|
Coming this Fall to IBM Z, LinuxONE and Power, IBM Spyre Accelerator Enables Enterprises to Scale Generative and Agentic AI Workloads
ARMONK, N.Y., Oct. 7, 2025 /PRNewswire/ -- IBM (NYSE: IBM) today announced the upcoming general availability of the IBM Spyre Accelerator, an AI accelerator enabling low-latency inferencing to support generative and agentic AI use cases while prioritizing the security and resilience of core workloads. Earlier this year, IBM announced the Spyre Accelerator would be available in IBM z17, LinuxONE 5, and Power11 systems. Spyre will be generally available on October 28 for IBM z17 and LinuxONE 5 systems, and in early December for Power11 servers.
Today's IT landscape is changing from traditional logic workflows to agentic AI inferencing. AI agents require low-latency inference and real-time system responsiveness. IBM recognized the need for mainframes and servers to run AI models along with the most demanding enterprise workloads without compromising on throughput. To address this demand, clients need AI inferencing hardware that supports generative and agentic AI while maintaining the security and resilience of core data, transactions, and applications. The accelerator is also built to enable clients to keep mission-critical data on-prem to mitigate risk while addressing operational and energy efficiency.
The IBM Spyre Accelerator reflects the strength of IBM's research-to-product pipeline, combining breakthrough innovation from the IBM Research AI Hardware Center with enterprise-grade development from IBM Infrastructure. Initially introduced as a prototype chip, Spyre was refined through rapid iteration, including cluster deployments at IBM's Yorktown Heights campus, and with collaborators like the University at Albany's Center for Emerging Artificial Intelligence Systems.
The IBM Research prototype has evolved into an enterprise-grade product for use in IBM Z, LinuxONE and Power systems. Today, the Spyre Accelerator is a commercial system-on-a-chip with 32 individual accelerator cores and 25.6 billion transistors. Produced using 5nm node technology, each Spyre is mounted on a 75-watt PCIe card, which makes it possible to cluster up to 48 cards in an IBM Z or LinuxONE system or 16 cards in an IBM Power system to scale AI capabilities.
"One of our key priorities has been advancing infrastructure to meet the demands of new and emerging AI workloads," said Barry Baker, COO, IBM Infrastructure & GM, IBM Systems. "With the Spyre Accelerator, we're extending the capabilities of our systems to support multi-model AI – including generative and agentic AI. This innovation positions clients to scale their AI-enabled mission-critical workloads with uncompromising security, resilience, and efficiency, while unlocking the value of their enterprise data."
"We launched the IBM Research AI Hardware Center in 2019 with a mission to meet the rising computational demands of AI, even before the surge in LLMs and AI models we've recently seen," said Mukesh Khare, GM of IBM Semiconductors and VP of Hybrid Cloud, IBM. "Now, amid increasing demand for advanced AI capabilities, we're proud to see the first chip from the Center enter commercialization, designed to deliver improved performance and productivity to IBM's mainframe and server clients."
For IBM clients, Spyre Accelerators offer fast, secured processing with on-prem AI acceleration. This marks a significant milestone, allowing businesses to leverage AI at scale while keeping data on IBM Z, LinuxONE and Power systems. In mainframe systems, coupled with the Telum II processor for IBM Z and LinuxONE, Spyre offers enhanced security, low latency, and high transaction rate processing power. Leveraging this advanced hardware and software stack, businesses can use Spyre to scale multiple AI models to power predictive use cases such as advanced fraud detection and retail automation.
On IBM Power-based servers, Spyre customers can leverage a catalog of AI services, enabling end-to-end AI for enterprise workflows. Clients can install the AI services from the catalog with just one click.1 Spyre Accelerator for Power, combined with an on-chip accelerator (MMA), also accelerates data conversion for generative AI to deliver high throughput for deep process integrations. Additionally, with a prompt size of 128, it enables the ingestion of more than 8 million documents for knowledge base integration in an hour2. This performance, combined with the IBM software stack, security, scalability, and energy efficiency, supports clients on their journey to integrating generative AI frameworks into their enterprise workloads.
To learn more about the IBM Spyre Accelerator, visit http://www.ibm.com/solutions/ai-accelerator.
Additional resources:
About IBM
IBM is a leading provider of global hybrid cloud and AI, and consulting expertise. We help clients in more than 175 countries capitalize on insights from their data, streamline business processes, reduce costs and gain a competitive edge in their industries. Thousands of governments and corporate entities in critical infrastructure areas such as financial services, telecommunications and healthcare rely on IBM's hybrid cloud platform and Red Hat OpenShift to affect their digital transformations quickly, efficiently and securely. IBM's breakthrough innovations in AI, quantum computing, industry-specific cloud solutions and consulting deliver open and flexible options to our clients. All of this is backed by IBM's long-standing commitment to trust, transparency, responsibility, inclusivity and service. Visit www.ibm.com for more information.
Media Contacts
Willa Hahn, willa.hahn@ibm.com
Chase Skinner, Chase.Skinner@ibm.com
1 AI service of the IBM-supported catalog is delivered as one or a set of containers that can be deployed with a single deployment command. The provided UI for the catalog executes such commands in the backend based on a single click within the UI page of the respective AI service.
2 Based upon internal testing running 1M unit data set with prompt size 128, batch size 128 using 1-card container. Individual results may vary based on workload size, use of storage subsystems and other conditions.
Coming this Fall to IBM Z, LinuxONE and Power, IBM Spyre Accelerator Enables Enterprises to Scale Generative and Agentic AI Workloads
ARMONK, N.Y., Oct. 7, 2025 /PRNewswire/ -- IBM (NYSE: IBM) today announced the upcoming general availability of the IBM Spyre Accelerator, an AI accelerator enabling low-latency inferencing to support generative and agentic AI use cases while prioritizing the security and resilience of core workloads. Earlier this year, IBM announced the Spyre Accelerator would be available in IBM z17, LinuxONE 5, and Power11 systems. Spyre will be generally available on October 28 for IBM z17 and LinuxONE 5 systems, and in early December for Power11 servers.
Today's IT landscape is changing from traditional logic workflows to agentic AI inferencing. AI agents require low-latency inference and real-time system responsiveness. IBM recognized the need for mainframes and servers to run AI models along with the most demanding enterprise workloads without compromising on throughput. To address this demand, clients need AI inferencing hardware that supports generative and agentic AI while maintaining the security and resilience of core data, transactions, and applications. The accelerator is also built to enable clients to keep mission-critical data on-prem to mitigate risk while addressing operational and energy efficiency.
The IBM Spyre Accelerator reflects the strength of IBM's research-to-product pipeline, combining breakthrough innovation from the IBM Research AI Hardware Center with enterprise-grade development from IBM Infrastructure. Initially introduced as a prototype chip, Spyre was refined through rapid iteration, including cluster deployments at IBM's Yorktown Heights campus, and with collaborators like the University at Albany's Center for Emerging Artificial Intelligence Systems.
The IBM Research prototype has evolved into an enterprise-grade product for use in IBM Z, LinuxONE and Power systems. Today, the Spyre Accelerator is a commercial system-on-a-chip with 32 individual accelerator cores and 25.6 billion transistors. Produced using 5nm node technology, each Spyre is mounted on a 75-watt PCIe card, which makes it possible to cluster up to 48 cards in an IBM Z or LinuxONE system or 16 cards in an IBM Power system to scale AI capabilities.
"One of our key priorities has been advancing infrastructure to meet the demands of new and emerging AI workloads," said Barry Baker, COO, IBM Infrastructure & GM, IBM Systems. "With the Spyre Accelerator, we're extending the capabilities of our systems to support multi-model AI – including generative and agentic AI. This innovation positions clients to scale their AI-enabled mission-critical workloads with uncompromising security, resilience, and efficiency, while unlocking the value of their enterprise data."
"We launched the IBM Research AI Hardware Center in 2019 with a mission to meet the rising computational demands of AI, even before the surge in LLMs and AI models we've recently seen," said Mukesh Khare, GM of IBM Semiconductors and VP of Hybrid Cloud, IBM. "Now, amid increasing demand for advanced AI capabilities, we're proud to see the first chip from the Center enter commercialization, designed to deliver improved performance and productivity to IBM's mainframe and server clients."
For IBM clients, Spyre Accelerators offer fast, secured processing with on-prem AI acceleration. This marks a significant milestone, allowing businesses to leverage AI at scale while keeping data on IBM Z, LinuxONE and Power systems. In mainframe systems, coupled with the Telum II processor for IBM Z and LinuxONE, Spyre offers enhanced security, low latency, and high transaction rate processing power. Leveraging this advanced hardware and software stack, businesses can use Spyre to scale multiple AI models to power predictive use cases such as advanced fraud detection and retail automation.
On IBM Power-based servers, Spyre customers can leverage a catalog of AI services, enabling end-to-end AI for enterprise workflows. Clients can install the AI services from the catalog with just one click.1 Spyre Accelerator for Power, combined with an on-chip accelerator (MMA), also accelerates data conversion for generative AI to deliver high throughput for deep process integrations. Additionally, with a prompt size of 128, it enables the ingestion of more than 8 million documents for knowledge base integration in an hour2. This performance, combined with the IBM software stack, security, scalability, and energy efficiency, supports clients on their journey to integrating generative AI frameworks into their enterprise workloads.
To learn more about the IBM Spyre Accelerator, visit http://www.ibm.com/solutions/ai-accelerator.
Additional resources:
About IBM
IBM is a leading provider of global hybrid cloud and AI, and consulting expertise. We help clients in more than 175 countries capitalize on insights from their data, streamline business processes, reduce costs and gain a competitive edge in their industries. Thousands of governments and corporate entities in critical infrastructure areas such as financial services, telecommunications and healthcare rely on IBM's hybrid cloud platform and Red Hat OpenShift to affect their digital transformations quickly, efficiently and securely. IBM's breakthrough innovations in AI, quantum computing, industry-specific cloud solutions and consulting deliver open and flexible options to our clients. All of this is backed by IBM's long-standing commitment to trust, transparency, responsibility, inclusivity and service. Visit www.ibm.com for more information.
Media Contacts
Willa Hahn, willa.hahn@ibm.com
Chase Skinner, Chase.Skinner@ibm.com
1 AI service of the IBM-supported catalog is delivered as one or a set of containers that can be deployed with a single deployment command. The provided UI for the catalog executes such commands in the backend based on a single click within the UI page of the respective AI service.
2 Based upon internal testing running 1M unit data set with prompt size 128, batch size 128 using 1-card container. Individual results may vary based on workload size, use of storage subsystems and other conditions.
** The press release content is from PR Newswire. Bastille Post is not involved in its creation. **
IBM Introduces the Spyre Accelerator for Commercial Availability
Upcoming openings include hotels, resorts, and residences—spanning Greece, Italy, Saudi Arabia, the United Arab Emirates, and the United States— underscoring the Group's commitment to global, quality‑driven expansion.
HONG KONG, Dec. 19, 2025 /PRNewswire/ -- Rosewood Hotel Group ("the Group") today announces continued expansion of its global development pipeline with the on-schedule opening of Rosewood Courchevel Le Jardin Alpin, the Group's first ski resort. A landmark debut for the brand, the new alpine retreat marks Rosewood's entry into a new sector and reinforces the Group's presence across some of the world's most sought after destinations and high-growth markets.
This debut follows seven on-track openings in 2025, including the milestone launch of Rosewood's first standalone residential property available for exclusive sale, Rosewood Residences Beverly Hills in the United States, reaffirming the Group's expansion into the luxury residential category and its strategic focus to redefine private branded residences by creating neighborhood landmarks that appreciate in both emotional and financial value. Together with the forthcoming launch of Rosewood AMAALA in Saudi Arabia, set to bring an ultra-luxury regenerative escape to the Red Sea region. These additions underscore the Group's commitment to quality‑driven expansion and elevating operational excellence across its global portfolio.
Sonia Cheng, Chief Executive Officer of Rosewood Hotel Group, said: "Rosewood Courchevel Le Jardin Alpin, our first ski resort, is a milestone that reflects our long‑term commitment to thoughtfully expanding our global portfolio and our ability to enter new, experience-driven sectors."
"We are guided by a clear ambition: to grow with purpose, to create enduring value, and to deliver transformative experiences that resonate with our communities. As we bring our brands to the world's most extraordinary destinations, our vision and commitment remain focused on quality, innovation, and the sustainable success of our global business. I am grateful for the ongoing support and trust from our associates, guests, and partners."
Strategic Expansion in 2025
The opening of Rosewood Courchevel Le Jardin Alpin brings the total number of openings for Rosewood Hotel Group in 2025 to eight across three continents – comprising seven properties under Rosewood, including a standalone Rosewood Residences, and New World Jinzhou Hotel.
Nestled in the exclusive village of Courchevel 1850, Rosewood Courchevel Le Jardin Alpin brings the brand's signature refined, residential‑style luxury to one of the world's most celebrated ski destinations. Anchoring the resort's connection to art and place, the lobby features an installation by renowned artist Olafur Eliasson - two crystalline structures suspended within mirrored walls and ceilings, creating the illusion of infinite, snowflake-inspired forms. The resort also offers luxury accommodations, elevated dining concepts, curated wellness experiences, and direct ski‑in/ski‑out access, providing guests with an intimate retreat that celebrates the distinct character and natural beauty of the French Alps.
From the French Alps to the dramatic sand dunes surrounding Qatar's cityscape lies Rosewood Doha's coral-inspired mashrabiya, to revitalizing heritage sites such as Rosewood Amsterdam and The Chancery Rosewood – the new era of Rosewood is one defined by catalyzing the future of place. This vision extends across a diverse portfolio of iconic openings in 2025: the lush coastal retreat of Rosewood Mandarina in Mexico, the idyllic Rosewood Miyakojima in Japan, the sophisticated Rosewood Residence in Beverly Hills, and the contemporary New World Jinzhou Hotel in China's vibrant port city. See Editor's Note for the full list of properties.
Expanding with Purpose Across New Destinations
Rosewood's upcoming openings further demonstrate the Group's thoughtful approach to development, with each property designed to deliver a deeper connection to each place and community. Some anticipated openings include:
- Rosewood AMAALA — An ultra‑luxury regenerative retreat on Saudi Arabia's Red Sea coast, set between the world's fourth‑largest barrier reef and the scenic Hijazi mountains, designed to harmonise wellness, sustainability, and the surrounding natural landscape.
- Rosewood Red Sea — Located along Saudi Arabia's west coast on the Shura Island, the property will be part of The Red Sea destination. Poised to be one of Saudi Arabia's top cultural and lifestyle hubs, the development is comprised of a stunning marina offering a yacht club, commercial retail and dining options, as well as an 18-hole championship golf course.
- Rosewood Blue Palaceand Rosewood Residence Crete — Rosewood's entrance into Greece. A coastal retreat woven seamlessly into the island's landscape, honouring Crete's rich cultural heritage.
- Rosewood Rome — Located in the former headquarters of Italy's Banca Nazionale del Lavoro (BNL), an urban retreat spanning three historic early‑1900s buildings on Via Veneto, blending timeless Roman elegance with contemporary design, complete with a rooftop Asaya Spa, modern Roman Bathhouse, and sweeping city views.
- Rosewood Calistoga and Rosewood Residences Calistoga — A contemporary hillside estate where forest, vine, and sky converge, inviting guests into a modern yet soulful sanctuary rooted in terroir, togetherness, and the quiet magic of Napa's natural rhythm.
- Rosewood Dubai and Rosewood Residences Dubai — Set on the shores of Peninsula Dubai, an upcoming landmark destination within the city's most prestigious waterfront district.
- Rosewood Residences Turtle Creek — Honouring the legacy of the Rosewood Mansion on Turtle Creek in Dallas, this landmark collection of residences sets a new standard for high-rise living in one of the country's most coveted communities.
- Rosewood Residences Lido Key — Situated along one of the country's most beautiful beaches, the elegant residences are set among pristine white sands and overlook the Gulf of Mexico.
Strengthening Presence in the Gulf Cooperation Council (GCC)
The forthcoming opening of Rosewood AMAALA builds on the Group's expanding presence in the GCC, joining Rosewood Doha, Rosewood Abu Dhabi, and the upcoming Rosewood Dubai. As one of the region's most anticipated ultra‑luxury developments, Rosewood AMAALA reinforces the Group's commitment to entering experience‑rich markets and shaping the next generation of transformative travel.
Each destination has been carefully selected for its exceptional market potential and cultural significance, showcasing the Group's commitment to meeting evolving traveller desires for new destinations, cultural immersion, and luxury hospitality.
Editor's Note:
Property openings in 2025:
Property photos are available for download here.
About Rosewood Hotel Group
Rosewood Hotel Group, privately owned by Chow Tai Fook Enterprises, is one of the world's leading global lifestyle and hospitality management groups. It encompasses four brands: ultra-luxury Rosewood; upper-upscale New World Hotels & Resorts; Asaya, an integrated well-being concept; and Carlyle & Co., a modern and progressive private members club. Its combined hotel portfolio consists of 59 properties in 26 countries with more than 30 new properties currently under development. For more information, visit rosewoodhotelgroup.com.
** The press release content is from PR Newswire. Bastille Post is not involved in its creation. **
Rosewood Hotel Group Accelerates Global Expansion with On-Track 2025 Openings; Entering New Sector with Its First-Ever Ski Resort
