Monday Oct 26, 2015

New SAP-SD 2-Tier 1-node Benchmark Record on SPARC T7-2

Today Oracle announced an all-new family of SPARC systems with new dramatic advancements in memory protection, encryption acceleration, and in-memory database processing.

A new record result of 30,800 SAP-SD users for the SAP Sales and Distribution (SD) Standard Application benchmark has been published for one of the small servers in this family, the SPARC T7-2 server with 2 processors / 64 cores / 512 threads, SPARC M7 4.133 GHz, 16 KB (D) and 16 KB (I) L1 cache per core, 256 KB (D) L2 cache per 2 cores and 256KB (I) per 4 cores, 64 MB L3 cache per processor, and 1024 GB main memory. 

Comparing this result to other SAP SD results* shows the new SPARC M7 to be:

  • SPARC M7 1.9x faster per chip than x86 E5 v3 (Haswell)
  • 2-chip SPARC M7 nearly same performance as 4-chip x68 E7 v3
  • SPARC M7 2.9x faster per chip than IBM Power8 (6c)

The SAP SD benchmark results can be found here.    

* Results as of Oct. 26, 2015. Source: SAP,  The following two-tier SAP Sales and Distribution (SD) application benchmarks have been certified with SAP enhancement package 5 for SAP ERP 6.0: SPARC T7-2, 2 processors / 64 cores / 512 threads, SPARC M7 4.133 GHz, 30,800 SD users, 168,600 SAPS, Solaris 11, Oracle 12c, 1 TB main memory. Certification Number: 2015050. Dell PowerEdge R730, 2 Processors / 36 Cores / 72 Threads, Intel Xeon Processor E5-2699 v3, 2.3 GHz, 16500 SD Users, 90120 SAPS, Red Hat Enterprise Linux 7, SAP ASE 16, 262 GByte main memory. Certification Number: 2014033. IBM Power System S824, 4 Processors / 24 Cores / 192 Threads, POWER8, 3.52 GHz, 21212 SD Users, 115870 SAPS, AIX 7.1, DB2 10.5, 524 Gbyte main memory. Certification Number: 2014045

ISV Partners See Amazing Results on SPARC M7-Based Systems

Today Oracle announced an all-new family of SPARC systems built on the revolutionary 32-core, 256-thread SPARC M7 microprocessor. The systems feature Security in Silicon for advanced intrusion protection and encryption; SQL in Silicon that delivers unparalleled database efficiency; and world record performance spanning enterprise, big data, and cloud applications. These new systems, include the Oracle SuperCluster M7 engineered system and SPARC T7 and M7 servers. Read the full press release.

Some of our ISV partners have been testing these new systems through the early access program and have been seeing amazing results: 

Siemens PLM: Hear how Siemens looks to Oracle for innovation and integration across the stack, highlighting the SPARC M7 servers with Software in Silicon technology for unprecedented performance and unique security capabilities in this video.

“As a leading global provider of product lifecycle management software and services, Siemens PLM Software, helps thousands of companies realize innovation by optimizing their processes. We continually leverage our strong relationship with Oracle to ensure that our Teamcenter software is tuned to run on Oracle platforms. Teamcenter tests of the new Oracle SPARC M7 servers showed dramatic performance improvements, surpassing any improvements seen with a single generation upgrade of SPARC servers. Software-in-Silicon features of the SPARC M7 processor such as the Silicon Secured Memory and SQL in Silicon offer unique capabilities for performance tuning,” said Chris Brosz, vice president of Technical Operations, Siemens PLM Software. 

BPC: “BPC Banking Technologies’ long-term relationship with Oracle aims to find the best technology solutions for our clients. We successfully tested SmartVista on Oracle’s SPARC M7 server running Oracle Solaris, and measured the impact of the Oracle Database In-Memory option along with the SPARC M7 processor’s new SQL in Silicon feature,” said Evgeny Kozhin, senior solutions architect, BPC Banking Technologies. “We were excited to see dramatic performance increases for both our online and batch processing tests. SmartVista is highly tuned and traditionally we only see incremental performance gains with new processor generations. No modifications to SmartVista were needed to get these extraordinary results.”

Capitek: “Capitek AAA is a carrier-grade access authentication management application for the wireless communication networks across China. In our tests processing log files for each AAA server, Oracle's SPARC M7 systems with Silicon Secured Memory and Oracle Solaris Studio development tools proved to be the only effective method of protection against dangerous programming vulnerabilities,” said Jerry Chen, senior manager, Telecom Software Product Department. “It enabled Capitek AAA to be more secure and highly available with very little impact on overall system performance. Other software based memory checking tools proved to be unusable due to their large overhead.”

JomaSoft: “JomaSoft recently completed performance tests on Oracle’s SPARC T7 system running Virtual Datacenter Control Framework (VDCF), our management solution for creating, migrating, patching and monitoring Oracle Solaris environments. Our results showed VDCF to be 1.5x faster core-to-core on SPARC T7 compared to SPARC T5. JomaSoft views Oracle’s powerful SPARC M7 and T7 systems as ideal platforms for customer consolidation and virtualization projects, with technology and value that no other vendor can offer,” said Marcel Hofstetter, CEO at JomaSoft.

MSC Software: “MSC Software, a worldwide leader in multidiscipline simulation technology, recently tested our SimManager simulation data and process management system on Oracle’s SPARC M7 system with Oracle Database 12c. Our testing found SPARC M7 to be extremely scalable and able to deliver better core-to-core throughput than an Intel Xeon X5 v3 server running a SimManager workload. Oracle Solaris 11 virtualization also consolidates multiple instances of the MSC SimManager server, providing a simplified method of managing and processing hundreds of thousands of simulations for product design onto a single platform,” said Leo Kilfoy, general manager, Engineering Lifecycle Management Business Unit, MSC Software Corporation.

SAS: "Oracle's Software in Silicon technology delivers significant value to both SAS customers and internal development teams. The scalability, performance and extensive memory bandwidth of the Oracle SPARC M7 is well-matched with the highly threaded and memory intensive algorithms of our high performance Business Analytics software – which means customers running SAS on Oracle will see faster analysis of their data so they can make better business decisions,” said Craig Rubendall, vice president, Research & Development, SAS. “In addition, SAS uses a variety of tools to ensure the quality of code that is delivered to our customers. The SPARC M7’s Silicon Secured Memory feature along with the Oracle Solaris Studio Code Analyzer detected difficult to find run-time errors far more quickly than other products we use for this purpose, resulting in faster fixes to common code across all platforms.”

Software AG: “Software AG’s Adabas Database Management System Platform is optimized for large-scale transaction processing and provides high-performance and reliable data processing for enterprise business transactions. We have been collaborating closely with Oracle engineering and we recently tested Adabas version 6.4 SP 1 on Oracle’s SPARC M7 system through their early access program and achieved an amazing 2.8X performance increase over Oracle’s SPARC T5 system,” said Angelika Siffring, VP, Product Management, Software AG. “Software AG’s relationship with Oracle helps us provide the fastest and most secure software solutions to our mutual customers.”

Software in Silicon Cloud 

You can test your applications on these new systems to leverage their breakthrough technologies using the Oracle Software in Silicon Cloud for developers and partners. Available now to all OPN members, enterprise developers with MOS accounts and university researchers (members of Oracle Academy), the Software in Silicon Cloud is a robust and secure cloud platform with ready-to-run virtual machine environments and offers easy access to Oracle SPARC M7 systems running Oracle Solaris 11.3. Try it today!

Tuesday Oct 13, 2015

Asseco def3000/CB Core Banking Systems Optimized on Oracle SuperCluster

 “Our biggest clients need highly performant and scalable systems to grow their business and consolidate data from other banks in the future.  With Oracle SuperCluster we can offer a platform that meets these requirements and offers our. Oracle Systems are now a preferred platform customers lower TCO for Asseco's def3000/CB solution.”- Robert Płociński, Technical Director, Commercial Banks Dept, Asseco

Asseco Poland is the largest IT company listed on the Warsaw Stock Exchange. It has developed technologically advanced software solutions for companies and institutions of all key sectors of the economy for more than 20 years. Today, Asseco is the number one IT powerhouse in Central Europe and the sixth largest software vendor in Europe.

Their def3000/CB (Core Banking) system constitutes the central point of their product offerings for a modern financial institution. It is a state-of-the-art, comprehensive tool, which allows to pursue an effective, efficient and competitive policy of the Bank.

Recently Asseco tested and tuned def3000/CG on Oracle SuperCluster and achieved Oracle Exastack SuperCluster Optimized Status.

Here's what they tested:

  • def3000/CB 10.05.000N
  • Oracle SuperCluster T5-8 Half Rack using Solaris Zones and 4 Exadata X5 HC storage nodes
  • Oracle WebLogic Server 11g
  • Oracle Database Enterprise Edition Release
  • Oracle Real Application Clusters
  • Oracle Partitioning

Oracle Solaris 11 Oracle SuperCluster accommodated the workload requirements and performance SLAs from their biggest customers as well as near linear scalability with RAC and Database partitioning.

It met business and technical requirements to be a preferred platform for def3000.

For more information about def3000 check here.

Monday Aug 31, 2015

Temenos T24 Optimized for Oracle SuperCluster

Earlier this year Temenos, a market leader for banking software, optimized their integrated Wealth Management Platform: Temenos WealthManager,  on Oracle SuperCluster. See blog for details. Now they have optimized their flagship product T24 on it.

T24 is a complete front- to back-office, CRM and product lifecycle management software platform that powers core banking operations. Consistently ranked as the first or second best-selling core banking software platform worldwide for the past 14 years (International Banking Systems Sales League Table), T24 has been developed using a complete service-oriented architecture that’s modular so banks can deploy and integrate the required functionality alongside the needs of their business.

Tests were run with the following:

  • Temenos T24 R14 Core Banking
  • Oracle SuperCluster M6-32 (used at Half capacity) with:
    • 2 x M6 Cabinet : 8 CPU each (50% of CPU capacity )
    • Exadata  Storage Server software
    • Exalogic  Elastic Cloud software
    • Exadata Storage Rack : 9 Storage Cell
  • Oracle Database Enterprise Edition 11GR2
  • Oracle Transparent Data Encryption (Advanced Security)
  • Weblogic Enterprise Edition 11G

Lower TCO, Maximum Performance and Reliability

This solution at a customer deployment provided savings of close to $5.6 million over 5 years with lower TCO and much higher availability. Storing the Temenos core banking data on SuperCluster storage cells costs 50% less than before.

“Temenos T24 on Oracle’s M6-32 SuperCluster engineered system enables Temenos’s customers to securely consolidate their solution at a large ratio without affecting performance, replacing a number of machines with capacity still available for future plans as well as growth. Temenos T24 on Oracle SuperCluster improves efficiency, performance and reduces costs, leading to a better customer experience.  With storage performance improving 10x on existing solutions and a TCO providing massive savings, the platform considerably improves security, performance and availability over existing deployments.” - Simon Henman, Temenos performance manager.

More information about Temenos can be found here.

Wednesday Jul 22, 2015

Scale up or Scale out?

QuartetFS In-memory Analytical Suite on Oracle SPARC Servers

Is scale out really the most cost effective architecture for all solutions?

ActivePivot, the in-memory analytics suite from QuartetFS, is implemented by customers such as HSBC, Société Générale, FNAC, Gefco and EBRD. On June 12, during Technology Keynote of the 7th annual ActivePivot User Group conference, Antoine Chambille, head of research & development at Quartet FS, along with Eric Bezille chief technologist of Oracle Systems France, discussed the benefits of scaling up ActivePivot on large memory machines. They shared the near linear scalability and great performance results of a joint benchmarking and tuning effort with recently released ActivePivot 5.2 running on an Oracle M6 SPARC server with 3072 CPU threads and 16 TB of memory. They also discussed the cost effectiveness of such a solution.

Watch the video and check out the presentation for more details.

Two sessions in JavaOne 2015 will also discuss the results of this project CON1855 and CON1917.

Wednesday Jan 21, 2015

CPU utilization of multi-threaded architectures explained

by Martin Tegtmeier from ISV Engineering in Walldorf


Simple CPU metrics (user/system/idle/io-wait) are still widely used although these numbers need interpretation on today's multi-thread/multi-core architectures. "Idle" as measured by operating systems cannot be literally translated into available CPU resources - turning capacity planning into a more complex problem.


Back in the days when 1 processor contained 1 core capable of running 1 thread, CPU utilization reported by the operating system indicated actual resource consumption (and resource availability) of the processor. In such environments CPU utilization grows linearly with increased workload.

Multi-core CPUs:  1 processor = 2 or more cores
In multi-core CPUs, where 1 processor contains 2 or more cores, each processing core has its own arithmetic and logic unit, floating point unit, set of registers, pipeline, as well as some amount of cache. However multi-core CPUs also share some resources between the cores (e.g. L3-Cache, memory controller).

Simultaneous multi-threading CPUs/cores:  1 processor or core = 2 or more threads  (aka "Hyper-Threading", "Chip Multi-threading")
The hardware components of one physical core are shared between several threads. Each thread has at least its own set of registers. Most resources of the core (arithmetic and logic unit, floating point unit, cache) are shared between the threads. Naturally those threads compete for processing resources and stall if the desired units are already busy.

What are the benefits of resource sharing?
Resource sharing can increase overall throughput and efficiency by keeping the processing units of a core busy. For instance hyper-threading can reduce or hide stalls on memory access (cache misses). Instead of wasting many cycles while data is fetched from main memory the current thread is suspended and the next runnable thread is resumed and continues execution.

What are the disadvantages?

  • CPU time accounting measurements (sys/usr/idle) as reported by standard tools do not reflect the side-effects of resource sharing between hardware threads
  • It is impossible to correctly measure idle and extrapolate available computing resources

Idle does not indicate how much more work can be accomplished by the CPU

Assuming 1 CPU core has 4 threads. Currently 2 (single-threaded) processes are scheduled to run on this core and these 2 processes already saturate all available shared compute resources (ALU, FPU, Cache, Memory bandwidth, etc.) of the core. Commonly used performance tools would still report (at least) 50% idle since 2 logical processors (hardware threads) appear completely idle.

In order to correctly estimate how much work can be added until the system approaches full saturation the operating system would need to get detailed utilization information of all shared core processing units (ALU, FPU, Cache, Memory bandwidth, etc.) as well as knowing the characteristics of the workload to be added (!).

Measurements with SAP ABAP workload

To illustrate our case, let's look at a very specific but very common workload in Enterprise Computing: SAP-SD ABAP. We took these measurements on a SPARC T5 system running the latest Solaris 11 release. Simulated benchmark users logged onto the SAP system and entered SD transactions. The maximum number of SD-Users and SAP transaction throughput the system could handle are represented by the 100% mark on the X-Axis. A series of test runs was carried out in order to measure CPU utilization (Y-Axis) as reported by the operating system at 0%, 12.5%, 25%, 50%, 60%, 75%, 90% and 100% of the maximum number of SD-Users.