launched the Intel Xeon E7 v4 processor family, a high-end, enterprise-focused class of processors based on Broadwell architecture and targeted at large systems with four or more CPUs. Accompanying the launch are several new world record industry-standard benchmarks; this is where things like increased memory capacity or larger on-chip caches benefit overall system performance, resulting in the highest reported scores on various standard benchmarks. The Xeon E7 v4 launch, along with other announcements like it, typically send a ripple of innovation throughout Red Hat’s partner ecosystem in the form of new and improved performance results. The ability to support these partners is of paramount importance to Red Hat and, as a result, Red Hat Enterprise Linux is often selected by these ongoing benchmarking efforts.
Here is how Red Hat Enterprise Linux scored this time:
|Significance||OEM Platform||Segment: Benchmark Name||OS|
|2-socket world record||Cisco UCS B460 M4||Technical Computing: SPEComp_baseG2012||Red Hat Enterprise Linux 6|
|4-socket world record||Cisco UCS C460 M4||Technical Computing: SPEComp_G2012||Red Hat Enterprise Linux 6|
|4-socket world record||Cisco UCS C460 M4||Server-side Java: SPECjbb2015 Multi-JVM Critical-jOPS||Red Hat Enterprise Linux 7|
|4-socket world record||Dell PowerEdge R930||Business Processing: SAP Sales and Distribution 2-tier||Red Hat Enterprise Linux 7|
|4-socket world record||HPE ProLiant DL580 Gen9||Infrastructure/Virtualization: SPECvirt_sc2013||Red Hat Enterprise Linux 7|
|4-socket world record||HPE ProLiant DL580 Gen9||Big Data Analytics: TPC Benchmark H @ 3TB non-cluster||Red Hat Enterprise Linux 7|
|Overall world record||Lenovo System x3850 X6||Big Data Analytics: STAC-M3 Shasta||Red Hat Enterprise Linux 7|
|Overall world record||Lenovo System x3850 X6||Server-side Java: SPECjbb2015 Distributed Critical-jOPS||Red Hat Enterprise Linux 7|
With 8 new world records in business critical workload categories such as ERP, Java, Big Data and virtualization, Red Hat Enterprise Linux is a clear platform of choice for several Original Equipment Manufacturers (OEMs) that need to execute demanding enterprise workloads across physical, virtual, or cloud installations.
Red Hat and Intel have enjoyed a long history of collaboration across a full spectrum of enterprise IT – covering a wide range of use cases, from applications running on physical servers to virtualized and cloud-based deployments. To this end, it should come as no surprise that Red Hat Enterprise Linux remains a key piece of the IT industry’s process for running and publishing standard benchmarks.
As the chart (above) demonstrates, Red Hat Enterprise Linux was predominantly used in TPC and SPEC benchmark publications during the last two years.*
With outstanding benchmark results from 2-socket Intel Xeon E5 family launch fresh in our minds, we are also observing great scalability from 2 to 4 CPUs across ERP, virtualization and Java workloads.
The above chart demonstrates that when it comes to ERP, virtualization and Java applications, Red Hat Enterprise Linux delivers industry-leading scalability going from dual to quad processor configuration while still maintaining excellent performance.**
These benchmarks provide more proof points supporting the argument that Red Hat Enterprise Linux excels at handling scalable workloads and thrives in ever-changing environments, as enterprise customers place ever increasing demands on their infrastructure. This recent set of performance records on Intel Xeon E7 v4 family of processors reinforces Red Hat’s continued commitment of delivering choice, value, and innovation to our customers and partners that require a stable platform to extract top performance from their infrastructure.
All results as of June 6, 2016. SPEC and the benchmark names SPEC CPU, SPECjbb, SPEComp and SPECvirt_sc are registered trademarks of the Standard Performance Evaluation Corporation. For more information about SPEC and its benchmarks see: www.spec.org. TPC is a trademark of the Transaction Processing Performance Council (TPC). For more information about the TPC and its benchmarks see www.tpc.org. SAP and SAP NetWeaver are the registered trademarks of SAP AG in Germany and in several other countries. See www.sap.com/benchmark for more information.
* Results as of June 6, 2016. Based on the data collected for two calendar years (from 06/2014 to 06/2016) using the following public resources: http://www.spec.org and http://www.tpc.org/
** Results as of June 6, 2016. Based on benchmark data collected from http://www.intel.com/content/www/us/en/benchmarks/server/xeon-e5-v4/xeon-e5-v4-world-record and http://www.intel.com/content/www/us/en/benchmarks/server/xeon-e7-v4/xeon-e7-v4-world-record
About the author
Yan Fisher is a Global evangelist at Red Hat where he extends his expertise in enterprise computing to emerging areas that Red Hat is exploring.