1. IBM z13 Hardware Innovation
Matthias R. Bangert
Executive IT-Specialist
IBM z Systems, Europe

2. The market is moving, forcing businesses to transform
Explosion in transaction growth
driven by mobility and the Internet of Things
Analytics is moving to real time
to capture new opportunities at the point of impact
Hybrid cloud is the new standard
for delivering service, agility, trust and efficiency
The market is moving, forcing businesses to transform
The technology forces of cloud, analytics, and mobile are causing havoc on traditional data centers. There is a marked shift from the somewhat stable and predictable workload of the Internet era to a highly unpredictable "Internet of things" that accumulates data from new and varied sources at greater volume and velocity.
In this environment the end user has the power and they are expecting a rapid rollout of new services that are customized to their unique needs, thus providing them with the ultimate in client experience.
At the heart of these new infrastructures is data and the ability to efficiently transact with it. A data-centric infrastructure must always be available for a 24x7x365 business, have flawless data integrity, and be secured from misuse. It needs to have integrated capabilities that can provide new mobile capabilities with real time analytics delivered by a secure cloud infrastructure.

3. Introducing the z13 Removing constraints on growth through innovation
Greater Workload Performance, Capacity and Scale in the same energy footprint
40% more configurable cores (up to 141 vs 101)
New built in vector facility (SIMD) for faster mathematical computation
3+ x more memory to reduce latency (10 TB vs 3 TB)
New multithreading (SMT2) to expand IFL (Linux) and zIIP capacity
40% more logical partitions to securely host more cloud tenants (85 vs 60)
Better Economics, Flexibility and Efficiency
zKVM and GDPS virtual appliance for Linux on IBM z Systems opens the door for more Linux
Standalone zBX support for more flexibility
New resilient IO Infrastructure addresses Skills, Complexity, Cost and Availability
Price Performance gains for Linux, zIIP, mobile and new SW workloads
Investment protection with full upgradeability from z196 and zEC12
Resilient and Secure Growth
Designed for Highest level of Security (PR/SM EAL5+)
Next Generation Hardware Cryptography
Best ever System z RAS with enhanced integrated sparing
Speaker notes:
*Best Ever System z availability: Per IBM Corporate Instruction ET105 which states that the RAS characteristics of a server must be equal to or better than the server it replaces in the marketplace
z13: An innovative, intelligent and integrated system that provides a trusted foundation for sustainable growth today and in the future

4. Performance delivered through multiple dimensions
Hardware/ software integration leads to richer optimization
40% more total capacity
2X performance boost for cryptographic coprocessors
50-80% more bandwidth per I/O domain
2X increase in channel speed
3X increase in memory
2X increase in cache
Lower cloud cost
Faster fraud detection
Top portion of the chart highlights the hardware innovations… the bottom half has the software advantages we get from taking advantage of those innovations – true hardware and software integration leads to richer optimization.
40% more total capacity
2X performance boost for cryptographic coprocessors
50-80% more bandwidth per I/O domain
2X increase in channel speed
3X increase in memory
2X increase in cache
More scale for mobile transactions
Faster data sharing between systems
Less exposure to regulatory penalties
Faster decision making with data-in-memory

5. Integrated system design
I/O and coprocessors bring RAS, cost savings and added compute power to workloads
Integrated system design
Up to 141 cores on a CPC
Up to 25 cores for offload system processing
Plus up to 320 POWER® cores:
I/O and Coprocessors
Plus up to RAS cores
24 SAPs
1 IFP
Share up to 141 processors with up to 85 LPARS
Configure the processors as CPs, IFLs, zIIPs, or ICFs
320 I/O RAS cores
2 Spares

6. Designed for transaction processing and data serving
Substantial economies of scale with simultaneous multi-threading delivering more throughput for Linux and zIIP-eligible workloads
Cognos® on Linux under z/VM® could see up to 60% increase in throughput with SMT on a z13 IFL1
Larger caches to optimize data serving environments
Single Instruction Multiple Data (SIMD) improves performance of mathematical operations and string processing.
Up to 2X improved cryptographic performance with enhanced Central Processor Assist for Cryptographic Functions (CPACF)
Compress more data helping to save disk space and cut data transfer time with improved on chip hardware compression
Better and faster memory management and execution time with new hardware instructions and functional facilities to optimize compilers
New 8-core Processor Design in 22nm Silicon Technology with wider instruction pipeline
With changes in the chip technology industry, microprocessor frequency is no longer the primary means to achieve performance. Hence, the new 22nm 8-core processor chip achieves performance gains over IBM® zEnterprise® EC12 (zEC12) by the following micro-architecture innovations:
Increased instruction parallelism through wider instruction decode bandwidth, increased execution bandwidth and a more aggressive out-of-order-execution.
Economies of scale, using simultaneous multi-threading (SMT) to execute two instruction streams (or threads) on a processor core which delivers more throughput for Linux® on z Systems™ and IBM z Integrated Information Processor (zIIP) eligible workloads. (As stated on an earlier chart – more work can be processed on zIIPs with an average capacity improvement of 38% compared to zEC12 including the exploitation of the new multithread option on the z13 zIIP and IFLs can process more work with an average capacity improvement of 32% compared to zEC12 including the exploitation of the new multithread option on the z13 IFL. Customers who are running COGNOS on Linux under z/VM could see up to 60% increase in throughput per core moving from a zEC12 to IBM z13 with SMT enabled.
Redesigned cache architecture, leveraging our leadership eDRAM technology to provide twice as much second level cache and substantially more third and fourth level caches compared to the zEC12. Bigger and faster caches help to avoid untimely swaps and memory waits while maximizing the throughput of concurrent workloads.
Single instruction, multiple data (SIMD) a vector processing model providing data parallelism, to speed workloads such as analytics and mathematical modeling. This is not the engineering/scientific vector processing from the past – which was used for weather, climate, etc. This is for analytics operations, and SIMD can enable applications to scan billions of rows of data per second, helping to accelerate response times for reports running against a column-oriented data store. SIMD can also be used for improved graphics processing. SIMD allows construction of richer, complex analytics models, increased programmer productivity and faster mathematical modeling solutions.
IBM z Systems continues to work on approaches that focus on increasing apparent thread speed such as accelerators for specific tasks. What is important about our accelerators is that we are not moving work off the platform to process – we are just moving the work to certain parts of the server to optimize it. On chip cryptographic and compression coprocessors receive a performance boost improving both general processors and IFLs. These include:
A cryptographic coprocessor with CP Assist for Cryptographic Function (CPACF) provides cryptographic functions and hashing functions in support of clear-key operations. We have seen up to 2X improved cryptographic performance with enhanced Cryptographic Assist Co-Processor Facility (CPACF).
Many years ago, IBM introduced S/390® Data Compression, right on the processor chip, which offered one-fifth the number of processor cycles of software-only compression. Implemented with the CMPSC instruction, it is an IBM proprietary compression using a dictionary-based approach. Processor chip compression is designed for relational database (row level) compression and is widely used by clients today. DB2® is one of the main use cases for this compression. DFSMS™ also utilizes hardware compression with generic compression available for VSAM and non-VSAM extended format data sets, as well as tailored compression available for non-VSAM extended format data sets. This chip based hardware compression is able to compress more data helping to save disk space and cut data transfer time.
Better and faster memory management and execution time with new hardware instructions and functional facilities to optimize compilers – including Transactional Execution, Runtime Instrumentation, Floating point execution bandwidth.
We are widening our pipes to do more instructions per cycle. We’ve doubled the floating point execution and we are still running this in out-of-order (OOO) execution to avoid waiting for some events to complete.
Results are based on internal lab measurements on a 4 core configuration on a single Linux guest running under z/VM and accessing DB2 on z/OS. Results may vary significantly depending on the workload and other factors.
A few examples we are seeing in SIMD value: 1. Enterprise PL/I 4.5 provides up to a 17% reduction in the CPU time for compute intensive batch PL/I programs executing on z13, compared to the same programs compiled with the Enterprise PL/I 4.4 compiler executing on zEC12. This significant reduction in execution time is achieved through more powerful hardware, improved compiler optimization, increased exploitation of the Decimal Floating Point facility and exploitation of the new Vector Facility. 2. Enterprise COBOL 5.2 provides up to 14% reduction in CPU time for compute intensive batch COBOL programs executing on z13 compared to the same program compiled with the Enterprise COBOL 5.1 GA compiler executing on zEC12. This significant reduction in execution time is achieved through more powerful hardware, improved compiler optimization, increased exploitation of the Decimal Floating Point facility and exploitation of the new Vector Facility. Users of COBOL 5.1 upgrading to the latest PTF will also see a performance improvement compared to the Enterprise COBOL 5.1 GA compiler.
1 Results are based on internal lab measurements on a 4 core configuration on a single Linux guest running under z/VM and accessing DB2 on z/OS. Results may vary significantly depending on the workload and other factors.

7. z13 Drawer Structure and Interconnect
Fully Populated Drawer
z13 Drawer Structure and Interconnect
Mem DIMMs
Mem
Mem
Mem
Node 1
Node 0
GX Bus
2x PCIe PU PU
GX Bus
GX Bus
2x PCIe PU PU
GX Bus PU
2x PCIe
2x PCIe
PSI
X-Bus
X-Bus
GX Bus
2x PCIe PU SC SC PU
S-Bus
GX Bus
2x PCIe
A-Bus
A-Bus
Mem
Mem
To other drawers
To other drawers
Physical node: (Two per drawer)
Chips
Three PU chips (with up to 8 active cores each)
One SC chip (480 MB L4 cache)
RAIM Memory
Three Memory Controllers: One per CP Chip
Five DDR3 DIMM slots per Controller: 15 total per logical node
Populated DIMM slots: 20 or 25 per drawer
SC and CP Chip Interconnects
X-bus: SC and CPs to each other (intra node)
S-bus: SC to SC chip in the (intra drawer)
A-bus: SC to SC chips in the remote drawers (intra box)
Node 1
Node 0
Drawer
Node 1
Node 0
Drawer
Node 1
Node 0
Drawer
Node 1
Node 0
Drawer

8. SIMD Exploitation Compute Intensity Data Intensity Integer Ops
Floating-Point Ops
String Ops
FP, String, Int
String, Int
Mathematical Optimization
Large
Matrix Math
Next Best Action
Predictive IT Analytics
Competitive
Algorithms
Compute Intensity
Adv Security/
Crypto
What will happen next?
Large String Ops
Security/
Crypto
Business Intelligence-Reporting
Next-Generation DW
Small Matrix Math
Data Warehousing (DW)
Large Compress
Traditional Algorithms
Traditional IT Analytics
Small Compress
Small Sort
Big Sort
Small String Ops
Big Scan
Data Intensity

9. Simultaneous Multi Threading (SMT)
Two Threads,
One core 50 80 50
Well that‘s why !!!
Why only 50?
Which approach is designed for the highest volume of traffic? Which road is faster?

10. Application Serving – SSL Enabled Day Trader 3.0
2.62x improvement in throughput with IBM Java 8 and IBM z13

11. More memory makes a difference
Enable totally new types of applications
Perform faster table scans with in memory data for faster response time; reduce CPU by avoiding IO, make possible new types of analysis
Accommodate growing workloads without changes to applications to gain benefits
Run sorts using large memory to improve elapsed times
Keep the entire Cognos Dynamic Cubes end-to- end application online for faster decision making
Support modern memory heavy computing languages and architectures
Larger Java® heaps without an increase in paging
Improves IBM MQSeries® V8 ability to manage increasing messaging volumes generated by today's mobile and cloud applications
Reduce need to fine tune memory and leverage the tuning capabilities in DB2®, IMS™ and CICS®
Memory really can provide increased value with the z13. Now is the time to break from traditional thinking on purchasing and assigning memory to your applications. New z/OS performance measurements have been run describing the benefits of running z/OS systems with very large central storage dedicated to DB2 buffers. Three papers are in the market today - the first is overall information on large buffers from a z/OS perspective, the second is the impact of large DB2 buffers on SAP performance (Get more work done – SAP online transaction processing can experience up to 70% reduction in response time with more memory), and the third is overall information on the benefits of very large buffers from the DB2 perspective (The DB2 buffer paper will show that adding additional memory can cut response time in half. This can lead to an increase in sales and client satisfaction by meeting your SLAs).
Large memory will allow you to enable totally new types of applications. You can perform faster table scans with in memory data for faster response time; reduce CPU by avoiding IO, make possible new types of analysis.
More memory helps to improve existing workload performance – such as being able to transparently support shrinking batch windows and meet service goals – no change to applications needed to gain benefits. Also you will be able to run more concurrent batch sort workloads. Users can run sorts using large memory to improve elapsed times. Or keep the entire Cognos Dynamic Cubes end-to-end application online for faster decision making.
Larger memory also supports modern memory heavy computing languages and architectures. You can have larger Java heaps without an increase in paging. And more memory improves IBM MQ V8 ability to manage increasing messaging volumes generated by today's mobile and cloud applications.
Improve system performance, minimize constraints and simplify management of applications with database middleware exploitation of additional memory. Large memory delivers significant performance improvements for DB2 by allowing it to exploit large fixed pages for improved paging and data in memory for better response time, offering new data linkages can be performed quickly to speed up data analysis for complex queries and bringing all your data into memory at once for faster table scans enabling faster response time. And having vast amounts of memory reduces the need to fine tune memory and leverage the tuning capabilities in DB2, IMS and CICS.
System z: Advantages of Configuring More Memory for DB2 Buffer Pools - and IBM zEnterprise System®: Performance Report on Exploiting Large Memory for DB2 Buffer Pools with SAP®
DB2 memory white paper -
DB2 Buffer Pool simulator tool available as a DB2 (V11) deliverable. Provides an accurate benefit estimation of increasing buffer pool size for DB2.

12. Resilient and intelligent I/O
New FICON Express16S links reduce latency for workloads such as DB2
Reduce up to 43% of DB2 write operations with IBM zHyperWrite – technology for DS8000® and z/OS for Metro Mirror environment
First system to use a standards based approach for enabling Forward Error Correction for a complete end to end solution
Clients with multi-site configurations can expect I/O service time improvement when writing data remotely which can benefit GDPS or TPC-R HyperSwap®
Extend z/OS workload management policies into SAN fabric to manage the network congestion
New Easy Tier ® API removes requirement from application/administrator to manage hardware resources
Improved and predictable performance for mission critical environments
The new z13 has been built to security support cloud, analytics, mobile and social workloads and the I/O enhancements available on it will reduce transactional latency - thus mitigating increases to transaction response times that may be introduced by adding cloud sourced data to the work flows. These performance improvements also improve the scalability of z/OS and middleware, such as DB2, to meet the demands of mobile applications. The increase in the volume of I/O work will be done with industry leading qualities of service (QoS).
We will offer a PCIe Gen3 I/O drawer – with the ability to add legacy workload as well. PCIe allows us to have better granularity and lower energy consumption – as well as being an industry standard. And moving to standardization with offerings like RoCE – RDMA over Converged Ethernet is important.
New FICON Express16S links improve I/O latency to reduce elapsed time for some batch jobs and improve SAP workloads. The FICON Express16S auto-negotiates 4, 8 and 16 Gbps so if a client still needs 2 Gbps they’ll need to keep the FICON Express8S around (or a switch). Our 16Gbps FICON is particularly excellent at large data transfer I/O options (A few proof points )
Using FICON Express16S on a z13, large data transfer I/O operations with zHPF (reads + writes) can achieve 2600 MB/sec a 63% increase in throughput over FICON Express8S on a zEC12
Using FICON Express16S on a z13, large data transfer I/O operations with FCP (reads + writes) can achieve 2560 MB/sec a 60% increase in throughput over FICON Express8S on a zEC12
IBM zHyperWrite is new technology provided by the IBM DS8870 and exploited by z/OS and DB2 for a metro mirror environment. It is designed to improve DB2 log write performance. It can reduce up to 43% of DB2 write operations along with having a throughput improvement.
First system to use a standards based approach for enabling Forward Error Correction (FEC) codes to improve resilience by reducing I/O errors. The improvement provided by FEC is equivalent to the improvement that would occur if the optical signal strength would be doubled. This technology will allow Z Systems I/O to operate at higher speeds, over longer distances, with reduced power and higher throughput, while retaining the same reliability and robustness that FICON has traditionally been known for.
Clients using multi-site business continuity solutions can experience improved I/O Service times when writing data remotely allowing them to achieve service level agreements after a disaster or storage control unit failure causes a HyperSwap event to occur.
Improved resilience against SAN hardware failures by extending the z/OS workload management policies into the SAN to manage congestion. When fabric ports, ISLs or switches fail, SAN congestion can occur. z/OS WLM policy controls which work gets preference to meet the client goals.
Additional information for presenter: The increased scale of the z13, specifically the increase in the number of devices available per channel, allows the consolidation of additional workloads onto a single foot print. Also, the increase in channel addressing and bandwidth allows adding more control units and devices onto a set of channels, allowing the client to reduce the number of I/O slots used for FICON so that other technologies can be exploited (i.e. Flash Express, zEDC Express, 10GbE RoCE Express, etc.).
New Easy Tier API removes requirement from application/administrator to manage hardware resources -- efficiently deploy storage with Easy Tier application for z Systems API, enabling applications on z Systems to direct optimal placement of data by communicating application performance requirements.
Between the processor drawer and the I/O subsystem – all connections are PCIe based so everything can be transported over the same fabric.
This performance data was measured in a controlled environment running an I/O driver program under z/OS. The actual throughput or performance that any user will experience will vary depending upon considerations such as the amount of multiprogramming in the user's job stream, the I/O configuration, the storage configuration, and the workload processed.
Supported by z/OS only
Optimized for enterprise-scale data from multiple platforms and devices

13. Specialty engines expand the use of the mainframe While lowering the cost of ownership
zIIP*
IFLs and Enterprise Linux Server
Coupling Facility
Relieves central processors of running specific workloads
Optimized for strategic web based applications with support for Java and XML processing
Focused on data and supporting workloads can help connect, manage, extend, and protect data
Special engine dedicated to Linux workloads on z Systems servers
IT optimization and cloud computing can deliver enhanced economics
Attractively priced and supported by the z/VM virtualization, the IBM Wave virtualization management and the Linux operating system
CF allows multiple processors to access the same data
New with z13 is support for 256 CHPIDs (2X available on zEC12)
New PCIe based short range coupling links
Specialty engines can help expand the use of the mainframe for new workloads. Simplification is also a goal of IBM as well as for its customers and z Systems has made changes to help customers get more economic value while simplifying configurations. The advantage of specialty engines is that customers do not incur software license charges for work running on the specialty engines, reducing their costs of running workloads. As additional work runs on the specialty engine, fewer processing units are consumed on CPs, resulting in lower software bills. And our specialty engines always run at 100% full capacity of the processor.
As a refresher, the zAAP was optimized to allow users to strategically deploy and integrate new Java™ and XML technology based workloads on the mainframe, facilitating the integration of applications and core business data in a highly cost effective manner. A zAAP helped simplify and reduce server infrastructures, providing both operational and performance advantages over a physically separated multi-tier solution; increase system productivity by reducing the demands and capacity requirements on general purpose processors which may be available for reallocation to other mainframe workloads; and lower the overall cost of computing for WebSphere® Application Server and other Java/XML solutions through potential hardware, software and maintenance savings. This capability hasn’t changed but we announced zAAP on IBM z Integrated Information Processor (zIIP) so that we could maximize the use of specialty engine white space. Effective with the z13, there is no zAAP and all work runs on zIIP.
So what are additional good workloads for zIIP? When it was first made available in 2006 it was only for centralized data serving - Portions of BI, ERP, and CRM remote connectivity to DB2 V8, as well as portions of long running parallel queries and select utilities. But each new release of z/OS has brought new exploiters such as: Network encryption on zIIP - IPsec network encryption/ decryption (with z/OS® V1.8), Remote mirror – zIIP assisted z/OS Global Mirror function (z/OS V1.9 or later), HiperSockets™ Multiple Write operation for outbound large messages (z/OS V1.9 or later), Business Intelligence – IBM Scalable Architecture for Financial Reporting for high-volume, high performance reporting, Intra-server communications – z/OS CIM Server processing (with z/OS V1.11) and DB2 sort utility – DB2 utilities sorting fixed-length records using IBM's memory object sorting technique. Plus select Tivoli products – for DASD scans and Performance Expert/ Performance Monitor, select RMF processing- on z/OS V2.1, a small portion of RMF™ monitoring is eligible for zIIP and ISVs like SyncSort support running their workload on zIIPs too.
New effective July 23, 2013 – the 2:1 ratio for zIIP to CPs was modified over the original 1:1. For every CP installed on a z13, there can up to two zIIPs installed.
Incremental throughput of the zIIP is achieved partially because the new processor chip offers simultaneous multi-threading (SMT). SMT on a zIIP will see up to xx% throughput improvement over the zEC12.
Linux on z Systems can benefit clients by freeing business from IT complexity and improving the responsiveness of systems and people. The Linux environment helps extract the maximum value from an IT budget through software savings, operational efficiency, power and space savings, as well as providing highest levels of security and virus-resistance while delivering legendary system reliability.
The IBM Enterprise Linux Server provides a virtualized infrastructure with the power and flexibility needed for enterprise Linux applications. It is a proven platform for Linux workloads and consolidation, and its life-cycle management costs can be considerably less expensive than other Linux platforms.
The IBM Enterprise Linux Server can provide significant advantages. It has the capability to run a large number of parallel workloads–up to hundreds–in a highly efficient and economical way. It can share system resources at extreme levels of utilization and provision flexible IT services. It provides load-balancing and efficient systems management helping to achieve superior levels of service and improved operational efficiency.
The IBM Enterprise Linux Server is designed from the ground up for enterprise-class workloads, can help on lower software license costs, can secure data from the growing threats und helps to use less of the environmental resources.
The IBM Enterprise Linux Server provides an infrastructure that is data ready, mobile ready, security ready and cloud ready. It is a simple way to run an efficient and economic infrastructure.
Like the zIIP, the IFL can run on the chip using simultaneous multithreading (SMT). The z13 offers predictable performance increase for Linux workload with simultaneous multithreading - has to do with the fact we are filling each thread completely and then going to the next. Filling each thread is what allows us to have a predictable throughput that can be measured with LSPR and our tools. Thus we can say we get xx% throughput increase and be assured for that workload we will achieve that.
With IBM's Parallel Sysplex technology, you can harness the power of up to 32 z/OS systems, yet make these systems behave like a single, logical computing facility. What's more, the underlying structure of the Parallel Sysplex remains virtually transparent to users, networks, applications, and even operations.
To accomplish all this, the z/OS Parallel Sysplex combines two critical capabilities: The first is parallel processing, and the second is enabling read/write data sharing across multiple systems with full data integrity.
The coupling facility makes data sharing possible by allowing data to be accessed throughout a sysplex with assurance that the data will not be corrupted and that the data will be consistent among all sharing users. The coupling facility provides the medium in which users of coupling facility structures can reconstruct shared data should a failure occur and can be used to assist in the isolation of failing systems.
A coupling facility is licensed internal code (LIC) running in a special type of PR/SM™ logical partition (LPAR). A coupling facility can be shared by the systems in one sysplex only; it cannot be shared simultaneously by multiple sysplexes.
New PCIe based short range coupling links •
In 2013 we announced that the Coupling Facility can use Flash Express improving availability. In the future CF will use Flash Express for a cost effective, resilient solution for overflow of WebSphere® MQSeries® shared queues in Coupling Facility.
Another CF enhancement of interest is Coupling Thin Interrupts (not on the chart to save space but a good to know). Coupling Thin Interrupts improve the efficiency of environments where shared-engines are used as Coupling Facilities (CFs) rather than dedicated engines. While dedicated engines continue to be recommended to obtain the best Coupling Facility performance, Coupling Thin Interrupts may help to facilitate use of a shared pool of engines, thus lowering hardware acquisition costs.
You can now experience CF response time improvements and/or more consistent CF response times when using Coupling Facilities with shared engines. This may allow more environments with multiple test and/or production CF images to coexist in a server and share CF engines, with reasonably good performance. The response time for asynchronous CF requests may also be improved as a result of support for Coupling Thin Interrupts on the z/OS host system, regardless of whether the CF is using shared or dedicated engines. The Coupling Thin Interrupts enhancement is exclusive to the z13, zEC12, zBC12, and z/OS.
zIIP and IFLs get throughput increase with simultaneous multithreading
* Supports 2:1 ratio for zIIP to CP 13

14. Linux on z Systems means an enterprise grade Linux solution
While “Linux is Linux”, z Systems server and virtualization technologies provide an enhanced Linux solution
Having an enterprise grade Linux
solution brings:
IT simplicity to run hundreds of workloads on one server
Workload integration of new and existing enterprise data and applications
Virtualization management for easy and flexible server provisioning
High productivity through efficient life cycle management
High utilization of shared resources
Companies, especially new ones are using Linux to help them bring their solutions to market quickly. As these solutions and companies grow, or are acquired by other companies, the Linux applications need to also be able to fit smoothly in an enterprise that has a focus on “risk-adverse central IT function” – think of that as z Systems core enterprise QoS business.
So while “Linux is Linux” … a z Systems server and our virtualization technologies provide an enhanced Linux solution. We are able to bring the following to an enterprise grade Linux solution:
The ability and simplicity to run hundreds of workloads on one server
Workload integration of new and existing enterprise data and applications
Virtualization management for easy and flexible server provisioning
High productivity through efficient life cycle management – no matter if this is for the end Companies, especially new ones are using Linux to help them bring their solutions to market quickly. As these solutions and companies grow, or are acquired by other companies, the Linux applications need to also be able to fit smoothly in an enterprise that has a focus on “risk-adverse central IT function” – think of that as z Systems core enterprise QoS business.
High productivity through efficient life cycle management – no matter if this is for the end
Linux on z Systems provides security, availability, and scalability to deploy and consolidate a variety of workloads

15. Reinventing enterprise IT for digital business
Designed for data and transaction serving for the mobile generation
Designed for integrating transactions and analytics for insight at the point of impact
Designed for efficient and trusted cloud services to transform the economics of IT
IBM has historically majored in hardware and firmware availability, then system availability, and with IBM zAware we extended this to application and workload availability.
IBM zAware is a unique application of IT analytics applied to help you optimize application and system availability, reduce PD time, and accelerate restoration of service levels. It is packaged in an innovative way, too, as a self-contained firmware solution ordered as a feature of the server to simplify delivery and support solutions, making it easy for clients to deploy and reduce the support costs.
IBM zAware takes IBM’s expertise in availability to the next level with built in z/OS knowledge about application and system problems. IBM zAware helps identify patterns of messages to hone in on, such as unusual or problematic messages are the most likely “culprits” warranting further analysis.
By pinpointing the most likely problematic messages IBM zAware can slash your problem determination time from hours to minutes, and help you restore service levels quickly. Difficult or unusual problems can be found in 2 clicks – not hours. It helps you with diagnosis of complex problems including the ones that span organizational boundaries, complex ones requiring many teams to understand, or ones that cross sysplexes.
As applications become more complex, in a skills constrained environment, IBM zAware can isolate a problem quickly---even if the application knowledge is missing
And IBM zAware can help you spot a problem in the making and intervene early before it cascades into a disruption.
IBM zAware V2.0 extends support to Linux on z Systems.
IBM Tivoli OMEGAMON XE on z/OS V5.1.1 offers new visibility and proactive notifications for IBM z Advanced Workload Analysis Reporter (IBM zAware). New workspaces are supplied for the Tivoli Enterprise Portal (TEP) as well as the enhanced 3270 user interface for the SMEs. In conjunction with the workspaces, new proactive situations are available for notification of alerts that IBM zAware would generate on finding or reporting on message anomalies.
Tivoli OMEGAMON XE on z/OS alerts you of excessively high IBM zAware anomaly scores, indicative of a problem on the system. Using the proactive situation alerting feature, you are notified of impending system problems and take action to potentially prevent system outages.
The trusted enterprise platform for integrating Data, Transactions and Insight!

16. Thank You