This member of the IBM Z family, the IBM z15 uses a 19-inch form factor and industry-standardized power and networking hardware. The system is configurable as a one to four 19-inch frame system, which easily aligns with the modern cloud data center.
- 190 client configurable cores, an increase of 20 over the z14, with single processor capacity of z15 for equal n-way at common client configurations, approximately 14% greater than on z14 with some variation based on workload and configuration.
- 25 % more total system capacity as compared to the z14 for exceptional scale in a single footprint.
- More on-chip cache per core, compared to z14, to help minimize memory waits while maximizing the throughput of concurrent workloads — perfectly optimized for data serving.
- Up to 40 terabytes (TB) of available Redundant Array of Independent Memory (RAIM) real memory per server to help improve transaction response times, lower CPU costs, simplify capacity planning, enlarge in-memory buffer pools, cache sysplex shared data and controls in Coupling Facilities, and ease deploying memory-intensive workloads.
- IBM Integrated Accelerator for z Enterprise Data Compression, designed to reduce the cost of storing, transporting, and processing data without changing applications. It replaces the zEDC Express card on z14 and older generations of IBM servers, and interoperates compatibly with the zEDC compression used on previous IBM Z platforms and with industry-standard compression used on other platforms. Improved compression ratio (using Huffman coding) and order-preserving compression result in fewer CPU cycles to enable further compression of data, improving memory, transfer, and disk efficiency. With the IBM Z Integrated Accelerator for z Enterprise Data Compression you can achieve up to 17x more throughput capacity than the largest configured z14.
- The z15 has 30+ new instructions codesigned and exploited by Java, new vector enhancements to improve analytics applications and new instructions for sort acceleration.
Security and cryptography:
- A design for data protection and privacy allowing you to encrypt many new data sets transparently, which can help you to provide an envelope of protection around data placed on IBM Z. This includes cryptographic performance improvements with the Crypto Express7S (#0898 or #0899) and the IBM Z processor based cryptography with the CP Assist for Cryptographic Functions that helps enable the protection of data in flight or at rest.
- Hardware accelerated encryption on every core with the Central Processor Assist for Cryptographic Function (CPACF) feature.
- Processor improvements include Message-Security-Assist extension 9 providing support for elliptic curve cryptography authentication of messages, the generation of elliptic curve keys, and scalar multiplication. This is accomplished through a new instruction (Compute Digital Signature Authentication (KDSA)) which supports the ECDSA and EdDSA algorithms using curves P-256, P-384, P-521, Ed25519, and Ed448 and is in compliance with the Digital Signature Standard (DSS), National Institute of Standards and Technology (NIST) July 2013.
- IBM Z Data Privacy Passports which will protect data not only on IBM Z, but across multicloud environments without application changes.
Network and I/O:
- OSA-Express7S GbE, 10GbE, 1000Base-T, and 25GbE SR1.1.
- FICON Express16SA (#0436, 0437) to help absorb large application and transaction spikes driven by large unpredictable analytic and mobile workloads.
- An increase in the maximum number of coupling CHPIDs per CPC from 256 with z14 to 384 with z15, which provides for improved virtualization of physical ICA SR and CE LR coupling links.
- An increase in the maximum number of physical ICA SR coupling links per CPC from 80 on z14 to 96 on z15, and per drawer from 20 on z14 to 24 on z15.
- An increase in the maximum number of internal coupling CHPIDs per CPC from 32 on z14 to 64 on z15.
- A new level of Coupling Facility support, CFLEVEL 24, which provides optimized latch management, improved message path resiliency, and a change to the defaults for dynamic dispatching. For details see the Parallel Sysplex Enhancements section.
- IBM zHyperLink Express1.1 (#0451), which uses a direct connect short distance link (zHyperLink) to deliver low latency connectivity between z15 and FICON storage systems. Working in conjunction with your existing FICON SAN infrastructure, zHyperLink Express1.1 delivers the next generation of I/O for IBM Z storage.
Systems management and infrastructure:
- IBM Hardware Management Console (HMC) 2.15.0 with simplification updates to improve workspace and manage system time.
- IBM Z Hardware Management Appliance (#0100), which can be used to create isolated partitions for protecting data and applications from cybercriminals.
- Trusted Key Entry (TKE) 9.2 License Internal Code (LIC), (#0881).
- Flexible configuration; each frame is an industry-standardized 19-inch frame taking up only two floor tiles of space. The system expands from one to four frames based on your requirements and potential growth.
- System Recovery Boost which enables restoration of service from, and workload catch up after, both planned and unplanned outages faster than on any prior Z machine and with no additional IBM software costs, along with faster GDPS-orchestrated reconfiguration actions such as those involved in a planned or unplanned DR site switch.
- Non-raised floor option, offering flexible possibilities for the data center.
- Optional water cooling, providing the ability to cool systems with user-chilled water.
- Optional top exit power and I/O cabling designed to provide increased flexibility.
- ASHRAE class A3 for robustness, data center flexibility, and energy savings.
- Upgradability to IBM z15 from IBM z14 and IBM z13 and upgradability within the IBM z15 family.
- IBM Dynamic Partition Manager enhancements that provide a simplified, consumable, enhanced IBM Z experience, reducing the barriers of adoption for new and existing Linux on IBM Z and z/VM clients.
The performance advantage
IBM’s Large Systems Performance Reference (LSPR) method is designed to provide comprehensive z/Architecture processor capacity ratios for different configurations of central processors (CPs) across a wide variety of system control programs and workload environments. For IBM z15, the z/Architecture processor capacity indicator is defined with a 4XX, 5XX, 6XX, or 7XX notation, where XX is the number of installed CPs.
In addition to the general information provided for z/OS, the LSPR also contains performance relationships for z/VM and Linux operating environments.
The capacity per processor engine of an IBM z15 (8561) processor is expected to provide approximately a 14 % increase over that of a z14 (3906), with some variation, based on workload and configuration. The largest IBM z15 (8561-7J0) is expected to provide up to 25 % more capacity than the largest z14 (3906-7H0). The IFL and zIIP processors on the IBM z15 also provide an optional IBM z15 multithreading technology capability; with the multithreading function enabled, the performance capacity of an IFL or zIIP is expected to typically be up to 25 % higher than without the multithreading function enabled.
The LSPR contains the Internal Throughput Rate Ratios (ITRRs) for IBM z15 and the previous-generation IBM Z processor families based upon measurements and projections using standard IBM benchmarks in a controlled environment. The actual throughput that any user may experience will vary depending upon considerations such as the level of multiprogramming in the user’s job stream, the I/O configuration, the workload processed, and the LPAR configuration. Therefore, no assurance can be given that an individual user will achieve throughput improvements equivalent to the performance estimates stated.
For more detailed performance information, consult the Large Systems Performance Reference (LSPR) available at the Resource Link website.
z15 merges the RAS characteristics from the performance-optimized z14 family with the 19-inch frame from the z14 model ZR1. z15 introduces:
- The use of IBM System Recovery Boost which expedites planned operating system shutdown processing, operating system IPL (Initial Program Load), middleware/workload restart and recovery, and the client workload execution that follows. It will let businesses return their systems to work faster, not just in disaster recovery scenarios, but after all kinds of disruptions, both planned and unplanned. Another aspect of System Recovery Boost is to expedite and streamline the execution of GDPS recovery scripts which perform reconfiguration actions during various planned and unplanned operational scenarios.
- Processor and memory PU refresh, RAIM memory, and cache symbol ECC which are designed to provide a robust computing platform.
- PU sparing, array macro sparing, micro-array masking integrated sparing, and expanded optics as a FRU which are used to reduce repair actions.
- The wide use of redundancy in the power, cooling, and service network, which continues with the z15 family. A “power redundancy test” is provided so the customer can verify the server is power redundant before servicing their customer power feeds.
- The improved “fill and drain” tool which reduces the service time when handling water (including discontinuing a server).